~ / leaderboard

Component leaderboard

Ranked by number of independent rigs using each component (not install counts). MCP servers are matched by package, image or remote host; skills and subagents by name, listed when they appear in 4+ rigs.

#nametyperigs
1 Context7 npm · ~1.2k tok 309
2 Playwright MCP binary · ~7.5k tok 223
3 GitHub MCP remote · ~18.0k tok 176
4 Chrome DevTools MCP npm · ~9.0k tok 114
5 Sequential Thinking npm · ~900 tok 87
6 Filesystem npm · ~4.2k tok 77
7 Linear npm · ~5.5k tok 67
8 Notion npm · ~6.0k tok 64
9 Exa remote · ~1.5k tok 62
10 Memory (knowledge graph) npm · ~2.6k tok 59
11 Atlassian remote · ~10.0k tok 58
12 Figma npm · ~3.0k tok 51
13 Serena git · ~8.0k tok 45
14 Slack npm · ~3.5k tok 41
15 shadcn/ui npm · ~2.0k tok 40
16 Fetch pypi · ~450 tok 39
17 Postgres npm · ~600 tok 38
18 DeepWiki remote · ~900 tok 37
19 Sentry remote · ~4.5k tok 36
20 Supabase remote · ~7.0k tok 32
21 CodeGraph npm · ~3.0k tok 27
22 AWS Documentation pypi · ~1.5k tok 26
23 Cloudflare remote · ~4.0k tok 24
24 Microsoft Learn Docs remote · ~1.2k tok 24
25 mcp.grep.app remote · ~2.5k tok 23
26 Brave Search npm · ~900 tok 21
27 Git pypi · ~3.2k tok 19
28 Firecrawl npm · ~5.0k tok 16
29 OpenAI Developer Docs remote · ~1.0k tok 16
30 tsx npm · ~2.5k tok 16
31 codebase-memory-mcp binary · ~2.5k tok 14
32 Puppeteer npm · ~2.2k tok 14
33 Tavily npm · ~2.0k tok 13
34 Vercel remote · ~4.0k tok 13
35 code-review-graph pypi · ~2.5k tok 12
36 docker binary · ~2.5k tok 12
37 mcp.datadoghq.com remote · ~2.5k tok 12
38 nix binary · ~2.5k tok 12
39 ${claude_plugin_root} pypi · ~2.5k tok 11
40 Excalidraw npm · ~2.0k tok 11
41 markitdown-mcp pypi · ~2.5k tok 11
42 mcp-proxy-for-aws pypi · ~2.5k tok 11
43 Next.js DevTools npm · ~2.5k tok 11
44 Perplexity npm · ~1.0k tok 11
45 @azure/mcp npm · ~2.5k tok 10
46 knowledge-mcp.global.api.aws remote · ~2.5k tok 10
47 mcp pypi · ~2.5k tok 10
48 mise binary · ~2.5k tok 9
49 Stripe npm · ~6.0k tok 9
50 graft binary · ~2.5k tok 8
51 hashicorp/terraform-mcp-server docker · ~2.5k tok 8
52 mcp-remote npm · ~2.5k tok 8
53 mcp.neon.tech remote · ~2.5k tok 8
54 python pypi · ~2.5k tok 8
55 . pypi · ~2.5k tok 7
56 21st.dev Magic npm · ~1.5k tok 7
57 dart binary · ~2.5k tok 7
58 huggingface.co remote · ~2.5k tok 7
59 mcp.asana.com remote · ~2.5k tok 7
60 mcp.example.com remote · ~2.5k tok 7
61 qmd binary · ~2.5k tok 7
62 Todoist remote · ~3.0k tok 7
63 @mobilenext/mobile-mcp npm · ~2.5k tok 6
64 awslabs.aws-iac-mcp-server pypi · ~2.5k tok 6
65 awslabs.aws-pricing-mcp-server pypi · ~2.5k tok 6
66 code-review-graph binary · ~2.5k tok 6
67 codex binary · ~2.5k tok 6
68 headroom binary · ~2.5k tok 6
69 maestro binary · ~2.5k tok 6
70 mcp.amplitude.com remote · ~2.5k tok 6
71 mcp.apify.com remote · ~2.5k tok 6
72 mcp.higgsfield.ai remote · ~2.5k tok 6
73 mcp.posthog.com remote · ~2.5k tok 6
74 mcp.svelte.dev remote · ~2.5k tok 6
75 @angular/cli npm · ~2.5k tok 5
76 @coding-solo/godot-mcp npm · ~2.5k tok 5
77 @hypothesi/tauri-mcp-server npm · ~2.5k tok 5
78 @next-ai-drawio/mcp-server npm · ~2.5k tok 5
79 arxiv-mcp-server pypi · ~2.5k tok 5
80 cmd binary · ~2.5k tok 5
81 fff-mcp binary · ~2.5k tok 5
82 gh binary · ~2.5k tok 5
83 grepai binary · ~2.5k tok 5
84 kubernetes-mcp-server npm · ~2.5k tok 5
85 mcp-nixos binary · ~2.5k tok 5
86 mcp-server-sqlite pypi · ~2.5k tok 5
87 mcp.hubspot.com remote · ~2.5k tok 5
88 rea-agents npm · ~2.5k tok 5
89 superlogical.com remote · ~2.5k tok 5
90 task-master-ai npm · ~2.5k tok 5
91 tessl binary · ~2.5k tok 5
92 Time pypi · ~500 tok 5
93 @executeautomation/playwright-mcp-server npm · ~2.5k tok 4
94 @modelcontextprotocol/server-everything npm · ~2.5k tok 4
95 @modelcontextprotocol/server-redis npm · ~2.5k tok 4
96 awslabs.cloudwatch-mcp-server pypi · ~2.5k tok 4
97 bigquery.googleapis.com remote · ~2.5k tok 4
98 convex npm · ~2.5k tok 4
99 dnx binary · ~2.5k tok 4
100 docs.langchain.com remote · ~2.5k tok 4
101 fastmcp pypi · ~2.5k tok 4
102 firebase-tools npm · ~2.5k tok 4
103 gopls (Go) binary · ~2.5k tok 4
104 mcp-grafana pypi · ~2.5k tok 4
105 mcp-nixos pypi · ~2.5k tok 4
106 mcp.box.com remote · ~2.5k tok 4
107 mcp.expo.dev remote · ~2.5k tok 4
108 mcp.intercom.com remote · ~2.5k tok 4
109 mcp.miro.com remote · ~2.5k tok 4
110 mcp/sonarqube docker · ~2.5k tok 4
111 memory binary · ~2.5k tok 4
112 microsoft365.mcp.claude.com remote · ~2.5k tok 4
113 MongoDB npm · ~6.0k tok 4
114 playwright npm · ~2.5k tok 4
115 ruflo npm · ~2.5k tok 4
116 semble[mcp] pypi · ~2.5k tok 4
117 xcodebuildmcp npm · ~2.5k tok 4
118 xcrun binary · ~2.5k tok 4
119 ${claude_plugin_root}/mcp/dist/server.js npm · ~2.5k tok 3
120 3.12 pypi · ~2.5k tok 3
121 @anthropic-ai/mcp-fetch npm · ~2.5k tok 3
122 @anthropic/mcp-slack npm · ~2.5k tok 3
123 @anthropic/playwright-mcp npm · ~2.5k tok 3
124 @bytebase/dbhub npm · ~2.5k tok 3
125 @context7/mcp-server npm · ~2.5k tok 3
126 @google-cloud/gcloud-mcp npm · ~2.5k tok 3
127 @modelcontextprotocol/server-gitlab npm · ~2.5k tok 3
128 @modelcontextprotocol/server-google-maps npm · ~2.5k tok 3
129 @netlify/mcp npm · ~2.5k tok 3
130 @railway/mcp-server npm · ~2.5k tok 3
131 @z_ai/mcp-server npm · ~2.5k tok 3
132 agent-device npm · ~2.5k tok 3
133 app.hex.tech remote · ~2.5k tok 3
134 argocd-mcp npm · ~2.5k tok 3
135 aspire binary · ~2.5k tok 3
136 awslabs.amazon-bedrock-agentcore-mcp-server pypi · ~2.5k tok 3
137 awslabs.aws-api-mcp-server pypi · ~2.5k tok 3
138 awslabs.aws-diagram-mcp-server pypi · ~2.5k tok 3
139 awslabs.core-mcp-server pypi · ~2.5k tok 3
140 awslabs.well-architected-security-mcp-server pypi · ~2.5k tok 3
141 blender-mcp pypi · ~2.5k tok 3
142 calendarmcp.googleapis.com remote · ~2.5k tok 3
143 code.claude.com remote · ~2.5k tok 3
144 component-explorer npm · ~2.5k tok 3
145 connector.scholargateway.ai remote · ~2.5k tok 3
146 context-mode npm · ~2.5k tok 3
147 developerknowledge.googleapis.com remote · ~2.5k tok 3
148 drivemcp.googleapis.com remote · ~2.5k tok 3
149 duckduckgo-mcp-server pypi · ~2.5k tok 3
150 engram binary · ~2.5k tok 3
151 env binary · ~2.5k tok 3
152 example-search-mcp npm · ~2.5k tok 3
153 example.com remote · ~2.5k tok 3
154 git binary · ~2.5k tok 3
155 gitmcp.io remote · ~2.5k tok 3
156 gmailmcp.googleapis.com remote · ~2.5k tok 3
157 Granola remote · ~1.5k tok 3
158 ios-simulator-mcp npm · ~2.5k tok 3
159 mcp-server-docker pypi · ~2.5k tok 3
160 mcp.api.getguru.com remote · ~2.5k tok 3
161 mcp.apollo.io remote · ~2.5k tok 3
162 mcp.canva.com remote · ~2.5k tok 3
163 mcp.developerz.ai remote · ~2.5k tok 3
164 mcp.devin.ai remote · ~2.5k tok 3
165 mcp.docs.astro.build remote · ~2.5k tok 3
166 mcp.heygen.com remote · ~2.5k tok 3
167 mcp.k.owkin.com remote · ~2.5k tok 3
168 mcp.monday.com remote · ~2.5k tok 3
169 mcp.platform.opentargets.org remote · ~2.5k tok 3
170 mcp.services.biorender.com remote · ~2.5k tok 3
171 mcp.socket.dev remote · ~2.5k tok 3
172 mcp.synapse.org remote · ~2.5k tok 3
173 nx npm · ~2.5k tok 3
174 pando binary · ~2.5k tok 3
175 pubmed.mcp.claude.com remote · ~2.5k tok 3
176 radius.pi.dev remote · ~2.5k tok 3
177 ui.nuxt.com remote · ~2.5k tok 3
178 pypi · ~2.5k tok 2
179 ${claude_plugin_root:-.} pypi · ~2.5k tok 2
180 ${plugin_data} npm · ~2.5k tok 2
181 @anthropic-ai/mcp-playwright npm · ~2.5k tok 2
182 @anthropic/mcp-filesystem npm · ~2.5k tok 2
183 @anthropic/mcp-github npm · ~2.5k tok 2
184 @anthropic/mcp-jira npm · ~2.5k tok 2
185 @anthropic/mcp-memory npm · ~2.5k tok 2
186 @anthropic/mcp-postgres npm · ~2.5k tok 2
187 @apify/actors-mcp-server npm · ~2.5k tok 2
188 @auth0/auth0-mcp-server npm · ~2.5k tok 2
189 @browsermcp/mcp npm · ~2.5k tok 2
190 @claude-flow/cli npm · ~2.5k tok 2
191 @cloudbase/cloudbase-mcp npm · ~2.5k tok 2
192 @context7/mcp npm · ~2.5k tok 2
193 @darkmoon_ai/mcp-server npm · ~2.5k tok 2
194 @datadog/mcp-server npm · ~2.5k tok 2
195 @drawio/mcp npm · ~2.5k tok 2
196 @formhaus/mcp npm · ~2.5k tok 2
197 @mastergo/magic-mcp npm · ~2.5k tok 2
198 @matematicsolutions/mcp-eu-sparql npm · ~2.5k tok 2
199 @modelcontextprotocol/server-docker npm · ~2.5k tok 2
200 @modelcontextprotocol/server-everart npm · ~2.5k tok 2
201 @modelcontextprotocol/server-sqlite npm · ~2.5k tok 2
202 @mozilla/firefox-devtools-mcp npm · ~2.5k tok 2
203 @negokaz/excel-mcp-server npm · ~2.5k tok 2
204 @neondatabase/mcp-server-neon npm · ~2.5k tok 2
205 @neuraforge/office-mcp npm · ~2.5k tok 2
206 @vercel/mcp-adapter npm · ~2.5k tok 2
207 @zereight/mcp-gitlab npm · ~2.5k tok 2
208 aeon.fun remote · ~2.5k tok 2
209 agent-baton binary · ~2.5k tok 2
210 agentsview binary · ~2.5k tok 2
211 amem binary · ~2.5k tok 2
212 api.ahrefs.com remote · ~2.5k tok 2
213 api.anthropic.com remote · ~2.5k tok 2
214 api.datacircle.dev remote · ~2.5k tok 2
215 api.definite.app remote · ~2.5k tok 2
216 api.fabric.microsoft.com remote · ~2.5k tok 2
