Stats
Actions
Tags
From dev-pipeline
The PRIMARY development workflow router for software engineering tasks. Routes development requests to specialized cookbooks based on intent. Routes to 10 specialized cookbooks based on what the user is trying to do: RESEARCH — "how does the orchestrator work?", "where is session state defined?", "trace the workflow execution flow", "what is IWorkflowStore?" INVESTIGATE — "should we use Drizzle or Prisma?", "what's the best way to add WebSockets?", "can we migrate to Turso?", "how do other projects handle rate limiting?" PRD — "write a PRD for dark mode", "spec out the notification feature", "product requirements for webhook retry" PLAN — "plan the auth refactor", "design the caching layer", "create an implementation plan for #42" IMPLEMENT — "implement the plan", "execute .claude/dev-pipeline/plans/auth.plan.md", "build the feature from the plan", "code this up" REVIEW — "review PR #123", "review my changes", "code review the diff" DEBUG — "debug the failing test", "why is streaming broken?", "root cause analysis on the timeout issue" COMMIT — "commit these changes", "commit the auth refactor" PR — "create a PR", "open a pull request for this branch" ISSUE — "report this to gh", "create a gh issue", "log it in github", "file a bug for this", "create a feature request" This skill triggers on ANY development task: researching, investigating, planning, building, reviewing, debugging, committing, or shipping code.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dev-pipeline:dev-pipelineThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Development workflow — research, plan, build, review, ship.
Development workflow — research, plan, build, review, ship.
git branch --show-current 2>/dev/null || echo "not in git repo"ls .claude/dev-pipeline/ 2>/dev/null || echo "none yet"ls .claude/dev-pipeline/plans/*.plan.md 2>/dev/null | head -5 || echo "none"Read $ARGUMENTS and determine which cookbook to load.
If the user explicitly names a cookbook (e.g., "plan", "implement"), use that. Otherwise, match intent from keywords:
| Intent | Keywords | Cookbook |
|---|---|---|
| Codebase questions, document what exists | "research", "how does", "what is", "where is", "trace", "find" | cookbooks/research.md |
| Strategic research, library eval, feasibility | "investigate", "should we", "can we", "compare", "evaluate", "feasibility", "best way to", "best approach" | cookbooks/investigate.md |
| Write product requirements | "prd", "requirements", "spec", "product requirement" | cookbooks/prd.md |
| Create implementation plan | "plan", "design", "architect", "write a plan" | cookbooks/plan.md |
| Execute an existing plan | "implement", "execute", "build", "code this", path to .plan.md | cookbooks/implement.md — authoritative; do NOT also invoke superpowers:executing-plans, superpowers:subagent-driven-development, or superpowers:verification-before-completion |
| Review code or PR | "review", "review PR", "code review", "review changes" | cookbooks/review.md |
| Debug or root cause analysis | "debug", "rca", "root cause", "why is", "broken", "failing" | cookbooks/debug.md — authoritative; do NOT also invoke superpowers:systematic-debugging |
| Commit changes | "commit", "save changes", "stage" | cookbooks/commit.md |
| Create pull request | "pr", "pull request", "create pr", "open pr" | cookbooks/pr.md |
| Report to GitHub | "issue", "report to gh", "log in github", "file a bug", "feature request", "create issue", "gh issue" | cookbooks/issue.md |
If ambiguous: Ask the user which cookbook to use.
After routing: Read the matched cookbook file and follow its instructions exactly.
Cookbooks feed into each other. After completing one, suggest the next:
research ──► investigate ──► prd ──► plan ──► implement ──► commit ──► pr
▲ │
debug ───────────┘ review ◄──────┘
│
▼
issue ──► plan (if feature) or debug (if bug)
All artifacts go to .claude/dev-pipeline/. Create subdirectories as needed on first use.
.claude/dev-pipeline/
├── prds/ # Product requirement documents
├── plans/ # Implementation plans
│ └── completed/ # Archived after implementation
├── reports/ # Implementation reports
├── issues/ # GitHub issue investigations
│ └── completed/
├── reviews/ # PR review reports
├── debug/ # Root cause analysis
└── research/ # Research findings
Do NOT hardcode project-specific commands. Detect dynamically:
bun.lockb → bun, pnpm-lock.yaml → pnpm, yarn.lock → yarn, else npmpackage.json scripts for validate, check, or verifytest script in package.jsonfile:linenpx claudepluginhub tviles/claude-plugins --plugin dev-pipelineGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.