rafaie/codex_home/test-plan
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Create an AC-mapped unit, integration, edge, and smoke test plan for a documented work item. Use before tests or implementation are written.
Install
npx vskill@latest install rafaie/codex_home/test-planSKILL.md
1) Read AGENTS.md, codex.toml (if present), and the 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/. - Source acceptance criteria from
feature.md(or the legacy single-file spec).
2) Convert acceptance criteria into a test matrix:
- Preserve stable identifiers (
AC-1,AC-2, etc.) in every mapping. - Unit tests (fast, isolated)
- Integration tests (component boundaries)
- End-to-end / scenario tests (happy path + key edge cases)
- Negative/error cases (validation, permissions, timeouts, etc.)
3) Decide what to mock vs run for real (with rationale). 4) Update test-plan.md with:
- Test cases mapped to ACs
- Test data/fixtures needed
- Any required test hooks/utilities
- Smoke plan fields:
- applicability:
requiredornot_applicable - rationale when not applicable; only non-runnable work may use this value
- scenario ID/name
- fixture path
- expected output shape (schema and invariants)
- pass/fail mode (schema/invariants only, or schema/invariants/golden)
- runtime constraints (mode, network/env, time budget, request/token budget)
- artifact path expectation (
artifacts/smoke/...) - Omit scenario/fixture/artifact fields only when applicability is
not_applicableand the rationale is documented.
5) End by recommending write-tests.
- Output exactly:
Next recommended skill:Run $write-tests <work-id> to implement the planned unit/integration/edge-case tests.- Replace
<work-id>with the real ID from the target folder (example:S-core-001). - Do not use markdown links or absolute file paths in this recommendation.
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/test-plan/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/test-plan)