217 api.github.com remote · ~2.5k tok 2
218 api.greptile.com remote · ~2.5k tok 2
219 api.mobbin.com remote · ~2.5k tok 2
220 api.n8n-mcp.com remote · ~2.5k tok 2
221 api.ref.tools remote · ~2.5k tok 2
222 api.refero.design remote · ~2.5k tok 2
223 api.superset.sh remote · ~2.5k tok 2
224 api.z.ai remote · ~2.5k tok 2
225 at-eli-mcp pypi · ~2.5k tok 2
226 aws-mcp.eu-central-1.api.aws remote · ~2.5k tok 2
227 aws-mcp.us-east-1.api.aws remote · ~2.5k tok 2
228 awslabs.aurora-dsql-mcp-server pypi · ~2.5k tok 2
229 awslabs.cdk-mcp-server pypi · ~2.5k tok 2
230 awslabs.eks-mcp-server pypi · ~2.5k tok 2
231 awslabs.iam-mcp-server pypi · ~2.5k tok 2
232 awslabs.mysql-mcp-server pypi · ~2.5k tok 2
233 awslabs.sagemaker-ai-mcp-server pypi · ~2.5k tok 2
234 better-design.com remote · ~2.5k tok 2
235 bun.com remote · ~2.5k tok 2
236 claude binary · ~2.5k tok 2
237 claude-code-wechat-channel npm · ~2.5k tok 2
238 clock-of-companion binary · ~2.5k tok 2
239 codebase-memory-mcp npm · ~2.5k tok 2
240 cohesivity.ai remote · ~2.5k tok 2
241 companion-server binary · ~2.5k tok 2
242 computefirst.net remote · ~2.5k tok 2
243 conductor binary · ~2.5k tok 2
244 connect.composio.dev remote · ~2.5k tok 2
245 connect.mcp.tedix.dev remote · ~2.5k tok 2
246 context-mode binary · ~2.5k tok 2
247 dataforseo-mcp-server npm · ~2.5k tok 2
248 de-eli-mcp pypi · ~2.5k tok 2
249 decomp binary · ~2.5k tok 2
250 deja binary · ~2.5k tok 2
251 deskcrew.io remote · ~2.5k tok 2
252 Desktop Commander npm · ~7.0k tok 2
253 docs-mcp.avaloniaui.net remote · ~2.5k tok 2
254 dos-mcp binary · ~2.5k tok 2
255 droit-francais-skill.onrender.com remote · ~2.5k tok 2
256 e2e npm · ~2.5k tok 2
257 elevenlabs-mcp pypi · ~2.5k tok 2
258 engram-serve binary · ~2.5k tok 2
259 es-eli-mcp pypi · ~2.5k tok 2
260 fetcher-mcp npm · ~2.5k tok 2
261 fi-eli-mcp pypi · ~2.5k tok 2
262 flurryx-code-memory pypi · ~2.5k tok 2
263 fr-eli-mcp pypi · ~2.5k tok 2
264 gcal.mcp.claude.com remote · ~2.5k tok 2
265 get-skill npm · ~2.5k tok 2
266 github-mcp binary · ~2.5k tok 2
267 github-mcp-server binary · ~2.5k tok 2
268 gitlab.com remote · ~2.5k tok 2
269 gitnexus binary · ~2.5k tok 2
270 gmail.mcp.claude.com remote · ~2.5k tok 2
271 grafana/mcp-grafana docker · ~2.5k tok 2
272 graphify-mcp binary · ~2.5k tok 2
273 graphifyy pypi · ~2.5k tok 2
274 graphifyy[mcp] pypi · ~2.5k tok 2
275 helius-mcp npm · ~2.5k tok 2
276 hive binary · ~2.5k tok 2
277 https://registry.npmjs.org npm · ~2.5k tok 2
278 ie-eli-mcp pypi · ~2.5k tok 2
279 kabo.sh remote · ~2.5k tok 2
280 kaggle.com remote · ~2.5k tok 2
281 kcap binary · ~2.5k tok 2
282 kfinance.kensho.com remote · ~2.5k tok 2
283 linkedin-scraper-mcp pypi · ~2.5k tok 2
284 logfire-eu.pydantic.dev remote · ~2.5k tok 2
285 lu-eli-mcp pypi · ~2.5k tok 2
286 marionette_mcp binary · ~2.5k tok 2
287 mcp-fetch pypi · ~2.5k tok 2
288 mcp-fetch-server npm · ~2.5k tok 2
289 mcp-for-blender pypi · ~2.5k tok 2
290 mcp-grafana binary · ~2.5k tok 2
291 mcp-language-server binary · ~2.5k tok 2
292 mcp-obsidian pypi · ~2.5k tok 2
293 mcp-obsidian binary · ~2.5k tok 2
294 mcp-proxy-for-aws-cli pypi · ~2.5k tok 2
295 mcp-server pypi · ~2.5k tok 2
296 mcp-server-docker npm · ~2.5k tok 2
297 mcp-server-filesystem binary · ~2.5k tok 2
298 mcp-server-filesystem pypi · ~2.5k tok 2
299 mcp-server-github binary · ~2.5k tok 2
300 mcp-server-kubernetes npm · ~2.5k tok 2
#namerigs
1 handoff
Compact the current conversation into a handoff document for another agent to pick up.
527
2 code-review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what
450
3 review
>
422
4 grill-me
A relentless interview to sharpen a plan or design.
378
5 frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defau
374
6 tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
374
7 skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill
363
8 setup
>-
360
9 release
>-
347
10 commit
>
342
11 research
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading le
307
12 grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
275
13 plan
>
257
14 brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
239
15 systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
234
16 implement
Implement a piece of work based on a spec or set of tickets.
230
17 verify
>-
226
18 ship
>-
221
19 domain-modeling
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
212
20 grill-with-docs
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
212
21 prototype
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
208
22 test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
207
23 retro
Conduct a retrospective on a coding session.
202
24 improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
197
25 find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This sk
195
26 triage
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.
195
27 teach
Teach the user a new skill or concept, within this workspace.
191
28 status
>
185
29 audit
>
182
30 pr
Use when writing a PR body.
182
31 codebase-design
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-n
181
32 security-review
Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and
177
33 unslop
Cut AI tells from any writing. Must always apply.
165
34 debug
>
161
35 diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
161
36 security-audit
Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions, focused reviews, vulnerability research, security audits, or pe
160
37 agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web a
150
38 caveman
>
148
39 design
>-
147
40 verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence
147
41 writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
147
42 init
>
145
43 humanizer
|
140
44 writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
140
45 api-design
REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.
137
46 spec
>
128
47 mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate externa
125
48 learn
|
124
49 to-spec
Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.
121
50 wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
120
51 orchestrate
>-
118
52 pdf
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rota
118
53 recall
Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recal
117
54 architect
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping
116
55 to-tickets
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locall
115
56 receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative
113
57 deep-research
Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any to
112
58 git-workflow
Git workflow patterns including branching strategies, commit conventions, merge vs rebase, conflict resolution, and collaborative development best practices for teams of all sizes.
111
59 refactor
>-
111
60 reflect
Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.
111
61 executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
110
62 onboard
Design or improve onboarding flows, empty states, and first-time user experiences. Helps users get started successfully and understand value quickly.
110
63 brainstorm
>
109
64 openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
109
65 openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
109
66 web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
109
67 openspec-apply-change
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
108
68 pr-review
>
107
69 doctor
>
106
70 using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
105
71 subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
104
72 review-pr
>
103
73 ui-ux-pro-max
UI/UX design intelligence for web, mobile, and desktop. This skill should be used when designing, building, reviewing, or fixing interfaces, including pages, components, design systems, accessibility,
103
74 vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patter
102
75 diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", report
101
76 openspec-propose
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for i
101
77 ponytail
>
99
78 requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
99
79 testing
>
99
80 writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
99
81 deploy
|
98
82 design-system
<redacted>, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use
96
83 explain
>-
95
84 webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser l
95
85 bro
Restate the last message in plain human language, with no jargon.
94
86 impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers we
93
87 technical-writing
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RF
93
88 create-pr
>
92
89 finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
92
90 seo-audit
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tag
92
91 dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
90
92 architecture
Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.
