agentrigs
+ submit rig
~ / rigs / ashish7802 / awesome-agent-skills

ashish7802/awesome-agent-skills

The ultimate open-source directory of production-grade AI Agent skills, system instructions, and custom rules (.mdc) for Cursor, Claude Code, Windsurf, and Copilot. Stop writing code from scratch—just copy, paste, and vibe-code at 10x speed

↗ GitHub ★ 2 no license updated 26d ago collection Claude CodeCursor
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~221 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit ashish7802/awesome-agent-skills/.claude ./rig-awesome-agent-skills  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit ashish7802/awesome-agent-skills/.claude/skills/clickhouse-analytics .claude/skills/clickhouse-analytics
$ npx degit ashish7802/awesome-agent-skills/.claude/skills/deterministic-ai-orchestrator .claude/skills/deterministic-ai-orchestrator
$ npx degit ashish7802/awesome-agent-skills/.claude/skills/flutter-riverpod-clean .claude/skills/flutter-riverpod-clean
$ npx degit ashish7802/awesome-agent-skills/.claude/skills/react-router-v7-ssr .claude/skills/react-router-v7-ssr
$ npx degit ashish7802/awesome-agent-skills/.claude/skills/sveltekit-runes .claude/skills/sveltekit-runes
$ npx degit ashish7802/awesome-agent-skills/.claude/skills/terraform-aws-modules .claude/skills/terraform-aws-modules

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(~/.aws/**)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(.env)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/.env.*)",
      "Read(**/*.key)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(npm publish:*)",
      "Bash(wget *)",
      "Bash(git rebase *)",
      "Bash(gh pr merge *)",
      "Bash(git commit *)"
    ]
  }
}

Skills (6)

clickhouse-analyticsdeterministic-ai-orchestratorflutter-riverpod-cleanreact-router-v7-ssrsveltekit-runesterraform-aws-modules

Cursor rules (12)

cloudflare-workers-honoexpo-new-architecturefastapi-async-optimizationgolang-grpc-microserviceslanggraph-multi-agentnextjs-15-approuterowasp-api-securityplaywright-e2e-suiteprisma-cockroachdb-harust-wasm-optimizationsupabase-postgres-rlszig-memory-safety

Similar rigs

ericrisco/rsc-harness
Your agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives it both, plus the trade to know the job and the reflexes to not break your repo. For Claude Code, C
★ 164 setup Claude Code 150 skills 2d ago
Skill Collector 7.6k tok ·
anomalyco/opencode
The open source coding agent.
★ 212k project Codex 2 skills 1d ago
Pragmatist 4.2k tok ·
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
★ 155k project CodexCursorCopilot 6 skills 4d ago
Pragmatist 1.6k tok ·
Shubhamsaboo/awesome-llm-apps
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
★ 141k project Claude CodeCodex 1 mcp 3 skills 9d ago
Pragmatist 4.2k tok ·
copied ✓