pillip/claude-dev-kit
A Claude Code kit that turns a PRD into shipped code — 32 AI agents, 21 skills, full implement-review-ship pipeline
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit pillip/claude-dev-kit/project/.claude ./rig-claude-dev-kit # 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 pillip/claude-dev-kit/skills/bizanalysis .claude/skills/bizanalysis $ npx degit pillip/claude-dev-kit/skills/brainstorm .claude/skills/brainstorm $ npx degit pillip/claude-dev-kit/skills/careful .claude/skills/careful $ npx degit pillip/claude-dev-kit/skills/desktop-uiux .claude/skills/desktop-uiux $ npx degit pillip/claude-dev-kit/skills/devops .claude/skills/devops $ npx degit pillip/claude-dev-kit/skills/diagnose .claude/skills/diagnose $ npx degit pillip/claude-dev-kit/skills/figma2proto .claude/skills/figma2proto $ npx degit pillip/claude-dev-kit/skills/freeze .claude/skills/freeze $ npx degit pillip/claude-dev-kit/skills/guard .claude/skills/guard $ npx degit pillip/claude-dev-kit/skills/implement .claude/skills/implement $ npx degit pillip/claude-dev-kit/skills/issue .claude/skills/issue $ npx degit pillip/claude-dev-kit/skills/kickoff .claude/skills/kickoff $ npx degit pillip/claude-dev-kit/skills/migrate .claude/skills/migrate $ npx degit pillip/claude-dev-kit/skills/mobile-uiux .claude/skills/mobile-uiux $ npx degit pillip/claude-dev-kit/skills/prd .claude/skills/prd $ npx degit pillip/claude-dev-kit/skills/refactor .claude/skills/refactor $ npx degit pillip/claude-dev-kit/skills/review .claude/skills/review $ npx degit pillip/claude-dev-kit/skills/scan .claude/skills/scan $ npx degit pillip/claude-dev-kit/skills/ship .claude/skills/ship $ npx degit pillip/claude-dev-kit/skills/spec .claude/skills/spec $ npx degit pillip/claude-dev-kit/skills/sprint .claude/skills/sprint $ npx degit pillip/claude-dev-kit/skills/testgen .claude/skills/testgen $ npx degit pillip/claude-dev-kit/skills/uiux .claude/skills/uiux
$ curl -fsSL --create-dirs -o .claude/agents/a11y-auditor.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/a11y-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/codebase-scanner.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/codebase-scanner.md $ curl -fsSL --create-dirs -o .claude/agents/data-modeler.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/data-modeler.md $ curl -fsSL --create-dirs -o .claude/agents/design-auditor.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/design-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/design-scanner.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/design-scanner.md $ curl -fsSL --create-dirs -o .claude/agents/desktop-uiux-developer.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/desktop-uiux-developer.md $ curl -fsSL --create-dirs -o .claude/agents/developer.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/developer.md $ curl -fsSL --create-dirs -o .claude/agents/figma-converter.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/figma-converter.md $ curl -fsSL --create-dirs -o .claude/agents/issue-writer.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/issue-writer.md $ curl -fsSL --create-dirs -o .claude/agents/mobile-uiux-developer.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/mobile-uiux-developer.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/qa-designer.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/qa-designer.md $ curl -fsSL --create-dirs -o .claude/agents/requirement-analyst.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/requirement-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/research-auditor.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/research-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/synthesizer-auditor.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/synthesizer-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/team-lead.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/team-lead.md $ curl -fsSL --create-dirs -o .claude/agents/test-generator.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/test-generator.md $ curl -fsSL --create-dirs -o .claude/agents/ui-reviewer.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/ui-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/uiux-developer.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/uiux-developer.md $ curl -fsSL --create-dirs -o .claude/agents/ux-designer.md https://raw.githubusercontent.com/pillip/claude-dev-kit/main/agents/ux-designer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (23)
bizanalysisbrainstormcarefuldesktop-uiuxdevopsdiagnosefigma2protofreezeguardimplementissuekickoffmigratemobile-uiuxprdrefactorreviewscanshipspecsprinttestgenuiux
Subagents (22)
| a11y-auditor | WCAG 2.1 AA accessibility audit — check color contrast, keyboard nav, screen reader support, touch targets, motion safety, and semantic structure. |
