code-reviewer

This skill guides the agent in conducting professional and thorough code reviews for both local development and remote Pull Requests.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "code-reviewer" with this command: npx skills add gemini-cli-extensions/workspace/gemini-cli-extensions-workspace-code-reviewer

Code Reviewer

This skill guides the agent in conducting professional and thorough code reviews for both local development and remote Pull Requests.

Workflow

  1. Determine Review Target
  • Remote PR: If the user provides a PR number or URL (e.g., "Review PR #123"), target that remote PR.

  • Local Changes: If no specific PR is mentioned, or if the user asks to "review my changes", target the current local file system states (staged and unstaged changes).

  1. Preparation

For Remote PRs:

  • Checkout: Use the GitHub CLI to checkout the PR. gh pr checkout <PR_NUMBER>

  • Verification: Execute the workspace's verification suite to catch issues early. Capture the output of these commands to inform your review (e.g., note any failed tests or linting errors). npm install npm run build npm run test npm run lint npm run format:check

  • Context: Read the PR description and any existing comments to understand the goal and history.

For Local Changes:

  • Identify Changes:

  • Check status: git status

  • Read diffs: git diff (working tree) and/or git diff --staged (staged).

  • Verification: Ask the user if they want to run the verification suite before reviewing. If yes, run the same commands as for remote PRs.

  1. In-Depth Analysis

Analyze the code changes based on the following pillars:

  • Correctness: Does the code achieve its stated purpose without bugs or logical errors?

  • Maintainability: Is the code clean, well-structured, and easy to understand and modify in the future? Consider factors like code clarity, modularity, and adherence to established design patterns.

  • Readability: Is the code well-commented (where necessary) and consistently formatted according to our project's coding style guidelines?

  • Efficiency: Are there any obvious performance bottlenecks or resource inefficiencies introduced by the changes?

  • Security: Are there any potential security vulnerabilities or insecure coding practices?

  • Edge Cases and Error Handling: Does the code appropriately handle edge cases and potential errors?

  • Testability: Is the new or modified code adequately covered by tests (even if preflight checks pass)? Suggest additional test cases that would improve coverage or robustness.

  1. Draft Feedback (DO NOT FIX)

IMPORTANT: You are a reviewer, NOT a fixer. Do NOT attempt to fix the code yourself. Your goal is to provide high-quality feedback.

Structure

  • Summary: A high-level overview of the review.

  • Verification Results: briefly summarize the results of the build, test, lint, and format checks.

  • Findings:

  • Critical: Bugs, security issues, test failures, lint errors, or breaking changes.

  • Improvements: Suggestions for better code quality or performance.

  • Nitpicks: Formatting or minor style issues (optional).

  • Conclusion: Clear recommendation (Approved / Request Changes).

Tone

  • Be constructive, professional, and friendly.

  • Explain why a change is requested.

  • For approvals, acknowledge the specific value of the contribution.

  1. Interactive Refinement
  • Present Draft: Show the drafted review feedback to the user.

  • Solicit Input: Ask the user for their thoughts.

  • "Does this feedback look accurate?"

  • "Is the tone appropriate?"

  • "Did I miss any context?"

  • Iterate: If the user provides suggestions or corrections, update the draft feedback accordingly.

  • Finalize: specific approval from the user is not strictly required if they don't have further comments, but ensure they have a chance to respond.

  1. Cleanup (Remote PRs only)
  • After the review is complete, ask the user if they want to switch back to the default branch (e.g., main or master ).

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

code-reviewer

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

code-reviewer

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

code-reviewer

No summary provided by upstream source.

Repository SourceNeeds Review