sickn33/agentic-awesome-skills/code-review-excellence
Claude Code and agent skill by sickn33/agentic-awesome-skills
- community
Checking that the SKILL.md file is still in the repository.
Review a defined code diff for correctness, security, performance and maintainability; report evidence-backed findings with severity and actionable feedback.
Install
npx vskill@latest install sickn33/agentic-awesome-skills/code-review-excellenceSKILL.md
The same SKILL.md was published earlier as sickn33/agentic-awesome-skills/code-review-excellence.
Code Review Excellence
Review the actual base/head diff and relevant surrounding behavior. Separate reproducible defects from questions and optional suggestions.
Use this skill when
- Reviewing pull requests and code changes
- Establishing code review standards
- Mentoring developers through review feedback
- Auditing for correctness, security, or performance
Do not use this skill when
- There are no code changes to review
- The task is a design-only discussion without code
- You need to implement fixes instead of reviewing
Instructions
- Identify the exact base/head, requested review scope, requirements and available test evidence first.
- Review for correctness, security, performance, and maintainability.
- Provide actionable feedback with severity and rationale.
- Ask clarifying questions when intent is unclear.
- If detailed checklists are required, open
resources/implementation-playbook.md.
Output Format
- High-level summary of findings
- Issues grouped by severity (blocking, important, minor)
- Suggestions and questions
- Test and coverage notes
Worked example: a retry can create two records
Given a diff that retries a create request, inspect the caller, server handling and existing idempotency tests. If a lost response can lead to a second committed record, cite the changed lines and describe the trigger and consequence. Use an isolated fixture to reproduce it when available. Recommend a contract-compatible fix and a regression covering the lost-response case; avoid treating every retry as a defect.
Return each finding with severity, location, evidence, impact and a suggested correction. Label an untested hypothesis as such, and report no findings when the reviewed evidence supports none. A clean review is scoped to that diff and is not proof that the entire application is secure.
Resources
resources/implementation-playbook.mdfor detailed review patterns and templates.
Limitations
- Draft findings in the requested channel; this skill alone does not authorize posting comments, approving a PR or merging it.
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
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 repositoryCheckingplugins/agentic-awesome-skills/skills/code-review-excellence/SKILL.md
Popularity
- Repository stars
- 47,167
- Repository forks
- 6,871
- 7-day trend score
- 54
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/sickn33/agentic-awesome-skills/code-review-excellence)