89
93 why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source contro
89
94 setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
88
95 herdr
Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent
87
96 wait-what
Stop. That last message did not land: re-pitch it.
87
97 docx
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (
86
98 playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
86
99 start
>
85
100 openspec-sync-specs
Sync delta specs from an OpenSpec change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change. Also use when the user says "openspec
84
101 qa
Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wan
82
102 release-notes
Generate release notes in multiple formats from git commits
82
103 wizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-part
82
104 blast-radius
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X',
81
105 coding-standards
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
81
106 fix
>
81
107 tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
81
108 graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first.
79
109 design-review
|
78
110 design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design system
77
111 create-verification-skill
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, \"make a control skill for this repo\",
75
112 deslop
Remove AI-generated code slop and clean up code style
75
113 council
Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.
73
114 git-commit
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (
73
115 copywriting
When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user s
72
116 frontend-patterns
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
72
117 sync
>
72
118 to-questionnaire
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
72
119 how
Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should this live\", \"which package owns this\", \"is this the right l
71
120 adr
>-
70
121 docs
>-
70
122 memory
Search, store, compress, and recall memories across the Energy platform. Semantic search over LEARNINGS.md, daily logs, vault notes, and rules.
70
123 pptx
Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting te
70
124 security
Rapid security assessment focused on OWASP Top 10 vulnerabilities
70
125 accessibility
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make
68
126 backend-patterns
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
68
127 debugging
系统化问题调试。通过复现、定位根因、编写回归测试、修复验证的闭环流程,快速稳定地解决问题。
67
128 resolving-merge-conflicts
Use when you need to resolve an in-progress git merge/rebase conflict.
67
129 xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., add
67
130 investigate
>
66
131 report
>
66
132 canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create ori
65
133 check
Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.
65
134 implement-spec
Implement the result of /to-spec and /to-tickets in code.
64
135 maintain-verification-skill
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use f
64
136 show-me
Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.
64
137 swarm
Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
63
138 ask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
62
139 brief
>
62
140 doc-coauthoring
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This wor
62
141 emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
62
142 help
>
62
143 performance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load time
62
144 algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or
61
145 code-reviewer
Analyzes code diffs and files to identify bugs, security vulnerabilities (SQL injection, XSS, insecure deserialization), code smells, N+1 queries, naming issues, and architectural concerns, then produ
61
146 e2e-testing
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.
61
147 grill
>-
61
148 simplify
Simplifies code for clarity without changing behavior. Use for readability, maintainability, and complexity reduction after behavior is understood.
61
149 update
>-
61
150 create-skill
>-
60
151 verification-loop
A comprehensive verification system for Claude Code sessions.
60
152 using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
59
153 worktree
>
59
154 arena
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial
57
155 eval-harness
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
57
156 i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-h
57
157 interrogate
Use for \"interrogate\", \"adversarial review\", \"multi-model review\", \"challenge this\", \"stress test this code\", \"find blind spots\", or \"tear this apart\". Multiple LLM reviewers challenge c
57
158 to-prd
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
57
159 ask
>
56
160 autopilot
>-
56
161 content-strategy
When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "con
56
162 context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
56
163 database-migrations
Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Kysely, Django, TypeORM, gol
56
164 no-comments
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
56
165 seo
Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimizatio
56
166 animate
Build an animation from scratch, making the decisions in the order that determines whether it feels right — should it animate at all, what purpose, which tool, which properties, which curve and durati
55
167 documentation
Write and maintain technical documentation. Trigger with "write docs for", "document this", "create a README", "write a runbook", "onboarding guide", or when the user needs help with any form of techn
55
168 github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
55
169 onboarding
When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation,
55
170 shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Appli
55
171 brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting
54
172 continuous-learning
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
54
173 karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiabl
54
174 openspec-update-change
Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reco
54
175 spec-driven-development
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and scope
54
176 typescript-best-practices
TypeScript best practices. Use when reading or editing any .ts or .tsx file.
54
177 claude-api
|-
53
178 ponytail-review
>
53
179 python-patterns
Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.
53
180 checkpoint
>
52
181 interview-me
Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an
52
182 resume
Bring the team back after team-resume started you on the machine taking the team over. Use when your first prompt names a resume report (tasks/resume-<date>-<time>.json) and this skill.
52
183 show-me-your-work
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to
52
184 strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
52
185 theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact t
52
186 apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum an
51
187 feature
Build, enhance, or revive GitHub repos - ship one feature PR per watched repo (watched), make the best single enhancement on one external repo (external), or revive the top dormant repo (dormant).
51
188 improve
Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or
51
189 observability
|
51
190 code-simplification
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code
50
191 correct
Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove ea
50
192 dispatch
>-
50
193 code-review-and-quality
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensi
49
194 codex-review
Second-opinion review. Drives OpenAI Codex CLI (codex exec review, gpt-6.1-sol, high reasoning) over a PR, branch, commit, or uncommitted diff, then verifies each finding. Trigger: $codex-review, \"ha
49
195 performance
Optimize web performance for faster loading and better user experience. Use when asked to "speed up my site", "optimize performance", "reduce load time", "fix slow loading", "improve page speed", or "
49
196 ponytail-audit
>
49
197 principle-encode-lessons-in-structure
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.
49
198 principle-prove-it-works
Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.
49
199 benchmark
|
48
200 context-budget
Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.
48
201 dashboard
>-
48
202 planning
任务规划。把高层目标(goal)拆解为可执行、可追踪的 plan 与任务清单,确定顺序、依赖、优先级与验收标准,避免盲目执行。
48
203 postgres-patterns
PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.
48
204 review-code
Audits a whole codebase in bounded waves of independent parallel auditors, publishes every verified finding ranked by severity, and applies only safe, in-scope repairs. Use when invoked explicitly for
48
205 speckit-analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
48
206 speckit-checklist
Generate a custom checklist for the current feature based on user requirements.
48
207 speckit-clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
48
208 speckit-constitution
Create or update the project constitution from interactive or provided principle inputs.
48
209 speckit-implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md
48
210 speckit-plan
Execute the implementation planning workflow using the plan template to generate design artifacts.
48
211 speckit-specify
Create or update the feature specification from a natural language feature description.
48
212 speckit-tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
48
213 vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with
48
214 adversarial-review
>
47
215 architecture-review
Traceability matrix mapping GDD requirements to ADRs. Finds gaps, cross-ADR conflicts, engine compatibility. PASS/CONCERNS/NOT ASSESSED/FAIL.
47
216 benchmark-checklist
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or re
47
217 continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to p
47
218 delegate
>-
47
219 figure-it-out
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop
47
220 obsidian-markdown
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wiki
47
221 prd
Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan thi
47
222 principle-fix-root-causes
Apply when debugging. Trace each symptom back to the first place the system went wrong and fix it there. A guard is a fix only when the state it handles is legitimate.
47
223 principle-subtract-before-you-add
Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.
47
224 security-scan
Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, an
47
225 web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state manag
47
226 explore
>
46
227 interview
>
46
228 principle-laziness-protocol
Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.
46
229 principle-sequence-verifiable-units
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next,
46
230 principle-type-system-discipline
Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at bou
46
231 python-testing
Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.
46
232 remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs
46
233 run
>-
46
234 session-handoff
Compress a long in-flight session into a cold-start handoff doc: goal, done, next, gotchas, key files, one-page cheat sheet.
46
235 to-issues
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementatio
46
236 weekly-review
>
46
237 codex
|
45
238 lint
>
45
239 migrate
>
45
240 principle-boundary-discipline
Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure
45
241 principle-build-the-lever
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead
45
242 principle-foundational-thinking
Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes
45
243 principle-minimize-reader-load
Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.
45
244 review-animations
Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.
45
245 browser
Web browser automation with AI-optimized snapshots for claude-flow agents
44
246 cleanup
>-
44
247 distill
Strip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean.
44
248 docker-patterns
Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.
44
249 incremental-implementation
Delivers changes incrementally in thin, verifiable slices. Use when implementing any feature or change that touches more than one file, or when picking up the next task from a plan. Use when rolling a
44
250 obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins,
44
251 pr-description
Write a PR title and description in this repo's house style, then create or update the PR via gh. Use when asked to draft or rewrite a PR title or body, to open a PR, or when another skill opens a PR.
44
252 principle-experience-first
Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.
44
253 principle-make-operations-idempotent
Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.
44
254 speckit-taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
44
255 analyze
>
43
256 architecture-decision-records
Capture architectural decisions made during Claude Code sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale. Maintains an ADR log so fut
43
257 autoresearch
Evolve a skill by generating variations, evaluating them, and updating the best version
43
258 capture
>
43
259 commit-message
>
43
260 new-project
>
43
261 obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, ta
43
262 principle-guard-the-context-window
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.
43
263 principle-model-the-domain
Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files.
43
264 principle-never-block-on-the-human
Apply when tempted to ask 'should I do X?' on reversible work.
43
265 animation-vocabulary
Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-
42
266 clickhouse-io
ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
42
267 defuddle
Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online do
42
268 documentation-and-adrs
Records decisions and documentation. Use when you need to document an architecture decision (ADR) or the reasoning behind a design choice, when changing public APIs, shipping features, or when you nee
42
269 frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a ta
42
270 go
>
42
271 optimize
Improve interface performance across loading speed, rendering, animations, images, and bundle size. Makes experiences faster and smoother.
42
272 principle-migrate-callers-then-delete-legacy-apis
Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.
42
273 principle-redesign-from-first-principles
Apply when integrating a new requirement into an existing design.
42
274 principle-separate-before-serializing-shared-state
Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.
42
275 standup
>-
42
276 thermo-nuclear-code-quality-review
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quali
42
277 typescript
>-
42
278 automate-me
Use for \"automate me\", \"create/update/refresh my -mode skill\", \"turn/capture my preferences or working style into a skill\", or wanting agents to follow how the user works. Drafts or revises a pe
41
279 caveman-commit
>
41
280 clarify
Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand. Use when the user mentions confusing text, unclear labels, bad error messages, har
41
281 gh-stack
>
41
282 incident-response
Run an incident response workflow — triage, communicate, and write postmortem. Trigger with "we have an incident", "production is down", an alert that needs severity assessment, a status update mid-in
41
283 merge
Merge PRs through a Codex review loop: /codex-fullreview, fix, then /codex-review reruns (3 max) until clean, then CI and squash-merge. Runs only when the user types /merge; from then on, every PR in
41
284 planning-and-task-breakdown
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scop
41
285 principle-exhaust-the-design-space
Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.
41
286 principle-outcome-oriented-execution
Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.
41
287 setup-pre-commit
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit
41
288 zoom-out
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
41
289 babysit-pr
Monitor a pull request through review and CI. Use when the user asks to monitor, watch, or babysit a PR.
