Code review hooks

mlflow/mlflow

Skill Claude CodeCodex

Review a pull request and emit a validated review payload.

mlflow/mlflow

Instructions file GitHub Copilot

Instructions for mlflow/mlflow, covering code review instructions, knowledge cutoff and do not comment on.

mlflow/mlflow

Instructions file GitHub Copilot

Instructions for mlflow/mlflow: For workflow style conventions, see .claude/rules/github-actions.md.

mastra-ai/mastra

Command Claude Code

../../.mastracode/commands/critique-pr.md.

mastra-ai/mastra

Command

GitHub OSS maintainer lifecycle triage, review, and approval management.

mastra-ai/mastra

Skill Claude CodeCodex

Re-review a pull request after a push — reconcile the previous review against the new commits, look for new defects the push introduced, then a fresh pass over the whole PR, and finish with a verdict on the PR.

QwenLM/qwen-code

Skill Claude CodeCodex ✓ vendor

A deep verification workflow for one Qwen Code pull request. It compares the proposed code with the original version and tests the changed behavior with scripts that do not rely on fake services.

PrefectHQ/fastmcp

Skill Claude CodeCodex

Monitor and respond to automated PR reviews (Codex bot). Use when pushing a PR, checking review status, or responding to bot feedback. Handles the full cycle of push -> wait for review -> evaluate comments -> fix -> re-push.

phuryn/pm-skills

Command

Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact.

phuryn/pm-skills

Command

Static security audit of AI-built code — map trust boundaries, cross-reference documented intent, self-refute every finding, and report only evidence-backed risks.

biomejs/biome

Skill Claude CodeCodex

Use this skill only when asked to review completed Biome changes in a PR, branch, commit range, diff, or working tree. Perform a read-only static review and report findings without editing files or running project code. Do not use for triage, reproduction, or implementation.

alirezarezvani/claude-skills

Skill Claude CodeCodexGemini CLI

../../../engineering-team/skills/adversarial-reviewer/SKILL.md.

EveryInc/compound-engineering-plugin

Command Claude Code

Triage all open PRs with parallel agents, label, group, and review one-by-one.

chromium/chromium

Command Gemini CLI

Add documentation to the methods for a diff from trunk.

modelcontextprotocol/python-sdk

Command Claude Code ✓ vendor

Command "review-pr" from modelcontextprotocol/python-sdk, covering step 1: resolve the pr, step 2: gather the diff, step 3: collect pr discussion context, step 4: find and read linked issues and step 5: analyze and validate.

activepieces/activepieces

Skill Claude CodeCodex

Review code for logging patterns and suggest evlog adoption. Guides setup on Nuxt, Next.js, SvelteKit, Nitro, TanStack Start, React Router, NestJS, Express, Hono, Fastify, Elysia, oRPC, Cloudflare Workers, and standalone TypeScript. Detects console.log spam, unstructured errors, and missing context. Covers wide…

slopus/happy

Agent Codex

GitHub issue and PR triage agent for slopus/happy. Use when you need to: review open issues/PRs, find duplicates, identify what needs a reply, close resolved items, draft maintainer responses, or get a status overview of the backlog. Invoke with /triage or when asked about issues, PRs, contributors, or community…

coleam00/Archon

Agent Claude Code

Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.

coleam00/Archon

Agent Claude Code

Autonomous code quality agent that scans for rule violations, fixes them in an isolated worktree, runs validation, creates a PR, and updates memory with findings for future runs.

coleam00/Archon

Agent Claude Code

Analyzes type design for encapsulation, invariant expression, and enforcement quality. Use when introducing new types, reviewing PRs with type changes, or refactoring existing types. Provides qualitative feedback and ratings (1-10) on four dimensions. Pragmatic focus.

dotnet/maui

Agent

Analyzes completed PRs for lessons learned, then applies improvements to instruction files, skills, and documentation.

dotnet/maui

Skill Claude CodeCodex

Deep code review of PR or materialized candidate-patch changes for correctness, safety, and MAUI conventions. Uses independence-first assessment (code before narrative) and delegates to the maui-expert-reviewer agent for per-dimension sub-agent evaluation. Triggers on: "review code for PR", "code review PR", "review…

oxc-project/oxc

Instructions file GitHub Copilot

Instructions for oxc-project/oxc: When reviewing pull requests in this repository.

vectorize-io/hindsight

Skill Claude CodeCodex

Review changed code against project standards. Checks for missing tests, dead code, type safety, lint issues, and coding conventions. Run after completing any implementation work.