code-review
bennycode/trading-signals/.github/skills/code-review/SKILL.md
Repository coding standards for reviewing pull requests. Apply when reviewing TypeScript code.
Often used withadd-new-model
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.
bennycode/trading-signals/.github/skills/code-review/SKILL.md
Repository coding standards for reviewing pull requests. Apply when reviewing TypeScript code.
Often used withadd-new-model
iovisor/ubpf/.github/skills/code-review/SKILL.md
Perform adversarial pull request review for uBPF in the format GitHub Copilot code review can publish. Use this for normal Copilot pull request reviews, especially for C and C++ changes.
Often used withadd-new-model
sirkirby/unifi-mcp/.github/skills/code-review/SKILL.md
Review UniFi MCP pull requests for architecture, controller-contract, cross-surface, security, test, release, and live-validation defects while preserving human merge authority.
Often used withadd-new-model
cpvalente/ontime/.github/skills/code-review/SKILL.md
Review Ontime changes for concrete correctness, architecture, testing, routing, security, and maintenance issues. For GitHub Copilot review.
Often used withadd-new-model
PrismML-Eng/llama.cpp/skills/code-review/SKILL.md
Review llama.cpp changes against project conventions and common reviewer pitfalls before a PR. Use when the user wants to review a diff, branch, or PR.
Often used withadd-new-model
polyipseity/obsidian-terminal/.agents/skills/code-review/SKILL.md
Use when reviewing PRs, code changes, or conducting code audits in obsidian-terminal. Covers correctness, type safety, architecture fit, test coverage, localization, and completeness.
Often used withadd-new-model
pnp/powershell/.agents/skills/code-review/SKILL.md
Review changes to PnP PowerShell for the failure modes this repository actually ships - silently ignored input, unpaged Graph collections, the wrong base class, permission attributes that do not match the API called, culture and cross-platform bugs, and missing documentation or changelog updates. Use when reviewing a diff, a PR, or uncommitted changes.
Often used withadd-new-model
pnp/powershell/.claude/skills/code-review/SKILL.md
Reviews changes to PnP PowerShell, a .NET 8 module of 800+ cmdlets for Microsoft 365. Knows the cmdlet base classes, how errors reach the user, unpaged Graph collections, the documentation and changelog conventions, and the failure modes this repository actually ships. Use when reviewing a diff, a PR, or uncommitted changes.
Often used withadd-new-model
spiritbuun/buun-llama-cpp/skills/code-review/SKILL.md
Review llama.cpp changes against project conventions and common reviewer pitfalls before a PR. Use when the user wants to review a diff, branch, or PR.
Cooling+1 new adopter in 4 weeks
194 projects use a version of this
Often used withadd-new-model
llama-farm/llamafarm/.claude/skills/code-review/SKILL.md
Comprehensive code review for diffs. Analyzes changed code for security vulnerabilities, anti-patterns, and quality issues. Auto-detects domain (frontend/backend) from file paths.
Often used withadd-new-model
NuGet/NuGet.Client/.github/skills/code-review/SKILL.md
Review pull requests for compliance with the NuGet.Client coding guidelines. Use when reviewing code changes in this repository.
Often used withadd-new-model
microsoft/beachball/.github/skills/code-review/SKILL.md
## Validating of change file (`change/*.json`) change type To determine correctness of a package
Often used withadd-new-model
i-am-manware/Manware-s-AI-Learning-Toolkit/.github/skills/code-review/SKILL.md
Review learner code for risk while teaching the reasoning behind findings.
Often used withadd-new-model
alinaqi/maggy/skills/code-review/SKILL.md
Mandatory code reviews via /code-review before commits and deploys
Often used withadd-new-model
AUTO-MAS-Project/AUTO-MAS/.agents/skills/code-review/SKILL.md
从固定点(commit、branch、tag 或 merge-base)开始,沿两条轴线审查变更——规范(代码是否遵循仓库文档化的编码规范?)和规格(代码是否与原始 issue/PRD 的要求一致?)。两条审查线在并行子 agent 中运行,并以并排方式报告结果。当用户想审查一个分支、PR、进行中的变更,或要求"从 X 开始审查"时使用。
Often used withadd-new-model
llnl/sundials/.agents/skills/code-review/SKILL.md
Review SUNDIALS pull requests using the repository’s correctness, numerical, API, documentation, testing, portability, and maintainability review patterns. Use for GitHub PR reviews or when asked to review changed SUNDIALS source, bindings, build files, examples, or documentation.
Often used withadd-new-model
baidu-baige/LoongForge/skills/code-review/SKILL.md
General-purpose code review for pull requests and local diffs. Produces a structured verdict with file:line citations, severity-tagged findings, and a concise verdict. Use as a GitHub Action bot prompt or before commit/PR submission. Triggers on 'review PR', 'review diff', 'code review', 'check PR', 'review changes', 'review my changes'.
Often used withadd-new-model
bazel-contrib/rules_python/.agents/skills/review-code/SKILL.md
High-level code review audit of local changes when preparing to
open-telemetry/opentelemetry-dotnet-contrib/.github/skills/code-review/SKILL.md
Review code changes in opentelemetry-dotnet-contrib for correctness, convention compliance, and consistency with project conventions. Use when reviewing PRs or code changes.
Often used withadd-new-model
evanca/flutter-ai-rules/skills/code-review/SKILL.md
Use when asked to review a PR, MR, branch, or diff, audit changed files, or check code quality.
Often used withadd-new-model
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.