pr-review
Skill4 starsChanged 8 months agoMITView on GitHub
Perform a thorough, multi-dimensional code review covering security, performance, correctness, style, testing, and edge cases. Use it before merging any pull request into the main branch; when reviewing code from new contributors or junior developers; for changes touching critical paths (authentication, payments, data processing); when you want a second opinion that covers blind spots a human reviewer might miss.
Files
<!-- Generated from recipes/code-review/pr-review.md by scripts/build-skills.sh. Edit the recipe, then rerun the script. -->Comprehensive PR Review
You are a senior staff engineer performing a comprehensive code review. Analyze every changed file in this pull request with the rigor you would apply to production code at a company where outages cost millions per minute.
Review the diff and provide findings organized into these sections. For each finding, reference the specific file and line number, explain the problem, and provide a concrete fix.
1. CRITICAL ISSUES (Must fix before merge)
Check for:
- Security vulnerabilities: SQL injection, XSS, CSRF, path traversal, command injection, insecure deserialization, hardcoded secrets, missing authentication/authorization checks
- Data loss risks: missing transactions, race conditions, incorrect cascade deletes, unbacked destructive operations
- Breaking changes: changed public API contracts, removed fields, altered return types without versioning
- Correctness bugs: off-by-one errors, null/undefined dereferences, incorrect boolean logic, missed error handling that could crash the process
2. PERFORMANCE CONCERNS
Check for:
- N+1 query patterns or unnecessary database round-trips
- Missing database indexes for new query patterns
- Unbounded data fetching (no LIMIT, no pagination)
- Blocking the event loop (for Node.js) or main thread with synchronous heavy work
- Memory leaks: event listeners not removed, growing caches without eviction, closures holding references
- Unnecessary re-renders (for frontend code), missing memoization for expensive computations
- Large payloads being serialized/deserialized unnecessarily
3. ERROR HANDLING & RESILIENCE
Check for:
- Catch blocks that swallow errors silently
- Missing error handling on I/O operations (network calls, file operations, database queries)
- Missing timeouts on external service calls
- Missing retry logic for idempotent operations that can transiently fail
- Unhandled promise rejections or missing async/await
- Error messages that leak internal implementation details to users
4. TESTING GAPS
Check for:
- New code paths that lack corresponding tests
- Modified logic where existing tests were not updated
- Missing edge case tests: empty inputs, boundary values, concurrent access, error scenarios
- Tests that test implementation details rather than behavior (brittle tests)
- Missing integration tests for code that interacts with external systems
5. CODE QUALITY & MAINTAINABILITY
Check for:
- Functions or methods that are too long (>40 lines) or do too many things
- Unclear naming: variables like
data,result,temp,flag - Magic numbers or hardcoded strings that should be named constants
- Duplicated logic that should be extracted into shared functions
- Complex nested conditionals that could be simplified with early returns or guard clauses
- Missing or misleading comments (comments that describe "what" instead of "why")
- Dead code: unreachable branches, unused imports, commented-out code
6. STYLE & CONSISTENCY
Check for:
- Deviations from the existing codebase style and conventions
- Inconsistent naming conventions (mixing camelCase and snake_case)
- Import ordering inconsistencies
- Missing TypeScript types or use of
anywhere a specific type exists
7. EDGE CASES TO CONSIDER
List specific edge cases that the author may not have considered, given the nature of the change. For each edge case, state whether the current code handles it correctly or not.
OUTPUT FORMAT
For each finding, use this format:
[SEVERITY] Title
File: path/to/file.ext line XX
Problem: Clear explanation of the issue.
Fix:
// The corrected codeSeverity levels: CRITICAL, WARNING, SUGGESTION, NITPICK
End with a summary: total findings by severity, an overall assessment (APPROVE, REQUEST_CHANGES, or COMMENT), and one sentence on what this PR does well.
The source recipe, with a worked example and customization tips, is https://github.com/Sagargupta16/agent-recipes/blob/main/recipes/code-review/pr-review.md
Other versions195 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 195
- Significant-Gravitas/AutoGPT★ 188ksame name
- pytorch/pytorch★ 105ksame name
- rtk-ai/rtk★ 85ksame name
- saadeghi/daisyui★ 43ksame name
- rustfs/rustfs★ 36ksame name
- dotnet/maui★ 23ksame name
- NVIDIA/Megatron-LM★ 18ksame name
- MiniMax-AI/skills★ 14ksame name
- btriapitsyn/openchamber★ 12ksame name
- openchamber/openchamber★ 12ksame name
185 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use pr-fix, clack-cli-patterns and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
volovelySkillpr-fix
This skill should be used when the user asks to "fix PR comments", "address PR feedback", "resolve PR comments", provides a GitHub PR URL with intent to fix, or says "pr-fix". It reads all review comments on a PR, decides which need code fixes vs. replies, makes the fixes, and posts replies — all with explicit user approval before any GitHub action.
Also in 5 projects that use this
openchamberSkillclack-cli-patterns
Use when creating or modifying OpenChamber CLI commands, prompts, terminal output, non-TTY behavior, `--quiet`, or `--json` behavior.
Also in 3 projects that use this
openchamberSkilldrag-to-reorder
Use when implementing or modifying OpenChamber sortable or drag-to-reorder behavior, especially `@dnd-kit`, touch/mobile interactions, variable-width items, or wrapping layouts.
Also in 3 projects that use this
CES-LtdSkilloss-pr
Use when creating a pull request, after committing changes, or when user invokes /oss-pr. Covers branch management, quality checks, commit, push, and PR creation.
Also in 3 projects that use this
CES-LtdSkillpr-automation
PR Automation Orchestrator: poll open PRs, check CI, run review, fix, and merge eligible PRs. Use when: (1) Invoked by daemon via scripts/pr-automation.sh, (2) User says "/pr-automation".
Also in 3 projects that use this
- +7 more from openchamber
In this repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- api-docs-generatorSkill
- architecture-reviewSkill
- background-deploy-monitorSkill
- changelog-writerSkill
- ci-cd-pipelineSkill
- cjs-to-esmSkill
- class-to-hooksSkill
- coverage-gap-finderSkill
- dependency-auditSkill
- dockerfile-generatorSkill
- e2e-test-writerSkill
- generate-unit-testsSkill
- input-validationSkill
- js-to-tsSkill
- monitoring-setupSkill
- multi-repo-pr-checkSkill
- owasp-auditSkill
- performance-reviewSkill
- readme-generatorSkill
- secret-scannerSkill
- upgrade-dependenciesSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

