Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.
NewMaintained
Automatic
◆Coding pack
Last verified 8/3/2026
What it changes
Passed 10 of 22 test cases with the skill, and 10 of 22 without it.
Without skill45%
With skill45%
Checks it passed that the model alone missed
Executes npm run preflight as part of preparation.
Executes gh pr checkout 999 to switch to the PR branch.
Asks whether to run npm run preflight before starting the review.
and 1 more in the full report
4 fixed6 passed either way8 still failing4 broke
Pass-rate lift
0 pp
Tokens
+4%
Agent turns
0%
Response time
-36%
Model gemini-3.6-flashMeasured 8/3/2026v1 · latest is v210 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/15/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
What's inside
The instructions your model reads when the skill loads.
SKILL.md61 linessingle file
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).
2. Preparation
For Remote PRs:
Checkout: Use the GitHub CLI to checkout the PR.
gh pr checkout <PR_NUMBER>
Preflight: Execute the project's standard verification suite to catch automated failures early. Detect the command rather than assuming one — look for the conventional entrypoint in this order and run the first that applies:
A Makefile target such as make check / make test / make lint.
An npm/pnpm/yarn script (package.json → preflight, check, test, lint).
A language-native runner (cargo test, pytest, go test ./..., etc.).
If the repo root has a flake.nix or .envrc (direnv), wrap the command with nix develop -c … per the nix-develop-shell skill.
If no verification command is discoverable, skip this step and note it in the review.
Context: Read the PR description and any existing comments to understand the goal and history.
Preflight (Optional): If the changes are substantial, ask the user if they want to run the project's verification suite (detected as in the Remote PR flow above) before reviewing.
3. 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?