Review code changes in Swashbuckle.AspNetCore for correctness, OpenAPI fidelity, compatibility, performance, and consistency with project conventions. Use when reviewing PRs or code changes.
Review pull requests to code-graph-rag, a multi-language code graph parser. Focuses on graph-edge correctness in language parsers, cross-language consistency, and test fixtures that actually exercise the fix.
Review SynapseML Python and Scala code changes. Use before finalizing PR reviews or implementation changes to check security, compatibility, style, generated code, and targeted tests.
Review code changes in dotnet/winforms for concrete problems. Always use this skill when GitHub Copilot code review is requested on a pull request, or when a user asks to review, inspect, audit, or check a PR, branch, commit range, staged changes, uncommitted changes, or local changes in this repository. Supports hosted GitHub.com reviews that post findings directly and interactive reviews of local or remote changes. Focus on correctness, compatibility, native resource and handle lifetime, designer serialization, accessibility, DPI/rendering, performance, security, and regression coverage; omit praise, style-only nits, and speculative concerns.
Use when reviewing Basic Machines code for house style, architecture risk, pre-merge hardening, or whether a change fits basic-memory/basic-memory-cloud conventions.
Pull Request Review Skill
The review checklist for MySQL2 pull requests. Read it before reviewing a pull request, a diff, or a branch.
Never approve a PR that violates
Generic checklist for reviewing DevTools CLs (your own before upload, or someone else's on Gerrit). Covers test correctness (tautological/vacuous tests, cleanup, leaks), code clarity, CL hygiene, and points to the specialized skills to consult for imports, UI, testing, strings, models, and verification. Use when asked to review a CL, a diff, a patch, or to self-review before `git cl upload`.
LLM-focused code review process for this repo: what to check, how to ground feedback in invariants/tests, and how to verify changes efficiently (including test-report.json).
Evidence-first review of Pimcore pull requests — judge against a fixed review contract, hold fixes to the Pimcore quality bar, and enforce the house PHP coding guidelines. Applies to all PHP changes in this repository.
Review code changes in opentelemetry-dotnet for correctness, conventions, and consistency with AGENTS.md and REVIEW.md. Use when reviewing PRs or code changes.
Perform code reviews. Use when reviewing pull requests, examining code changes, or providing feedback on code quality. Covers security, performance, testing, and design review.
Pull request code review guidance for FluentMigrator (https://github.com/fluentmigrator/fluentmigrator), the .NET database migration framework. Use this whenever reviewing a pull request, diff, or patch in this repository — changes to expressions, generators, quoters, type maps, processors, runner/DI registration, the dotnet-fm/console/MSBuild runners, Roslyn analyzers, tests, docs, ADRs, or build/package configuration. It lists the architectural invariants, recurring bug classes, and compatibility rules (public API package validation, net48/netstandard2.0, NativeAOT/trimming, central package management) that a generic reviewer would not know, so review comments are specific to how FluentMigrator works.
Guides AI agents through systematic, prioritized code reviews in Clypra. Activate when reviewing pull requests, git diffs, architectural proposals, or agent-generated changes. Focuses on correctness, architectural invariants, concurrency bugs, and regression risks over cosmetic styling.
Review code changes in dotnet/sdk for problems — either a GitHub pull request or local changes in your branch before a PR exists. Use when asked to review a PR, review local or uncommitted changes, do a code review, check a PR or branch for issues, or review pull request changes. Focuses only on identifying problems — not style nits or praise.
Review IronRDP pull requests and diffs using focused protocol, compression, prose, and skeptical passes. Use whenever Copilot code review is requested or a proposed change needs review.
Review seekdb pull requests and diffs for high-signal correctness, resource-lifetime, concurrency, current-version state-consistency, credential-exposure, workflow-security, performance, and test-evidence defects. Use when reviewing changes to seekdb C++, Rust, build, CI, or test code; report only actionable Blocker or Major findings and exclude persistence-format and upgrade-compatibility analysis.
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 issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
Review changed code for naming, stale references, unnecessary complexity, and comment quality. Use after completing implementation work, before committing, or when the user asks to review or audit code.
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 or AGENTS.md?
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.
What is a skill?
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.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.