40
290 caveman-review
>
40
291 content-engine
Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars
40
292 deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.
40
293 golang-testing
Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.
40
294 internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal com
40
295 open-pr
Write a PR description using conversation context and open PR creation in browser.
40
296 principle-attack-the-premise
Apply when two or more fixes that share one premise have failed the same gate. Write the premise down and test it directly before you write another fix that assumes it.
40
297 prompt-engineering
Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production
40
298 writing
Write or edit audience-facing prose: docs, UI copy, emails, release notes, and application answers. Use also for voice matching, clarity review, or AI-tell cleanup. Ordinary session replies follow ses
40
299 agentic-engineering
Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
39
300 article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished
39
#namerigs
1 code-reviewer
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
471
2 reviewer
>
292
3 architect
Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions
254
4 security-reviewer
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injectio
231
5 planner
Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation, architectural changes, or complex refactoring. Automatically activated for p
215
6 researcher
>
159
7 implementer
|
143
8 security-auditor
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
127
9 debugger
Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
109
10 verifier
>
97
11 test-writer
Generates comprehensive test suites for Energy platform modules.
79
12 refactor-cleaner
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely r
78
13 doc-updater
Documentation and codemap specialist. Use PROACTIVELY for updating codemaps and documentation. Runs /update-codemaps and /update-docs, generates docs/CODEMAPS/*, updates READMEs and guides.
75
14 tdd-guide
Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage.
75
15 scout
>
72
16 build-error-resolver
Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the
68
17 e2e-runner
End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines fl
68
18 DevOps Engineer
>
65
19 tester
Comprehensive testing and quality assurance specialist
65
20 builder
Builds one claimed TASKS.md item in a fresh context and reports back in ~20 lines, so the orchestrator context stays small. Does not pick items, edit TASKS.md, or commit.
62
21 test-engineer
QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
62
22 orchestrator
PROACTIVE - Coordinateur du pipeline spec-driven complet. Invoquer pour orchestrer le développement d'une nouvelle feature de bout en bout : lance spec-analyst → spec-architect → spec-developer en séq
61
23 database-reviewer
PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database p
59
24 code-simplifier
Simplifies and refines code for clarity, consistency, and maintainability while preserving behavior. Focus on recently modified code unless instructed otherwise.
57
25 qa
Tests every change against its requirement rows, hunts regressions, writes the QA report and holds the release gate. Use after any build step and before any release.
55
26 explorer
Read-only codebase explorer on Sonnet at medium effort. Use to locate files, symbols, call paths, tests, uncertainties, and candidate affected surfaces before implementation or judgment. Returns `FIND
53
27 product-manager
Turns a high-level ask into a crisp, exec-ready PRD with acceptance criteria and scope.
49
28 test-runner
>
49
29 explore
Codebase search specialist for finding files and code patterns
46
30 developer
Implement an assigned plan task or rework within its file scope, self-check the change and return versioned evidence for independent review.
45
31 QA Engineer
>-
45
32 security-engineer
Identify security vulnerabilities and ensure compliance with security standards and best practices
44
33 analyst
Advanced code quality analysis agent for comprehensive code reviews and improvements
43
34 python-reviewer
Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects.
43
35 ai-engineer
Expert AI/ML engineer specializing in machine learning model development, deployment, and integration into production systems. Focused on building intelligent features, data pipelines, and AI-powered
42
36 coder
Implementation specialist for writing clean, efficient code
42
37 frontend-developer
Expert frontend developer specializing in modern web technologies, React/Vue/Angular frameworks, UI implementation, and performance optimization
41
38 performance-engineer
Optimize system performance through measurement-driven analysis and bottleneck elimination
41
39 go-reviewer
Expert Go code reviewer specializing in idiomatic Go, concurrency patterns, error handling, and performance. Use for all Go code changes. MUST BE USED for Go projects.
40
40 release-manager
>
39
41 silent-failure-hunter
Review code for silent failures, swallowed errors, bad fallbacks, and missing error propagation.
39
42 UI Designer
Use this agent when creating user interfaces, designing components, building design systems, or improving visual aesthetics. This agent specializes in creating beautiful, functional interfaces that ca
39
43 backend-architect
Design reliable backend systems with focus on data integrity, security, and fault tolerance
38
44 designer
UI/UX Designer-Developer for stunning interfaces (Sonnet)
38
45 performance-optimizer
Performance analysis and optimization specialist. Use PROACTIVELY for identifying bottlenecks, optimizing slow code, reducing bundle sizes, and improving runtime performance. Profiling, memory leaks,
38
46 data-engineer
Designs, builds, and optimizes scalable and maintainable data-intensive applications, including ETL/ELT pipelines, data warehouses, and real-time streaming architectures. This agent is an expert in Sp
35
47 ux-designer
Produces a concise, accessible UX brief with flows, states, and annotations.
35
48 worker
Drafts or updates documentation and boilerplate in the files its brief names
35
49 plan-reviewer
One-pass review of an implementation plan against its spec and the repo, before the owner approves the plan.
34
50 Technical Writer
Create clear, comprehensive technical documentation tailored to specific audiences with focus on usability and accessibility
34
51 devops
Owns environments, CI, releases, rollback, backups and monitoring. Use to set up hosting and CI after setup, and for every release - and it never deploys, migrates or deletes without the founder's go
33
52 security
Reviews designs and diffs for security and privacy risk - auth, access control, secrets, injection, dependencies, data exposure. It writes its report and never changes code. Use on any feature touchin
33
53 auditor
>
32
54 performance-reviewer
Use this agent when you need to analyze code for performance issues, bottlenecks, and resource efficiency. Examples: After implementing database queries or API calls, when optimizing existing features
32
55 project-manager
>
32
56 doc-writer
|
31
57 architecture-reviewer
>
30
58 docs-writer
Технический писатель. Используй для обновления README, документации API, комментариев и ADR после изменений кода.
30
59 frontend-engineer
Use this agent when building modern frontend applications with React 19.2, Next.js 16 App Router, TypeScript 6, and Tailwind CSS v4. Invoke for component architecture, data fetching, Cache Components,
30
60 go-build-resolver
Go build, vet, and compilation error resolution specialist. Fixes build errors, go vet issues, and linter warnings with minimal changes. Use when Go builds fail.
29
61 system-architect
Expert agent for system architecture design, patterns, and high-level technical decisions
28
62 typescript-reviewer
Expert TypeScript/JavaScript code reviewer specializing in type safety, async correctness, Node/web security, and idiomatic patterns. Use for all TypeScript and JavaScript code changes. MUST BE USED f
28
63 writer
Writer of player-facing text — dialogue, lore entries, item and ability descriptions, environmental text.
27
64 code-architect
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing implementation blueprints with concrete files, interfaces, data flow, and build order.
26
65 code-explorer
Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, and documenting dependencies to inform new development.
26
66 data-scientist
Data analysis expert for SQL queries, BigQuery operations, and data insights. Use proactively for data analysis tasks and queries.
26
67 api-designer
Use this agent when designing new APIs, creating API specifications, or refactoring existing API architecture for scalability and developer experience. Invoke when you need REST/GraphQL endpoint desig
25
68 backend-dev
Specialized agent for backend API development, including REST and GraphQL endpoints
25
69 critic
Work plan and code review expert — thorough, structured, multi-perspective (Opus)
25
70 loop-operator
Operate autonomous agent loops, monitor progress, and intervene safely when loops stall.
25
71 type-design-analyzer
Analyze type design for encapsulation, invariant expression, usefulness, and enforcement.
25
72 validator
Runs a verified change the way a consumer would, in the operational environment, against the requirement that asked for it. Invoked by the engine at VALIDATE, once `verification-evidence` is green. Re
25
73 docs-lookup
When the user asks how to use a library, framework, or API or needs up-to-date code examples, use Context7 MCP to fetch current documentation and return answers with examples. Invoke for docs/API/setu
24
74 harness-optimizer
Analyze and improve the local agent harness configuration for reliability, cost, and throughput.
24
75 incident-responder
Handles production incidents with urgency and precision. Use IMMEDIATELY when production issues occur. Coordinates debugging, implements fixes, and documents post-mortems.
24
76 librarian
|
24
77 pr-reviewer
Expert code reviewer for GitHub pull requests. Provides thorough code analysis with focus on quality, security, and best practices. Use when reviewing PRs for code quality and potential issues.
24
78 pr-test-analyzer
Review pull request test coverage quality and completeness, with emphasis on behavioral coverage and real bug prevention.
24
79 architect-reviewer
Use this agent when you need to evaluate system design decisions, architectural patterns, and technology choices at the macro level.
23
80 chief-of-staff
Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers (skip/info_only/meeting_info/action_required), generates draft replies, and enfor
23
81 prompt-engineer
A master prompt engineer who architects and optimizes sophisticated LLM interactions. Use for designing advanced AI systems, pushing model performance to its limits, and creating robust, safe, and rel
23
82 backend-engineer
Use this agent when building Spring Boot 4 applications with Java 25, REST APIs, Spring Data JPA, Flyway migrations, Spring Security 7, OpenAPI documentation, and production-ready backend patterns.
22
83 frontend
화면(UI) 개발 전담 에이전트. 프로파일 CHECK_PATHS 의 ui 경로 아래 화면 코드 편집, 컴포넌트·차트·색상·레이아웃 작업 시 사용. design/DESIGN_GUIDE.md 5원칙과 dev/CONVENTIONS.md 의 화면 관례·스택 관례(토큰 파일, 차트 래퍼, 공용 fetch 래퍼)를 자동 준수한다.
22
84 java-reviewer
Expert Java and Spring Boot code reviewer specializing in layered architecture, JPA patterns, security, and concurrency. Use for all Java code changes. MUST BE USED for Spring Boot projects.
22
85 kotlin-reviewer
Kotlin and Android/KMP code reviewer. Reviews Kotlin code for idiomatic patterns, coroutine safety, Compose best practices, clean architecture violations, and common Android pitfalls.
22
86 business-analyst
Use when analyzing business processes, gathering requirements from stakeholders, or identifying process improvement opportunities to drive operational efficiency and measurable business value.
21
87 research
Search docs, web, and GitHub wikis — one agent for all lookups
21
88 rust-reviewer
Expert Rust code reviewer specializing in ownership, lifetimes, error handling, unsafe usage, and idiomatic patterns. Use for all Rust code changes. MUST BE USED for Rust projects.
21
89 backend-developer
Use this agent when building server-side APIs, microservices, and backend systems that require robust architecture, scalability planning, and production-ready implementation.
