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.
npm run preflight
- 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).
- Preflight (Optional): If the changes are substantial, ask the user if they want to run
npm run preflight 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?
- 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.
4. Provide Feedback
Structure
- Summary: A high-level overview of the review.
- Findings:
- Critical: Bugs, security issues, 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.
5. Cleanup (Remote PRs only)
- After the review, ask the user if they want to switch back to the default branch (e.g.,
main or master).
Security Deep-Dive (Trail of Bits Skills)
When the code review involves security-sensitive areas (auth, crypto, input handling, privilege escalation, memory safety, access control), escalate to Trail of Bits specialized skills:
| Skill |
Trigger |
/insecure-defaults |
Default configs, hardcoded values, weak crypto params |
/static-analysis |
Logic bugs, null dereference, race conditions |
/differential-review |
What changed vs. what was intended — spotting regressions |
/variant-analysis |
Same bug class appearing in multiple places |
/sharp-edges |
Language-specific pitfalls (JS prototype pollution, Python pickle, etc.) |
/audit-context-building |
Before a full audit — maps attack surface, entry points, trust boundaries |
Auto-escalate when reviewing:
- Auth flows, JWT handling, session management
- File upload / path traversal risks
- SQL queries or raw DB access
- Any
eval(), exec(), subprocess, dynamic imports
- Cryptographic operations
- API endpoints accepting user-controlled data without validation
Say: "🔒 Security-sensitive code detected — escalating to Trail of Bits audit skills."
1---2name: code-reviewer3description: 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.4---56# Code Reviewer78This skill guides the agent in conducting professional and thorough code reviews for both local development and remote Pull Requests.910## Workflow1112### 1. Determine Review Target13* **Remote PR**: If the user provides a PR number or URL (e.g., "Review PR #123"), target that remote PR.14* **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).1516### 2. Preparation1718#### For Remote PRs:191. **Checkout**: Use the GitHub CLI to checkout the PR.20 ```bash21 gh pr checkout <PR_NUMBER>22 ```232. **Preflight**: Execute the project's standard verification suite to catch automated failures early.24 ```bash25 npm run preflight26 ```273. **Context**: Read the PR description and any existing comments to understand the goal and history.2829#### For Local Changes:301. **Identify Changes**:31 * Check status: `git status`32 * Read diffs: `git diff` (working tree) and/or `git diff --staged` (staged).332. **Preflight (Optional)**: If the changes are substantial, ask the user if they want to run `npm run preflight` before reviewing.3435### 3. In-Depth Analysis36Analyze the code changes based on the following pillars:3738* **Correctness**: Does the code achieve its stated purpose without bugs or logical errors?39* **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.40* **Readability**: Is the code well-commented (where necessary) and consistently formatted according to our project's coding style guidelines?41* **Efficiency**: Are there any obvious performance bottlenecks or resource inefficiencies introduced by the changes?42* **Security**: Are there any potential security vulnerabilities or insecure coding practices?43* **Edge Cases and Error Handling**: Does the code appropriately handle edge cases and potential errors?44* **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.4546### 4. Provide Feedback4748#### Structure49* **Summary**: A high-level overview of the review.50* **Findings**:51 * **Critical**: Bugs, security issues, or breaking changes.52 * **Improvements**: Suggestions for better code quality or performance.53 * **Nitpicks**: Formatting or minor style issues (optional).54* **Conclusion**: Clear recommendation (Approved / Request Changes).5556#### Tone57* Be constructive, professional, and friendly.58* Explain *why* a change is requested.59* For approvals, acknowledge the specific value of the contribution.6061### 5. Cleanup (Remote PRs only)62* After the review, ask the user if they want to switch back to the default branch (e.g., `main` or `master`).6364## Security Deep-Dive (Trail of Bits Skills)6566When the code review involves security-sensitive areas (auth, crypto, input handling, privilege escalation, memory safety, access control), escalate to Trail of Bits specialized skills:6768| Skill | Trigger |69|-------|---------|70| `/insecure-defaults` | Default configs, hardcoded values, weak crypto params |71| `/static-analysis` | Logic bugs, null dereference, race conditions |72| `/differential-review` | What changed vs. what was intended — spotting regressions |73| `/variant-analysis` | Same bug class appearing in multiple places |74| `/sharp-edges` | Language-specific pitfalls (JS prototype pollution, Python pickle, etc.) |75| `/audit-context-building` | Before a full audit — maps attack surface, entry points, trust boundaries |7677**Auto-escalate when reviewing:**78- Auth flows, JWT handling, session management79- File upload / path traversal risks 80- SQL queries or raw DB access81- Any `eval()`, `exec()`, `subprocess`, dynamic imports82- Cryptographic operations83- API endpoints accepting user-controlled data without validation8485Say: `"🔒 Security-sensitive code detected — escalating to Trail of Bits audit skills."`
chidekina