code-review
sammcj/agentic-coding/Skills/code-review/SKILL.md
Use when the user asks for a code review of a change, branch or PR.
Often used withclose-specadd-new-modelcompare-screenshots
One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
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.
sammcj/agentic-coding/Skills/code-review/SKILL.md
Use when the user asks for a code review of a change, branch or PR.
Often used withclose-specadd-new-modelcompare-screenshots
colasama/MahoShojo-Generator/.agents/skills/code-review/SKILL.md
Use when reviewing MahoShojo-Generator code, a branch, commit range, pull request, or implementation against current behavior and accepted ADR/spec requirements. Do not use when the primary request is to implement a known fix.
Often used withclose-specadd-new-modelcompare-screenshots
OpenHands/extensions/skills/code-review/SKILL.md
Review code changes for material correctness, security, compatibility, and maintainability risks, grounded in the current repository and acceptance criteria.
Often used withclose-specadd-new-modelcompare-screenshots
totvs/engpro-advpl-tlpp-skills/skills/advpl-tlpp/code-review/SKILL.md
Perform comprehensive AdvPL/TLPP code review covering SonarQube rules, Protheus.doc documentation, security, performance, clean code, and TOTVS Protheus framework best practices. Use when a user says "review this code", "code review", "check this source", "audit this AdvPL/TLPP", or needs a structured quality assessment of .prw/.tlpp/.prx files.
Often used withclose-specadd-new-modelcompare-screenshots
Azure/AgentBaker/.github/skills/code-review/SKILL.md
Review AgentBaker pull requests and diffs for production regressions, backward compatibility, security, architecture, cross-OS behavior, provisioning failures, and risky package updates. Use this skill whenever reviewing AgentBaker code, pull requests, diffs, dependency bumps, or changes to Linux or Windows VHD build and node provisioning paths.
Often used withclose-specadd-new-modelcompare-screenshots
HybridAIOne/hybridclaw/skills/code-review/SKILL.md
Review diffs and change sets for bugs, regressions, risks, and missing tests.
Often used withclose-specadd-new-modelcompare-screenshots
irahardianto/awesome-agv/.agents/skills/code-review/SKILL.md
Structured code review protocol for inspecting code quality against the full rule set. Use when auditing code written by yourself or another agent, during the /audit skill, or when the user asks for a code review.
Often used withclose-specadd-new-modelcompare-screenshots
brevdev/workshop-build-an-agent/skills/code-review/SKILL.md
Systematic approach to reviewing code for quality and correctness
Often used withclose-specadd-new-modelcompare-screenshots
yamcodes/arkenv/skills/code-review/SKILL.md
Fetch, analyze, and address code reviews and comments on GitHub, or perform a code review on changes in the workspace. Make sure to use this skill whenever the user mentions code reviews, addressing PR reviews, fixing PR comments, resolving review feedback, performing a code review, or running '/code-review', even if they don't explicitly name GitHub or the PR number.
Often used withclose-specadd-new-modelcompare-screenshots
imbenrabi/Financial-Modeling-Prep-MCP-Server/.claude/skills/code-review/SKILL.md
Review a PR or working diff against this repo's intent layer (the AGENTS.md hierarchy), toolception pitfalls, and core invariants. Use when reviewing code, auditing a PR, or checking changes before merge in the Financial Modeling Prep MCP server. Triggers on: "review", "code review", "review this PR", "review the diff", "audit", "check this diff", "before merge", "pull request review", "PR review".
Often used withclose-specadd-new-modelcompare-screenshots
Azure/sap-automation/.github/skills/code-review/SKILL.md
Review pull requests in the SAP Deployment Automation Framework. Use when reviewing a diff, a pull request, or staged changes touching Terraform modules, Ansible roles and playbooks, the deployer shell scripts, the Python helpers, or the GitHub Actions workflows. Reviews for correctness, reliability, security, Azure/SAP domain rules, performance, test coverage, and maintainability — in that priority order. Finds defects that change one sibling module and not the other four, widen a network or an RBAC scope without saying so, break idempotency and force a resource replace, or leave one half of the SUSE/RHEL or HANA topology matrix unhandled.
