rafaie/codex_home/implementation-phase
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Run test-plan, write-tests, and implement-feature as one implementation workflow. Use when a work item is specified and ready to move from reviewed documentation through tests and code.
Install
npx vskill@latest install rafaie/codex_home/implementation-phaseSKILL.md
1) Read project AGENTS.md, codex.toml (if present), and target work item folder spec/features/<work-id>-<slug>/.
<work-id>must useS-<stream>-<nnn>(example:S-core-001) for new work.- For legacy single-file specs, read the matching file under
spec/features/.
2) Execute the implementation phase in this exact order for the same work item ID:
Run $test-plan <work-id>Run $write-tests <work-id>Run $implement-feature <work-id>
3) Validate outcomes after each step:
test-plan:test-plan.mdis updated with AC-mapped cases and fixtures.write-tests: tests are added/updated undertests/, the quick command is run, and the result is classified as passing, expected red, or unexpected failure.- Expected red is allowed only when each failure maps to an unimplemented AC, the failing signatures are recorded in
test-results.md, and no previously passing behavior regressed. implement-feature: AC checklist is completed, implementation checks pass, and work item docs include commands plus milestone smoke evidence when applicable.
4) Failure handling:
- Continue from
write-teststoimplement-featurefor a documented expected-red baseline. - Unexpected deterministic failures: run
debug-loop. - Many simultaneous failures: run
failure-triage. - Do not continue when failures are unrelated to unimplemented ACs, alter existing behavior, or cannot be explained.
5) End with a concise status summary:
- completed steps
- blockers/deferred items (if any)
- next recommended command:
Run $ship-feature <work-id> ...when all steps are complete- otherwise
Run $debug-loop ...with the failing signature
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/implementation-phase/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/rafaie/codex_home/implementation-phase)