20
90 deployment-engineer
Configure CI/CD pipelines, Docker containers, and cloud deployments. Handles GitHub Actions, Kubernetes, and infrastructure automation. Use PROACTIVELY when setting up deployments, containers, or CI/C
20
91 design-reviewer
>
20
92 java-build-resolver
Java/Maven/Gradle build, compilation, and dependency error resolution specialist. Fixes build errors, Java compiler errors, and Maven/Gradle issues with minimal changes. Use when Java or Spring Boot b
20
93 mobile-developer
Architects and leads the development of sophisticated, cross-platform mobile applications using React Native and Flutter. This role demands proactive leadership in mobile strategy, ensuring robust nat
20
94 python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY f
20
95 qa-tester
Writes test cases, bug reports, and checklists — test case generation, regression checklist creation, execution documentation.
20
96 rust-build-resolver
Rust build, compilation, and dependency error resolution specialist. Fixes cargo build errors, borrow checker issues, and Cargo.toml problems with minimal changes. Use when Rust builds fail.
20
97 kotlin-build-resolver
Kotlin/Gradle build, compilation, and dependency error resolution specialist. Fixes build errors, Kotlin compiler errors, and Gradle issues with minimal changes. Use when Kotlin builds fail.
19
98 ml-engineer
Designs, builds, and manages the end-to-end lifecycle of machine learning models in production. Specializes in creating scalable, reliable, and automated ML systems. Use PROACTIVELY for tasks involvin
19
99 spec-reviewer
|
19
100 tech-lead
技术负责人代理。用于拆解复杂需求、定义任务、协调多代理工作。不要自己写代码,而是定义 Task Prompt。触发词:技术负责人、拆解需求、项目管理、任务拆分。
19
101 cloud-architect
Design AWS/Azure/GCP infrastructure, implement Terraform IaC, and optimize cloud costs. Handles auto-scaling, multi-region deployments, and serverless architectures. Use PROACTIVELY for cloud infrastr
18
102 react-reviewer
Expert React/JSX code reviewer specializing in hook correctness, render performance, server/client component boundaries, accessibility, and React-specific security. Use for any change touching .tsx/.j
18
103 research-agent
Deep research agent for investigating topics, reading docs, searching repos, and summarizing findings. Optimized for breadth.
18
104 review
Architectural code reviewer for codealmanac. Use after meaningful code changes, before merging, or whenever code shape feels off.
18
105 tech-writer
Technical Writer - Documentation creation using documentation patterns
18
106 UX Researcher
Use this agent when conducting user research, analyzing user behavior, creating journey maps, or validating design decisions through testing. This agent specializes in understanding user needs, pain p
18
107 ux-reviewer
Performs live browser-walk UX audits using the console-idiom rubric. Restricted to read-only browser interaction - no writes, deletes, or submissions. Requires a browser MCP.
18
108 adversarial-reviewer
MUST BE USED as pipeline stage 4. Attacks the Implementer's output for correctness bugs — especially concurrency, idempotency and money-conservation defects. The gate HALTS unless this stage emits at
17
109 cpp-build-resolver
C++ build, CMake, and compilation error resolution specialist. Fixes build errors, linker issues, and template errors with minimal changes. Use when C++ builds fail.
17
110 cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
17
111 database-architect
Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.
17
112 dependency-auditor
Specialist for analyzing dependency health, detecting security vulnerabilities, and identifying outdated or unused packages. Uses Knip for accurate unused dependency detection.
17
113 executor
승인된 plan 하나를 통째로 자율 실행하는 대규모 구현 에이전트. 파일 8개 이상이거나 레이어 3개 이상을 횡단하는 plan의 3단계 구현에 사용. 절차 지시 대신 목표·제약·완료 조건으로 구동한다.
17
114 seo-specialist
SEO specialist for technical SEO audits, on-page optimization, structured data, Core Web Vitals, and content/keyword mapping. Use for site audits, meta tag reviews, schema markup, sitemap and robots i
17
115 test-automator
Create comprehensive test suites with unit, integration, and e2e tests. Sets up CI pipelines, mocking strategies, and test data. Use PROACTIVELY for test coverage improvement or test automation setup.
17
116 backend
서버(백엔드) 개발 전담 에이전트. 프로파일 LANG 의 서버 소스 편집, 라우트/DB 쿼리/배치 스크립트 작업 시 사용. 승인된 컴포넌트 그래프의 의존 방향과 workboard 과업 보드 프로토콜을 자동 준수한다.
16
117 comment-analyzer
Analyze code comments for accuracy, completeness, maintainability, and comment rot risk.
16
118 data-analyst
Use when you need to extract insights from business data, create dashboards and reports, or perform statistical analysis to support decision-making.
16
119 database-optimizer
An expert AI assistant for holistically analyzing and optimizing database performance. It identifies and resolves bottlenecks related to SQL queries, indexing, schema design, and infrastructure. Proac
16
120 documentation-writer
>
16
121 frontend-architect
Create accessible, performant user interfaces with focus on user experience and modern frameworks
16
122 frontend-dev
>
16
123 Performance Benchmarker
Implements comprehensive performance benchmarking for distributed consensus protocols
16
124 plan
Product discovery, requirements and acceptance criteria, architecture and ADR, the spec review axis, and domain consult or the domain review axis (a domain reference loaded). Never writes product code
16
125 qa-reviewer
Independently select counterexample and acceptance checks on the final implementation, execute them and report observed results without fixing product code.
16
126 solution-architect
Expert solution architect. MUST BE USED to design system architecture, create technical specifications, define data models, and make technology stack decisions based on analyzed requirements.
16
127 ui-ux-designer
Expert designer who creates intuitive, beautiful, and accessible user experiences
16
128 agent
运维与交付主Agent,统筹CI/CD流水线、发布部署、线上监控排障、资源成本管控的一级调度者。当测试通过的稳定版本需要流水线构建、发布上线、环境初始化、监控告警、故障排查、成本优化时使用。
15
129 flutter-reviewer
Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-
15
130 graphql-architect
A highly specialized AI agent for designing, implementing, and optimizing high-performance, scalable, and secure GraphQL APIs. It excels at schema architecture, resolver optimization, federated servic
15
131 product-owner
Lead the Fusebase Flow ticket lifecycle from lane classification through deploy closeout. Own specs, decisions, tasks, gates, reviews, and handoffs; never application code or deploy side effects.
15
132 requirements-analyst
Transform ambiguous project ideas into concrete specifications through systematic requirements discovery and structured analysis
15
133 Software Architect
Expert software architect specializing in system design, domain-driven design, architectural patterns, and technical decision-making for scalable, maintainable systems.
15
134 Editor
文件編輯:與作者討論文件結構與內容,協助潤稿與重組敘事。寫作過程中的協作為主要用法。
14
135 impeccable-manual-edit-applier
Applies leased Impeccable live manual copy-edit batches to source and returns canonical Apply results.
14
136 lead
Discovery, scope, tier and ranked candidates for a WUWEI plan pass.
14
137 performance-analyzer
Analyzes code for performance bottlenecks, memory leaks, bundle size issues, and optimization opportunities.
14
138 python-expert
Deliver production-ready, secure, high-performance Python code following SOLID principles and modern best practices
14
139 pytorch-build-resolver
PyTorch runtime, CUDA, and training error resolution specialist. Fixes tensor shape mismatches, device errors, gradient issues, DataLoader problems, and mixed precision failures with minimal changes.
14
140 refactorer
Code refactoring and tech debt reduction. Use for improving code structure, extracting abstractions, reducing duplication, and improving maintainability without changing behavior.
14
141 Strategist
Council Gold Lens — business value, scope, MVP, prioritization
14
142 api-documenter
Create OpenAPI/Swagger specs, generate SDKs, and write developer documentation. Handles versioning, examples, and interactive docs. Use PROACTIVELY for API documentation or client library generation.
13
143 design-critic
Independent visual critic. Judges a rendered screen against DESIGN_MAP.md (character, world, signature, tokens) and the slop signs, runs the competitor test, and returns a ranked list of what makes it
13
144 impeccable-asset-producer
Produces clean reusable raster assets from approved Impeccable mock references without redesigning the direction.
13
145 impeccable-documenter
Records DESIGN.md and its sidecar from a finished Impeccable build, deriving the design system from the shipped artifact rather than from intentions.
13
146 impeccable-finish-reviewer
Reviews a finished Impeccable build against its direction contract, the approved comp, and the chosen world's quality bar, returning an ordered list of material fixes.
13
147 meta-agent
Generates a new, complete Claude Code sub-agent configuration file from a user's description. Use this to create new agents. Use this Proactively when the user asks you to create a new sub agent.
13
148 oracle
Council Violet Lens — AI/LLM integration, RAG, prompt engineering
13
149 performance-analyst
Performance analyst — profiling, bottlenecks, memory analysis, frame time investigation, recommends optimizations, tracks metrics over time.
13
150 typescript-pro
A TypeScript expert who architects, writes, and refactors scalable, type-safe, and maintainable applications for Node.js and browser environments. It provides detailed explanations for its architectur
13
151 accessibility-specialist
Accessibility standards and assistive features — remapping, text scaling, colorblind modes, screen reader support.
12
152 Brand Guardian
Use this agent when establishing brand guidelines, ensuring visual consistency, managing brand assets, or evolving brand identity. This agent specializes in creating and maintaining cohesive brand exp
12
153 codex-reviewer
>
12
154 context-manager
Manages context across multiple agents and long-running tasks. Use when coordinating complex multi-agent workflows or when context needs to be preserved across multiple sessions. MUST BE USED for proj
12
155 documenter
Keeps documentation true to the code, CONTEXT.md files first, then README and user-facing docs. Use when asked to update, check or write docs, to close a finished plan, or to add CONTEXT.md files to a
12
156 error-detective
Search logs and codebases for error patterns, stack traces, and anomalies. Correlates errors across systems and identifies root causes. Use PROACTIVELY when debugging issues, analyzing logs, or invest
12
157 evaluator
>
12
158 fixer
Use for quick fixes, hotfixes, urgent patches, and time-sensitive bug repairs.
12
159 qa-lead
Test strategy and process — test plan creation, bug severity assessment, regression planning, release quality gates, readiness evaluation.
12
160 refactoring-expert
Improve code quality and reduce technical debt through systematic refactoring and clean code principles
12
161 security-scanner
Use proactively for comprehensive security vulnerability scanning including SQL injection, XSS, authentication issues, RLS policy validation, and hardcoded secrets detection. Specialist for finding se
12
162 agent-auditor
Audits agent definitions (currently .energy format) for completeness, token efficiency, and harness quality.
11
163 agent-creator
|
11
164 analytics-engineer
Telemetry and analytics — event tracking, player behavior, A/B test frameworks, dashboard specification, data pipelines.