Often used withclose-specadd-new-modelcompare-screenshots
microsoft/vscode-containers/.github/skills/code-review/SKILL.md
Review a pull request in this repository (the vscode-containers / Container Tools extension) when the automated reviewer has already supplied the diff and changed files. Checks localization, async/resource correctness, TypeScript conventions, command-line construction, telemetry, settings, and cross-platform issues distilled from this repo's review history. For an on-demand review by PR number, URL, or current branch, use review-pr instead.
Often used withclose-specadd-new-modelcompare-screenshots
langchain-ai/langchain-azure/.github/skills/code-review/SKILL.md
Reviews changes in the langchain-azure monorepo using package-specific knowledge of langchain-azure-ai, langchain-azure-compute, langchain-azure-cosmosdb, langchain-azure-postgresql, langchain-azure-storage, langchain-sqlserver, and langchain-azure-dynamic-sessions, together with the LangChain, LangGraph, Deep Agents, and Azure SDK contracts each package must satisfy. Use this skill whenever reviewing a pull request or diff, checking code for bugs or regressions, or assessing changes under libs/, samples/, or .github/ in this repository, including when the request is only to "review", "check", "look at", or "give feedback on" a change, and even when no package is named explicitly.
Often used withclose-specadd-new-modelcompare-screenshots
luongnv89/skills/skills/code-review/SKILL.md
Review or improve code — one skill, four modes: bug/security review (default), performance, clean-code audit, slop cleanup. Pass mode:review|perf|clean|cleanup or infer. Don't use for writing features or generating tests (use test-coverage).
Often used withclose-specadd-new-modelcompare-screenshots
Kangentic/kangentic/.claude/skills/code-review/SKILL.md
Review git changes for quality and conventions via parallel reviewer subagents synthesized in the main agent (fixes everything it verifies in or out of the diff, records the decisions it made, fills red-green test-coverage holes, commits that pass locally, and ends Ready or Blocked from a script, sending what it could not finish back as numbered steps, never as new tasks)
Often used withclose-specadd-new-modelcompare-screenshots
GoogleCloudPlatform/cloud-solutions/projects/build-with-gemini-demo/build-with-antigravity/.agents/skills/code-review/SKILL.md
Reviews project source code against workspace development standards covering copyright headers, documentation completeness, PEP 8 style, logging, error handling, and dependency hygiene. Use when performing a local code review or checking code quality. Don't use for GitHub pull request creation or dependency installation.
Often used withclose-specadd-new-modelcompare-screenshots
rengwu/wayfinder-maps/skills/.optional/review-code/SKILL.md
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating spec/PRD asked for?). Use when the user wants to review a branch, work-in-progress changes, or asks to "review since X".
hw-native-sys/pypto/.claude/skills/code-review/SKILL.md
Review code changes against PyPTO project standards before committing. Use when reviewing code, preparing commits, checking pull requests, or when the user asks for code review.
Often used withclose-specadd-new-modelcompare-screenshots
Azure/azure-sdk-tools/.github/skills/code-review/SKILL.md
Guide GitHub Copilot code review (CCR) for PRs and diffs that change tools/azsdk-cli, focusing on high-confidence behavioral and integration defects beyond analyzers. WHEN: 'GitHub Copilot code review for azsdk-cli', 'CCR review of an azsdk-cli PR', 'Copilot review of tools/azsdk-cli changes'.
Often used withclose-specadd-new-modelcompare-screenshots
jellydn/my-ai-tools/skills/code-review/SKILL.md
Review a branch, PR, or worktree diff for repository conventions and stated intent.
Often used withclose-specadd-new-modelcompare-screenshots
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.