| architect | Design pragmatic software architecture from PRD and requirements. Make explicit tradeoffs, not theoretical diagrams. In evidence mode (invoked by /scan), documents the as-is architecture with CONFIRME |
| codebase-scanner | Analyze an existing codebase in 4 passes — identity, architecture, requirements inference, quality assessment. Produces structured scan_context for downstream scan agents. |
| data-modeler | Design detailed data models — schemas, indexes, migrations, seed data, query patterns. Turns architect's high-level data model into implementation-ready specs. In evidence mode (invoked by /scan when |
| design-auditor | Audit the design SYSTEM (tokens, component definitions, cross-platform alignment, philosophy compliance) — system-level only. Implementation-level checks belong to ui-reviewer. |
| design-scanner | Extract the design system a codebase already ships — tokens, type scale, spacing, motion, and a reverse-engineered Signature Move — from web, React Native, or Electron sources. Read-only, provenance-t |
| desktop-uiux-developer | Desktop UI/UX development expert who establishes design philosophy based on PRD and UX specs, and generates desktop design systems, wireframes, and Electron prototypes. |
| developer | Implement issues with tests and GitHub-first flow — create GH Issue (if missing) + PR with Closes #N. Write code that works, then code that's clean. |
| figma-converter | Convert Figma API design data (from figma_fetch.py) into clean prototype HTML using project design system tokens. Reads node trees, maps values to tokens, outputs semantic HTML. |
| issue-writer | Create a single well-formed issue from natural language and update relevant planning docs. |
| mobile-uiux-developer | Mobile UI/UX development expert who establishes design philosophy based on PRD and UX specs, and generates mobile design systems, wireframes, and React Native (Expo) prototypes. |
| planner | Break requirements into small, implementable issues with dependencies, ordering, and estimates. Maintain issues.md as SSOT; in evidence mode (invoked by /scan) derives improvement issues from scan obs |
| qa-designer | Design test strategy and test cases from requirements — risk-based prioritization, coverage matrix, not test code. In evidence mode (invoked by /scan), audits existing test coverage and gaps instead. |
| requirement-analyst | Analyze PRD.md and produce crisp requirements, scope, assumptions, and success metrics. In evidence mode (invoked by /scan), reverse-engineers requirements from code and tests with CONFIRMED/INFERRED |
| research-auditor | Separate-context auditor for the kit's degraded research path. Verifies that every claim in brainstorm_notes.md / business_analysis.md carries a verbatim quote that appears in the captured source snap |
| reviewer | Degraded-path fallback for /review's correctness + security dimensions (per SPEC-019), plus the kit-distinctive over-engineering minimality axis which runs on BOTH paths. On the primary path, kit /rev |
| synthesizer-auditor | Separate-context auditor for the kit's synthesis layer. Verifies that a /deep-research report's claims survive into the kit's rendered output without being dropped, distorted, or scope-changed. Refute |
| team-lead | Sprint phase executor — receives a specific phase (IMPLEMENT/REVIEW/SHIP) and target issues, executes that phase, updates sprint state. |
| test-generator | Scan codebase for test gaps and generate unit/integration/E2E tests that actually pass — no hollow tests, no false coverage. |
| ui-reviewer | Audit the design IMPLEMENTATION (rendered state coverage, copy usage, token usage in code, interaction fidelity, accessibility in code, component existence) — implementation-level only. System-level c |
| uiux-developer | UI/UX development expert who establishes design philosophy based on PRD and UX specs, and generates design systems, wireframes, and HTML prototypes. |
| ux-designer | Create UX spec (IA, flows, screen states, copy, a11y) from PRD. v0 scope — spec only, no visual design. |
Similar rigs
pruthvidarji1993/ai-automation-jira
AI-assisted dev workflow: Jira ticket in, reviewed PR out. Claude Code plugin + GitHub Copilot prompts with human approval gates (plan, diff).
Skill Collector 2.1k tok · · Q48
tammai/ai-sdlc
Claude Code plugin for vibe coding on the AI-native SDLC playbook: intent → design → spec → plan → verify → review → ship. Runs on a Claude subscription, with opinionated stacks (Nuxt/Next + Cloudflare, Go + Postgres, Flutter, Tauri) and de
Orchestrator 3.2k tok · · Q5
vannt-dev/governed-agent-sdlc
Ship with agents. Keep humans in control. Cross-platform governance toolkit for AI coding agents.
Fort Knox 632 tok · · Q24
romerma/mstack
Rigorous, verifiable agent workflows for Claude Code: gates that are code, not prose
Orchestrator 1.6k tok · · Q0