11
165 API Tester
Use this agent for comprehensive API testing including performance testing, load testing, and contract testing. This agent specializes in ensuring APIs are robust, performant, and meet specifications
11
166 code-analyzer
Advanced code quality analysis agent for comprehensive code reviews and improvements
11
167 codebase-analyzer
Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the b
11
168 codex
Use this agent when the user explicitly requests Codex for code analysis, questions, or other tasks.
11
169 commit
Create a commit on main that closes the GitHub issue (Fixes #N) and push it.
11
170 content-creator
Use for Horizon content creator work: writes every word Horizon publishes: posts, the newsletter, video scripts and page copy, in the Sunny voice.
11
171 csharp-reviewer
Expert C# code reviewer specializing in .NET conventions, async patterns, security, nullable reference types, and performance. Use for all C# code changes. MUST BE USED for C# projects.
11
172 DevOps Automator
Use this agent when setting up CI/CD pipelines, configuring cloud infrastructure, implementing monitoring systems, or automating deployment processes. This agent specializes in making deployment and o
11
173 engineer
Strategic engineering specialist. Use when a feature introduces a new module/service, is cross-cutting, performance-sensitive, requires a new dependency, establishes a new pattern, or raises a real bu
11
174 Feedback Synthesizer
Expert in collecting, analyzing, and synthesizing user feedback from multiple channels to extract actionable product insights. Transforms qualitative feedback into quantitative priorities and strategi
11
175 golang-pro
A Go expert that architects, writes, and refactors robust, concurrent, and highly performant Go applications. It provides detailed explanations for its design choices, focusing on idiomatic code, long
11
176 MEMORY
>
11
177 Mobile App Builder
Use this agent when developing native iOS or Android applications, implementing React Native features, or optimizing mobile performance. This agent specializes in creating smooth, native-feeling mobil
11
178 opensource-sanitizer
Verify an open-source fork is fully sanitized before release. Scans for leaked secrets, PII, internal references, and dangerous files using 20+ regex patterns. Generates a PASS/FAIL/PASS-WITH-WARNINGS
11
179 pm
Product orchestrator for Builders Camp Claude OS. Use for every incoming task to classify the request, choose the minimum correct workflow, decide whether to delegate to specialist agents, and define
11
180 quality-reviewer
Reviews code and plans for production risks, project conformance, and structural quality
11
181 react-build-resolver
Diagnose and fix React build failures across Vite, webpack, Next.js, CRA, Parcel, esbuild, and Bun. Handles JSX/TSX compile errors, hydration mismatches, server/client component boundary failures, mis
11
182 skeptic
Council Red Lens — risk assessment, devil's advocate, security
11
183 synthesizer
Reads gathered context and produces structured reflections, summaries, and insights. Use after the Researcher has gathered raw material.
11
184 Trend Researcher
Expert market intelligence analyst specializing in identifying emerging trends, competitive analysis, and opportunity assessment. Focused on providing actionable insights that drive product strategy a
11
185 typescript-expert
>-
11
186 verify-app
push前の変更の包括的な検証 - テスト、型チェック、Lint、手動チェック
11
187 a11y-architect
Accessibility Architect specializing in WCAG 2.2 compliance for Web and Native platforms. Use PROACTIVELY when designing UI components, establishing design systems, or auditing code for inclusive user
10
188 accessibility-reviewer
>
10
189 ARCHITECTURE
>
10
190 bug-fixer
Use proactively to systematically fix bugs from bug-hunter reports. Specialist for processing bug-hunting-report.md files and implementing fixes by priority level with validation and progress tracking
10
191 code-review
Multi-axis code-review persona (correctness + architecture + performance). Code Review Board L2 member; joins L1 when the diff touches a hot path or a latency/throughput-AC path without a perf-budget
10
192 codebase-pattern-finder
codebase-pattern-finder is a useful subagent_type for finding similar implementations, usage examples, or existing patterns that can be modeled after. It will give you concrete code examples based on
10
193 content-strategist
Deep autonomous content strategy — multi-pass site crawl, competitor content audit, full keyword + topic gap analysis, pillar + cluster topology, and 90-day publishing queue grounded in real GSC/SERP
10
194 copywriter
BRACE's copywriter. Delegate to it when a BRACE skill needs the words of a brand route (voice, tagline, one-liner, names, the texts of the mockups). Pass the strategist's routes and creative brief, si
10
195 curator
Binds every claim that a release makes to the evidence for it, and refuses each claim that has none. Invoked by the engine at SHIP, once verify and validate are green. Returns a `release-record` in wh
10
196 design
UX research, information architecture, wireframes and design tokens, design system, accessibility (WCAG 2.2 AA), the ui review axis (Phase 3a), and design-run requests. Design authority; has no Bash a
10
197 dx-optimizer
A specialist in Developer Experience (DX). My purpose is to proactively improve tooling, setup, and workflows, especially when initiating new projects, responding to team feedback, or when friction in
10
198 game-designer
Mechanical and systems design — core loops, progression, combat, economy, player-facing rules. Mechanics-level questions.
10
199 gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
10
200 gan-generator
GAN Harness — Generator agent. Implements features according to the spec, reads evaluator feedback, and iterates until quality threshold is met.
10
201 gan-planner
GAN Harness — Planner agent. Expands a one-line prompt into a full product specification with features, sprints, evaluation criteria, and design direction.
10
202 Growth Hacker
Expert growth strategist specializing in rapid user acquisition through data-driven experimentation. Develops viral loops, optimizes conversion funnels, and finds scalable growth channels for exponent
10
203 healthcare-reviewer
Reviews healthcare application code for clinical safety, CDSS accuracy, PHI compliance, and medical data integrity. Specialized for EMR/EHR, clinical decision support, and health information systems.
10
204 investigator
Given a ticket, digs into the affected codebase and produces the two mandatory pre-implementation artifacts, investigation.md and test_plan.md.
10
205 legacy-modernizer
A specialist agent for planning and executing the incremental modernization of legacy systems. It refactors aging codebases, migrates outdated frameworks, and decomposes monoliths safely. Use this to
10
206 marketing
Pazarlama ve marka. Ürün içi metin, mağaza metni (ASO), sosyal içerik taslağı ve marka kılavuzu üretir; varlık (ikon, ekran görüntüsü, banner) için brif yazar. Yayınlamaz: sosyal paylaşım ve mağaza li
10
207 mle-reviewer
Production machine-learning engineering reviewer for data contracts, feature pipelines, training reproducibility, offline/online evaluation, model serving, monitoring, and rollback. Use when ML, MLOps
10
208 mlops-engineer
ML infrastructure and operations specialist. Use PROACTIVELY for ML pipelines, experiment tracking, model registries, automated retraining, data versioning, and MLOps platform implementation.
10
209 performance
Performance optimization and profiling. Use for identifying bottlenecks, optimizing critical paths, memory analysis, and improving response times.
10
210 platform-engineer
|
10
211 product-analyst
The lead agent for planning. Reads a request or requirements text, interrogates it against a fixed set of lenses, runs a short focused conversation to close the open decisions, and produces a purely b
10
212 product-strategist
Use during Discovery Track phases Frame and Converge as the consulted specialist for product strategy. Brings Lean Canvas, Jobs to be Done, North Star Metric, and Opportunity Solution Tree to the conv
10
213 qa-expert
A sophisticated AI Quality Assurance (QA) Expert for designing, implementing, and managing comprehensive QA processes to ensure software products meet the highest standards of quality, reliability, an
10
214 refactoring-specialist
Performs systematic code refactoring including dead code removal, abstraction extraction, and structural improvements
10
215 research-analyst
Career Kit 调研分析员——读取岗位/面经详情(read_research_details),输出分析结论与重点名单(conclusions/shortlist/gaps),供父 Agent 汇总
10
216 Senior Developer
Premium implementation specialist - Masters Laravel/Livewire/FluxUI, advanced CSS, Three.js integration
10
217 seo-content
Content quality reviewer. Evaluates E-E-A-T signals, readability, content depth, AI citation readiness, and thin content detection.
10
218 seo-technical
Technical SEO specialist. Analyzes crawlability, indexability, security, URL structure, mobile optimization, Core Web Vitals, and JavaScript rendering.
10
219 skill-reviewer
Fresh-context reviewer for Claude Ads skill and agent routing, progressive disclosure, prompt contracts, safety boundaries, examples, and runnable verification.
10
220 test-author
>
10
221 test_reviewer
Review test adequacy, characterization coverage, and verification evidence.
10
222 web-researcher
Comprehensive web research specialist for documentation, code examples, and technical information
10
223 accessibility-auditor
Practical accessibility audit covering WCAG 2.2, contrast, focus, keyboard, screen reader, and touch targets
9
224 advisor
The expensive brain, consulted on demand. Call this agent ONLY for hard judgment calls a cheaper executor shouldn't make alone: reviewing a plan, challenging an architecture, resolving a tricky tradeo
9
225 agent-organizer
A highly advanced AI agent that functions as a master orchestrator for complex, multi-agent tasks. It analyzes project requirements, defines a team of specialized AI agents, and manages their collabor
9
226 blog-writer
>
9
227 bug-hunter
Use proactively for comprehensive bug detection, code validation, dead code identification, and generating prioritized fix tasks. Specialist for finding security vulnerabilities, performance issues, d
9
228 codebase-locator
Locates files, directories, and components relevant to a feature or task. Call `codebase-locator` with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" —
9
229 Competitive Analyst
Use when you need to analyze direct and indirect competitors, benchmark against market leaders, or develop strategies to strengthen competitive positioning and market advantage.
9
230 conversation-analyzer
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Triggered by /hookify without arguments.
9
231 coordinator
Orchestrates a swarm of feature-stream background sessions. Plans streams from tasks/TASKS.md, dispatches each as `claude --bg --worktree feat-<N>`, monitors via `claude agents --json`, merges PRs as
9
232 dart-build-resolver
Dart/Flutter build, analysis, and dependency error resolution specialist. Fixes `dart analyze` errors, Flutter compilation failures, pub dependency conflicts, and build_runner issues with minimal, sur
9
233 database-admin
Manage database operations, backups, replication, and monitoring. Handles user permissions, maintenance tasks, and disaster recovery. Use PROACTIVELY for database setup, operational issues, or recover
9
234 database-engineer
Use this agent when designing database schemas, writing Flyway migrations, optimizing JPA queries, configuring connection pooling, implementing caching strategies, or troubleshooting N+1 queries and s
9
235 dependency-manager
Use this agent when you need to audit dependencies for vulnerabilities, resolve version conflicts, optimize bundle sizes, or implement automated dependency updates.
9
236 deployer
Assists with deploy verification and troubleshooting. Deployments happen automatically via GitHub Actions on push to main. Use when the user needs to check deploy status or debug deploy issues.
