Critically triage pull request review comments against PR requirements and codebase reality, implement only valid fixes, and reply only when declining a suggestion. Use when the user asks to address PR comments, review feedback, CodeRabbit/Bugbot threads, or `/address-pr-review`.
7 projects use a version of this
40k4d agoReviewMountCreate a free account to mount
Review a GitHub pull request and leave inline comments in a natural human reviewing voice, indistinguishable from comments typed by hand on the GitHub web UI. Deliberately bounded to defects a reader can settle by looking at the anchored line, rather than a deep audit, so every comment is cheap for the author to check. Scales to 2-20 comments by PR size, parallelises analysis across sub-agents, drafts for approval, then posts individually with human pacing. Use when the user says "review this PR", "review PR 123", pastes a github.com/.../pull/N link, or asks for comments on a pull request. Don't use for reviewing local uncommitted changes or a diff against a branch (use the `review` skill for that).
Steady5 mentions in 2 weeks
19 projects use a version of this
11k49d agoReviewMountCreate a free account to mount
Review a proposed public API for the dotnet/aspnetcore repo the way the @dotnet/aspnet-api-review team would, and recommend concrete changes to the API shape. USE FOR reviewing an API proposal or api-ready-for-review issue, critiquing a ref-assembly diff, deciding whether a new or changed type/method/overload/property should be added at all, evaluating whether an API change or addition is a good idea, changing/extending an existing API or a shipped default/convention, or checking naming/namespace/nullability/async/sealing/return-type/overload/language-feature choices. Trigger phrases: "review this API", "is this API a good idea", "should we add", "API proposal", "api-ready-for-review". Produces a verdict, a need assessment (commonality + target audience), per-type bullet changes, and a diff against the existing repo API surface. DO NOT USE FOR implementing an approved API, writing analyzers, or general code review unrelated to public API surface.
39k6mo agoReviewMountCreate a free account to mount
Review an identified ASP.NET Core pull request against a complete, frozen, trusted source-and-guidance bundle. Return source-supported findings without publishing.
39k6mo agoReviewMountCreate a free account to mount
Review and fix an existing pnpm pull request, rebase it, commit and push fixes, then follow CI and review to completion. Use when asked to review and fix a PR or launched by the git-wt PR hook.
37k13d agoReviewMountCreate a free account to mount
Reviews GitHub pull requests for the Medusa repository. Checks PR template compliance, contribution guidelines, code conventions, security, performance, and bugs. Emits a structured review decision (labels + review template) for a downstream step to apply. Use when a PR is opened or updated, whether you fetch the PR with scripts or are given its data.
Steady9 mentions in 2 weeks
7 projects use a version of this
37k11mo agoReviewMountCreate a free account to mount
Review guidance for Nightshift changes. Defines risk tiers by what a change touches and the checks each tier needs, with calibration examples from past reviews.
21k5mo agoReviewMountCreate a free account to mount
Guidance for writing and modifying Microsoft.Extensions.* and System.IO.Compression code in dotnet/runtime. Covers DI lifetime management, configuration binding, options validation, logging provider patterns, caching semantics, compression format compliance, and host lifecycle. For full code review, delegates to the @extensions-reviewer agent. Trigger words: Microsoft.Extensions, IServiceCollection, IConfiguration, ILogger, IHost, IMemoryCache, IOptions, ZipArchive, HttpClientFactory, IFileProvider, IChangeToken.
18k2y agoReviewMountCreate a free account to mount
Write and review content for the OpenSEO website (web/), including blog posts, guides, feature pages, FAQs. Makes sure each page delivers real value to its target reader. Use whenever adding or editing user-facing prose in web/content or web/src.
Steady18 mentions in 2 weeks
4 projects use a version of this
28k3mo agoReviewMountCreate a free account to mount
Shared foundation every CDK review-dimension skill applies — the harm-based severity scale (BLOCKING/RECOMMENDED/OPTIONAL), evidence + citation authority order, exact file:line, the concrete-fix rule, the 3-7 comment budget, review tone, the shared what-NOT-to-flag exclusions, the finding-output contract (ruleId + reference fields), and the rules-lookup convention. Apply whenever conducting a CDK PR review, rating a finding's severity, deciding whether something is a finding at all, or turning a finding into a posted comment.
13k19d agoReviewMountCreate a free account to mount
Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.
Correctness and invariants lens for Orleans — invariants and assertions, error handling, failure semantics, idempotence, grain concurrency and reentrancy, activation scheduling, async and cancellation, security boundaries, and observability. Use during code review, and when designing or implementing runtime or provider code.
No other project uses it yet
11k14d agoReviewMountCreate a free account to mount
Review any business decision, plan, or strategy through the minimalist entrepreneur lens. Use when someone wants a gut-check on a business decision, wants to simplify their approach, or needs to decide between options.
Steady2 mentions in 2 weeks
9 projects use a version of this
11k8mo agoReviewMountCreate a free account to mount
Run a literature review using paper search and primary-source synthesis. Use when the user asks for a lit review, paper survey, state of the art, or academic landscape summary on a research topic.
Find the right reviewer for a Firefox/Gecko change so the user does not have to. Use this primarily when committing changes, to fill in the `r=` part of the commit message automatically instead of leaving it blank or guessing. Also use it when the user asks directly who should review a patch or what reviewer group to use.
14k3d agoReviewMountCreate a free account to mount
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.