Refactor high-complexity React components in Dify frontend. Use when `pnpm analyze-component...
npx skills add cordsjon/agentflow --skill "agentflow-dod"
Install specific skill from multi-skill repository
# Description
Run the Definition of Done gate check before deployment. Use when verifying work is complete, before committing, or when checking if a task meets exit criteria.
# SKILL.md
name: agentflow-dod
description: Run the Definition of Done gate check before deployment. Use when verifying work is complete, before committing, or when checking if a task meets exit criteria.
Definition of Done (DOD) Gate
Gate: Must pass BEFORE deployment.
An item that fails DOD cannot be deployed. The queue tail enforces this automatically.
Checklist
Code Quality
- [ ] All new code has tests β every US has a corresponding test file
- [ ] Tests pass β project's test suite 100% green
- [ ] No new test failures β pre-existing failures documented, zero regressions
- [ ] Quality audit clean β analysis returns only Low findings (or none). All findings classified using FIPD taxonomy (Fix/Investigate/Plan/Decide). Investigate/Decide findings must include an
Unknown:clause - [ ] Low findings fixed β cleanup applied and verified
Architecture
- [ ] Service-first β business logic in service layer, not route handlers
- [ ] No constraint violations β checked against project's constraints
- [ ] Backward compatible β or all callers updated
External Writes
- [ ] Dry-run before mutation β any write to files outside current task scope MUST preview changes before executing
Committed
- [ ] Clean commit β descriptive message, atomic scope
- [ ] No uncommitted changes β
git statusclean after commit - [ ] No secrets β no credentials, API keys, or tokens in committed code
- [ ] Pre-commit hooks pass β all configured hooks green
Deployable
- [ ] Application starts β server responds, no crash on boot
- [ ] Existing functionality intact β no regressions
Verification
- [ ] Verification pass β run with evidence (test output, screenshots) before marking task done
Pipeline Housekeeping
- [ ] Queue item checked β
[x]in TODO-Today.md - [ ] DONE-Today updated β item moved with timestamp
- [ ] BACKLOG updated β source item marked completed or removed
Enforcement (Mandatory Queue Tail)
1. Analyze changed files (findings use FIPD classification)
2. Deep audit (M+ size tasks only -- security/perf/architecture)
3. Cleanup (fix Low findings, enforce coding standards)
4. Run tests with coverage (if new test files)
5. Atomic conventional commit
6. Deploy (project-specific)
If any step fails, autopilot pauses and reports the blocker.
See checklist.md for a printable version.
# Supported AI Coding Agents
This skill is compatible with the SKILL.md standard and works with all major AI coding agents:
Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.