9
237 devops-troubleshooter
Debug production issues, analyze logs, and fix deployment failures. Masters monitoring tools, incident response, and root cause analysis. Use PROACTIVELY for production debugging or system outages.
9
238 django-reviewer
Expert Django code reviewer specializing in ORM correctness, DRF patterns, migration safety, security misconfigurations, and production-grade Django practices. Use for all Django code changes. MUST BE
9
239 docker-expert
Use this agent when you need to build, optimize, or secure Docker container images and orchestration for production environments.
9
240 docs-reviewer
Documentation-sync reviewer. Checks that docs match the code after a change — missing docs for new behavior, stale/contradicting docs, and violations of procedural "when you touch A, update B" rules.
9
241 documentation-expert
A sophisticated AI Software Documentation Expert for designing, creating, and maintaining comprehensive and user-friendly software documentation. Use PROACTIVELY for developing clear, consistent, and
9
242 electron-pro
An expert in building cross-platform desktop applications using Electron and TypeScript. Specializes in creating secure, performant, and maintainable applications by leveraging the full potential of w
9
243 Experiment Tracker
Expert project manager specializing in experiment design, execution tracking, and data-driven decision making. Focused on managing A/B tests, feature experiments, and hypothesis validation through sys
9
244 frontend-reviewer
Use this agent to review component structure, state, accessibility, responsive behavior and client performance. Provide evidence-based, read-only repository analysis.
9
245 frontend-specialist
Especialista de Frontend. Implementa componentes, layouts, páginas y hooks en Next.js 16 App Router con Tailwind CSS v4. Domina Server vs Client Components, TanStack Query v5, React Hook Form + Zod, y
9
246 fullstack-developer
Expert full-stack developer specializing in modern web technologies. MUST BE USED for all implementation tasks including backend APIs, frontend applications, database operations, and full-stack featur
9
247 fullstack-engineer
End-to-end feature development across frontend, backend, and database layers
9
248 gitter
The ONLY agent that writes git in the forward-compaction repo. Phases COMMIT, PUSH, RELEASE, PULL; no phase named = freeform git ask. Returns the verified refs. Pushes and releases only on the owner's
9
249 guardian
Council Silver Lens — compliance, governance, privacy
9
250 judge
Use this agent when evaluating implementation artifacts against an evaluation specification produced by the meta judge. Applies rubric dimensions, checklist items, and scoring metadata to produce stru
9
251 migration-reviewer
Use PROACTIVELY after any change to database schema definitions (ORM models, schema files) or to migration files (new or edited migrations, generated SQL). MUST BE USED before committing schema or mig
9
252 observability-engineer
Use when the user says \"add tracing\", \"define our SLOs\", \"these alerts are noise\" or \"build a dashboard for this service\". Designs and extends logs, metrics, traces, SLOs, alerts and dashboard
9
253 opensource-forker
Fork any project for open-sourcing. Copies files, strips secrets and credentials (20+ patterns), replaces internal references with placeholders, generates .env.example, and cleans git history. First s
9
254 opensource-packager
Generate complete open-source packaging for a sanitized project. Produces CLAUDE.md, setup.sh, README.md, LICENSE, CONTRIBUTING.md, and GitHub issue templates. Makes any repo immediately usable with C
9
255 pr-manager
Comprehensive pull request management with swarm coordination for automated reviews, testing, and merge workflows
9
256 prototyper
Throwaway builds — concept prototypes after brainstorm to test an idea is fun before GDDs; vertical slices pre-production. Speed over standards.
9
257 Rapid Prototyper
Specialized in ultra-fast proof-of-concept development and MVP creation using efficient tools and frameworks
9
258 review-security
Reviews changed code for real, reachable security issues at system boundaries. Spawned by the pr-ci-review skill.
9
259 scribe
Records user-dictated raw content verbatim to a named target file. Handles five operations — daily-note capture, dining-log row append, GTD entry append/toggle, people-note stub create, generic raw pa
9
260 seo-performance
Performance analyzer. Measures and evaluates Core Web Vitals and page load performance.
9
261 seo-schema
Schema markup expert. Detects, validates, and generates Schema.org structured data in JSON-LD format.
9
262 seo-sitemap
Sitemap architect. Validates XML sitemaps, generates new ones with industry templates, and enforces quality gates for location pages.
9
263 seo-visual
Visual analyzer. Captures screenshots, tests mobile rendering, and analyzes above-the-fold content using Playwright.
9
264 spec-writer
Writes detailed formal specifications from the approved proposal
9
265 Sprint Prioritizer
Expert product manager specializing in agile sprint planning, feature prioritization, and resource allocation. Focused on maximizing team velocity and business value delivery through data-driven prior
9
266 test-agent
Test-Generierung, Test-Ausführung, Coverage-Analyse. Use proactively when adding new features, before commits, or when investigating test gaps. Abzugrenzen von parseltongue:python-testing (Plugin-Vari
9
267 test-coverage-reviewer
Use this agent when you need to review testing implementation and coverage. Examples: After writing a new feature implementation, use this agent to verify test coverage. When refactoring code, use thi
9
268 Visual Storyteller
Use this agent when creating visual narratives, designing infographics, building presentations, or communicating complex ideas through imagery. This agent specializes in transforming data and concepts
9
269 web-search-researcher
Do you find yourself desiring information that you don't quite feel well-trained (confident) on? Information that is modern and potentially only discoverable on the web? Use the web-search-researcher
9
270 Whimsy Injector
PROACTIVELY use this agent after any UI/UX changes to ensure delightful, playful elements are incorporated. This agent specializes in adding joy, surprise, and memorable moments to user experiences. T
9
271 accessibility-tester
Use this agent when you need comprehensive accessibility testing, WCAG compliance verification, or assessment of assistive technology support.
8
272 build-validator
>
8
273 byzantine-coordinator
Coordinates Byzantine fault-tolerant consensus protocols with malicious actor detection
8
274 cicd-engineer
Specialized agent for GitHub Actions CI/CD pipeline creation and optimization
8
275 community-manager
Player-facing communication — patch notes, social posts, community updates, feedback collection, player bug triage, crisis communication.
8
276 crdt-synchronizer
Implements Conflict-free Replicated Data Types for eventually consistent state synchronization
8
277 creative-director
Highest creative authority — vision, tone, aesthetic direction. Use when a decision affects game identity or department leads deadlock.
8
278 cto
Reviews finished work from the chief technology officer's seat: is it finished enough to ship, and what does shipping it commit us to supporting? Leaves vulnerabilities to security-reviewer. Read-only
8
279 deep-reasoner
Architecture research and judgment executor on Opus at xhigh effort. Use for architecture proposals, complex multi-step reasoning, and high-risk analysis — design trade-offs, risky migrations, securit
8
280 dev
Écrit et modifie du code source. Déléguer pour implémenter une fonctionnalité, corriger un bug ou appliquer un refactor — dès que le changement crée un fichier de code ou en touche plus de deux, qu'il
8
281 devils-advocate
|
8
282 diff-reviewer
Adversarial review of an implemented feature's diff against its spec, plan, acceptance tests and gate results. Read-only, pinned to another model than the session, starts without its context. Spawned
8
283 docs
Confluence·Jira 문서 작업 전문 에이전트. 페이지 생성·수정, 이슈 관리 시 사용. MCP(confluence) 접근 권한 보유. git 작업은 gitops에게 위임.
8
284 docs-researcher
Documentation perspective for replacing recalled knowledge about a framework, library, API, platform, or protocol with cited facts for the version this repository actually depends on — version differe
8
285 fastapi-reviewer
Reviews FastAPI applications for async correctness, dependency injection, Pydantic schemas, security, OpenAPI quality, testing, and production readiness.
8
286 Finance Tracker
Use this agent when managing budgets, optimizing costs, forecasting revenue, or analyzing financial performance. This agent excels at transforming financial chaos into strategic clarity, ensuring stud
8
287 fsharp-reviewer
Expert F# code reviewer specializing in functional idioms, type safety, pattern matching, computation expressions, and performance. Use for all F# code changes. MUST BE USED for F# projects.
8
288 git-workflow-manager
Expert Git workflow manager specializing in branching strategies, automation, and team collaboration. Masters Git workflows, merge conflict resolution, and repository management with focus on enabling
8
289 goal-planner
Goal-Oriented Action Planning (GOAP) specialist that dynamically creates intelligent plans to achieve complex objectives. Uses gaming AI techniques to discover novel solutions by combining actions in
8
290 gossip-coordinator
Coordinates gossip-based consensus protocols for scalable eventually consistent systems
8
291 gsd-codebase-mapper
Explores codebase and writes structured analysis documents. Spawned by map-codebase with a focus area (tech, arch, quality, concerns). Writes documents directly to reduce orchestrator context load.
8
292 gsd-debugger
Investigates bugs using scientific method, manages debug sessions, handles checkpoints. Spawned by /gsd:debug orchestrator.
8
293 gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
8
294 gsd-integration-checker
Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end.
8
295 gsd-phase-researcher
Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.
8
296 gsd-plan-checker
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /gsd:plan-phase orchestrator.
8
297 gsd-planner
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd:plan-phase orchestrator.
8
298 issue-tracker
Intelligent issue management and project coordination with automated tracking, progress monitoring, and team coordination
8
299 learning-guide
Teach programming concepts and explain code with focus on understanding through progressive learning and practical examples
8
300 level-designer
Spatial design for levels and areas — encounter layouts, pacing, difficulty, layout planning, environmental storytelling.
