gongshichen/luminacode/code-review-checklist
Claude Code and agent skill by gongshichen/luminacode
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Review implementation changes for correctness and maintainability.
Install
npx vskill@latest install gongshichen/luminacode/code-review-checklistSKILL.md
Use this checklist to write or contribute to <project_root>/REVIEW_REPORT.md.
Review dimensions:
- Requirements and process
- User request is satisfied.
- PRD, UX design, backend plan, frontend plan, interface contract, integration report, QA report exist when applicable.
- Team Acceptance Contract matches the delivered architecture.
- Integration correctness
- User-facing component consumes the real backend/API/storage/tooling contract.
- No direct-file shortcut or mock-only substitute unless explicitly allowed.
- Contract fields, validation, errors, and ordering match implementation.
- Code correctness
- Main happy path works.
- Edge cases and validation behave predictably.
- Persistence, cleanup, and restart behavior are reasonable.
- No obvious race, partial-write, stale-state, or data-loss issue.
- CLI/terminal products cover parser-level errors as well as business errors: missing arguments, invalid argument types, unknown commands/options, empty input, nonexistent resources, and corrupted data/configuration.
- User-visible stdout/stderr, help text, and error text obey the requested locale and wording contract when localization is part of the user request, PRD, UX design, or Team Acceptance Contract.
- Security and privacy
- Secrets are not logged or committed.
- User input is handled safely for the stack.
- Trust boundaries, file paths, local ports, and permissions are appropriate.
- Maintainability
- Code follows existing project conventions or a justified simple local pattern.
- No unnecessary dependencies.
- Names and file structure are understandable.
- Errors and comments help future maintenance.
- QA evidence quality
- Required commands were actually run.
- Required commands are valid for the delivered stack. For Python CLI/package work,
python -m <name>must use an importable module/package name, not a hyphenated display name unless packaging defines that entrypoint. - Test/build evidence preserves the failing command's exit status; pipelines that truncate output must not hide failures.
- Integration smoke proves the real contract.
- Parent workspace cleanliness was checked.
- Review verification must not create undeclared helper scripts or temporary source/test files. Use existing tests and product commands, or ask Team Leader to add an expected artifact before writing a helper.
Finding format:
- Severity: blocking, non-blocking, note.
- Category.
- File/path or artifact.
- Evidence.
- Consequence.
- Recommended fix.
Verdict policy:
rejectfor unresolved blocking issues.- Treat unresolved violations of explicit user requirements, PRD acceptance criteria, UX requirements, or runtime contract items as blocking.
accepted_with_notesonly for truly non-blocking residuals.passonly when process, integration, correctness, and evidence are sufficient.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryChecking.Lumina/TEAM/product-development/reviewer/skills/code-review-checklist/SKILL.md
Popularity
- Repository stars
- 9
- Repository forks
- 1
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. 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/gongshichen/luminacode/code-review-checklist)