8
#namerigs
1 frontend-design@claude-plugins-official 226
2 typescript-lsp@claude-plugins-official 173
3 superpowers@claude-plugins-official 165
4 skill-creator@claude-plugins-official 130
5 code-review@claude-plugins-official 122
6 context7@claude-plugins-official 122
7 pyright-lsp@claude-plugins-official 115
8 rust-analyzer-lsp@claude-plugins-official 114
9 code-simplifier@claude-plugins-official 111
10 security-guidance@claude-plugins-official 109
11 gopls-lsp@claude-plugins-official 108
12 claude-md-management@claude-plugins-official 107
13 swift-lsp@claude-plugins-official 81
14 playwright@claude-plugins-official 80
15 commit-commands@claude-plugins-official 75
16 feature-dev@claude-plugins-official 73
17 github@claude-plugins-official 72
18 lua-lsp@claude-plugins-official 72
19 ponytail@ponytail 65
20 claude-code-setup@claude-plugins-official 61
21 pr-review-toolkit@claude-plugins-official 60
22 clangd-lsp@claude-plugins-official 59
23 codex@openai-codex 58
24 plugin-dev@claude-plugins-official 56
25 figma@claude-plugins-official 54
26 caveman@caveman 45
27 ralph-loop@claude-plugins-official 43
28 vercel@claude-plugins-official 37
29 hookify@claude-plugins-official 33
30 slack@claude-plugins-official 32
31 mattpocock-skills@claude-plugins-official 31
32 document-skills@anthropic-agent-skills 29
33 ruby-lsp@claude-plugins-official 29
34 cc-plugin-you-should-know@builtin 28
35 chrome-devtools-mcp@claude-plugins-official 26
36 claude-mem@thedotmack 26
37 superpowers@superpowers-marketplace 26
38 explanatory-output-style@claude-plugins-official 23
39 claude-hud@claude-hud 22
40 expo@claude-plugins-official 21
41 claude-security@claude-plugins-official 20
42 cloudflare@cloudflare 20
43 impeccable@impeccable 20
44 jdtls-lsp@claude-plugins-official 20
45 agent-sdk-dev@claude-plugins-official 19
46 example-skills@anthropic-agent-skills 19
47 i-have-adhd@i-have-adhd 18
48 ui-ux-pro-max@ui-ux-pro-max-skill 18
49 mattpocock-skills@mattpocock 15
50 Notion@claude-plugins-official 15
51 playground@claude-plugins-official 15
52 csharp-lsp@claude-plugins-official 14
53 remember@claude-plugins-official 14
54 typesafe@typesafe-ai 14
55 warp@claude-code-warp 14
56 kotlin-lsp@claude-plugins-official 13
57 worktrunk@worktrunk 13
58 claude-code-wakatime@wakatime 12
59 context-mode@context-mode 12
60 linear@claude-plugins-official 12
61 frontend-design@claude-code-plugins 11
62 supabase@claude-plugins-official 11
63 andrej-karpathy-skills@karpathy-skills 10
64 learning-output-style@claude-plugins-official 10
65 obsidian@obsidian-skills 10
66 php-lsp@claude-plugins-official 10
67 sentry@claude-plugins-official 10
68 atlassian@claude-plugins-official 9
69 session-report@claude-plugins-official 9
70 stripe@claude-plugins-official 9
71 chrome-devtools-mcp@chrome-devtools-plugins 8
72 everything-claude-code@everything-claude-code 8
73 humanizer@humanizer 8
74 telegram@claude-plugins-official 8
75 compound-engineering@compound-engineering-plugin 7
76 datadog@claude-plugins-official 7
77 mcp-server-dev@claude-plugins-official 7
78 pstack@cursor-plugins 7
79 serena@claude-plugins-official 7
80 agent-browser@agent-browser 6
81 claude-seo@agricidaniel-claude-seo 6
82 cloudflare@claude-plugins-official 6
83 diagram-design@diagram-design 6
84 engineering@knowledge-work-plugins 6
85 firecrawl@claude-plugins-official 6
86 huggingface-skills@claude-plugins-official 6
87 last30days@last30days-skill 6
88 nx@nx-claude-plugins 6
89 posthog@claude-plugins-official 6
90 superpowers-developing-for-claude-code@superpowers-marketplace 6
91 understand-anything@understand-anything 6
92 agent-skills@addy-agent-skills 5
93 ast-grep@ast-grep-marketplace 5
94 cli-anything@cli-anything 5
95 kk@claude-toolbox 5
96 marketing-skills@marketingskills 5
97 marketing@knowledge-work-plugins 5
98 plannotator@plannotator 5
99 roadkeep@alegauss 5
100 claude-api@anthropic-agent-skills 4
101 coderabbit@claude-plugins-official 4
102 context7@anthropic-plugin-directory 4
103 crit@crit 4
104 design@knowledge-work-plugins 4
105 discord@claude-plugins-official 4
106 ecc@ecc 4
107 eli5@claude-community 4
108 feature-dev@claude-code-plugins 4
109 firebase@claude-plugins-official 4
110 gitlab@claude-plugins-official 4
111 oh-my-claudecode@omc 4
112 plugin-dev@claude-code-plugins 4
113 product-management@knowledge-work-plugins 4
114 productivity@knowledge-work-plugins 4
115 qodo-skills@claude-plugins-official 4
116 security-guidance@claude-code-plugins 4
117 skill-codex@skill-codex 4
118 superpowers@anthropic-plugin-directory 4
119 superpowers@superpowers-dev 4
120 beads@beads-marketplace 3
121 dev-browser@dev-browser-marketplace 3
122 enterprise-search@knowledge-work-plugins 3
123 expo@expo-plugins 3
124 finance@knowledge-work-plugins 3
125 greptile@claude-plugins-official 3
126 kyosei@konoka 3
127 legal@knowledge-work-plugins 3
128 microsoft-docs@claude-plugins-official 3
129 nix-tasuke@konoka 3
130 operations@knowledge-work-plugins 3
131 planning-with-files@planning-with-files 3
132 postman@claude-plugins-official 3
133 programming-tasuke@konoka 3
134 pstack@pstack-claude 3
135 react-native-best-practices@callstack-agent-skills 3
136 security-scanning@claude-code-workflows 3
137 semgrep@claude-plugins-official 3
138 shopify-plugin@shopify-ai-toolkit 3
139 small-business@knowledge-work-plugins 3
140 superpowers-lab@superpowers-marketplace 3
141 terraform-skill@antonbabenko 3
142 terraform@claude-plugins-official 3
143 vercel-plugin@vercel-vercel-plugin 3
144 visual-explainer@visual-explainer-marketplace 3
145 vtsls@claude-code-lsps 3
146 agent-patterns-plugin@laurigates-claude-plugins 2
147 agent-store@tj-agents 2
148 agent@tj-agents 2
149 agentmemory@agentmemory 2
150 agents-plugin@laurigates-claude-plugins 2
151 astral@astral-sh 2
152 autoresearch@autoresearch 2
153 avoid-ai-writing@conorbronsdon-skills 2
154 baloo@bunderlog 2
155 base@tj-agents 2
156 basedpyright@claude-code-lsps 2
157 blueprint-plugin@laurigates-claude-plugins 2
158 brag@brag 2
159 bun-install@chewygumxx 2
160 cache-tax@claude-code-mods 2
161 cc-plugin-agents-md@builtin 2
162 cct@dagonet 2
163 claude-codex-computer-use@songkeys 2
164 claude-notifications-go@claude-notifications-go 2
165 claude-seo@agricidaniel-seo 2
166 cli@tj-agents 2
167 code-quality-plugin@laurigates-claude-plugins 2
168 codebase-mapper@eigenwise-toolshed 2
169 commit-commands@claude-code-plugins 2
170 communication-plugin@laurigates-claude-plugins 2
171 comprehensive-review@claude-code-workflows 2
172 configure-plugin@laurigates-claude-plugins 2
173 container-plugin@laurigates-claude-plugins 2
174 cowork-plugin-management@knowledge-work-plugins 2
175 customer-support@knowledge-work-plugins 2
176 dart-flutter@dart-flutter 2
177 data@knowledge-work-plugins 2
178 dd@datadog-claude-plugins 2
179 documentation-generation@claude-code-workflows 2
180 documentation-plugin@laurigates-claude-plugins 2
181 double-shot-latte@superpowers-marketplace 2
182 drawio@drawio 2
183 dx@ykdojo 2
184 engineering-advanced-skills@claude-code-skills 2
185 engineering@tj-agents 2
186 engram@engram 2
187 episodic-memory@superpowers-marketplace 2
188 evaluate-plugin@laurigates-claude-plugins 2
189 fallow@fallow-skills 2
190 feedback-plugin@laurigates-claude-plugins 2
191 flightdeck@claude-flightdeck 2
192 frontend-design@anthropic-plugin-directory 2
193 frontend-mobile-development@claude-code-workflows 2
194 frontend-slides@frontend-slides 2
195 git-plugin@laurigates-claude-plugins 2
196 github-actions-plugin@laurigates-claude-plugins 2
197 github-actions@tj-agents 2
198 github@anthropic-plugin-directory 2
199 gitkraken-hooks@gitkraken 2
200 harness@harness-marketplace 2
201 header-metadata@chewygumxx 2
202 health-plugin@laurigates-claude-plugins 2
203 hey@37signals 2
204 hooks-plugin@laurigates-claude-plugins 2
205 image-view@claude-image-view 2
206 infra@yeyo11 2
207 javascript-typescript@claude-code-workflows 2
208 laravel@laravel 2
209 linear-cli@linear-cli 2
210 live-rules@eigenwise-toolshed 2
211 macos-plugin@laurigates-claude-plugins 2
212 mcpmarket-me@mcpmarket-me 2
213 minimalist-entrepreneur@minimalist-entrepreneur 2
214 mintlify@claude-plugins-official 2
215 modern-web-guidance@claude-plugins-official 2
216 modern-web-guidance@googlechrome 2
217 neon-postgres@neon 2
218 obsidian-plugin@laurigates-claude-plugins 2
219 paper-desktop@paper 2
220 personal@tj-agents 2
221 phpstorm-plugin@phpstorm-marketplace 2
222 playwright-skill@playwright-skill 2
223 prisma@claude-plugins-official 2
224 prohibit-em-dash@chewygumxx 2
225 project-artifact@claude-plugins-official 2
226 project-plugin@laurigates-claude-plugins 2
227 prompt-engineering-plugin@laurigates-claude-plugins 2
228 prose-plugin@laurigates-claude-plugins 2
229 python-plugin@laurigates-claude-plugins 2
230 python@tj-agents 2
231 ralph-loop@claude-code-plugins 2
232 ralph-specum@smart-ralph 2
233 repo-memory@chewygumxx 2
234 repo-metadata@chewygumxx 2
235 ruflo-console@ruflo 2
236 ruflo-mods@ruflo 2
237 ruflo-swarm@ruflo 2
238 sales@knowledge-work-plugins 2
239 scientific-skills@claude-scientific-skills 2
240 seo-analysis-monitoring@claude-code-workflows 2
241 session-plugin@laurigates-claude-plugins 2
242 shannon@wincent-agent-plugins 2
243 simple-english@simple-english 2
244 skill-creator@anthropic-plugin-directory 2
245 static-analysis@trailofbits 2
246 superpowers-chrome@superpowers-marketplace 2
247 swift-concurrency@swift-concurrency-agent-skill 2
248 swiftui-expert@swiftui-expert-skill 2
249 taskwarrior-plugin@laurigates-claude-plugins 2
250 template@tj-agents 2
251 testing-plugin@laurigates-claude-plugins 2
252 tools-plugin@laurigates-claude-plugins 2
253 ux@claudefiles 2
254 vercel-plugin@vercel 2
255 voltagent-lang@voltagent-subagents 2
256 workflow-orchestration-plugin@laurigates-claude-plugins 2
257 workflow@tj-agents 2

Showing the top 300 per type. The filter box searches all 8,741 ranked components.

copied ✓