Claude skills and agent skills

JuliusBrusseeSkill

caveman-review

JuliusBrussee/caveman/skills/caveman-review/SKILL.md

Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".

gluestackReads credentialsSkill

review-pr

gluestack/gluestack-ui/.claude/skills/review-pr/SKILL.md

Pre-submission PR checklist for gluestack-ui contributions

DefectDojoSkill

review-pr

DefectDojo/django-DefectDojo/.claude/skills/review-pr/SKILL.md

Adversarial review of a DefectDojo/django-DefectDojo pull request (Django app): this repo's CI gates, a hands-on run, at least five recorded attempts to break the change drawn from this repo's past breaks, and one verdict. Use when asked to review, adversarially review, or check a PR in this repo before approving or merging, including Dependabot/Renovate bumps.

pytorchSkill

pr-review

pytorch/executorch/.claude/skills/pr-review/SKILL.md

Review ExecuTorch pull requests for issues CI cannot check. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".

DevolutionsSkill

contract-review

Devolutions/IronRDP/.agents/skills/contract-review/SKILL.md

Review a normative CONTRACT*.md for overreach, unspecified failure paths, duplicated lists, examples standing in for rules, one-implementation bias, and untestable wording; returns findings with proposed rewordings, never edits. Use when asked to review, critique, tighten, or prepare a rewrite of a contract or protocol specification.

DockerSkill

review-pr

docker/docs/.agents/skills/review-pr/SKILL.md

Review one or more incoming Docker documentation pull requests as a maintainer. Independently validate technical claims, assess editorial fit and information architecture, choose a verdict, and draft exact inline or PR-wide feedback behind a confirmation gate. Use for requests such as "review PR 123", "is this PR correct?", "does this information belong here?", "validate this PR", or "help review backlog PRs". Do not use to maintain or fix a PR you own; use maintain-pr for that.

opendataloader-projectSkill

odl-review

opendataloader-project/opendataloader-pdf/.agents/skills/odl-review/SKILL.md

Decide whether an opendataloader-pdf pull request is safe to merge, by its results, inside clear bounds: the change does nothing harmful or hidden; it fixes its target (what the issue or the pull request asks), shown with the code, tests, and runs; and nothing that works on main breaks. If these hold, approve; do not ask for more. Code enforces what must not vary (the trust boundary of the trees, the scan, the earlier decisions, the test-suite comparison, and the verdict itself), you judge the target, the risks, and the checks, and the user approves what cannot be undone. You doubt your plan, the change, and the evidence once. Other people's code runs only in an isolated environment. Use it when the user asks "review #123", "can I merge #123", "is this PR safe", or wants a merge verdict. Also use it to triage all open pull requests ("which PRs should I look at first"). Do not use it to fix an issue. The user approves twice: the plan at the start, and the answers and posts at the end.

No other project uses it yet

ben-manesSkill

review-change

ben-manes/caffeine/.claude/skills/review-change/SKILL.md

Multi-layer adversarial code review of a diff or branch using parallel specialized reviewers with triage

Often used withplan-change·implement-change

facebookincubatorSkill

pr-review

facebookincubator/velox/.claude/skills/pr-review/SKILL.md

Review Velox pull requests for code quality, memory safety, performance, and correctness. Use when reviewing PRs, when asked to review code changes, or when the user mentions "/pr-review".

ardanlabsSkill

review-pr

ardanlabs/service/.agents/skills/review-pr/SKILL.md

Service Diffguard: read-only PR review lenses for correctness, error visibility, comment truthfulness, test coverage, type/contract boundaries, and simplification across every language in this repo (Go, Vue/JS/SCSS, Rego, protobuf, SQL, Helm/YAML, shell). Use for PR review, pre-commit review, unstaged-diff review, or a targeted review of one of those aspects.

marin-communitySkill

review-pr

marin-community/marin/.agents/skills/review-pr/SKILL.md

Independently review an identified Marin pull request for correctness, design fit, and consequences outside the diff. Supports correctness comments and holistic overviews.

pipeshub-aiSkill

pr-review

pipeshub-ai/pipeshub-ai/.claude/skills/pr-review/SKILL.md

Review a PipesHub pull request or diff for correctness, scalability, null safety, reuse, design and tests. Use when asked to review a PR, a branch, a commit or the current diff, and when CI runs the automated review.

kube-hetznerSkill

review-pr

kube-hetzner/terraform-hcloud-kube-hetzner/.claude/skills/review-pr/SKILL.md

Use when reviewing a pull request - security-focused review following repo agent guidance for breaking changes, malicious patterns, and backward compatibility

PennyLaneAISkill

pl-review

PennyLaneAI/pennylane/.agents/skills/pl-review/SKILL.md

Review a PR or local change in PennyLane, Catalyst, Lightning, or pennylane-ecosystem. Assess overall quality with a fast path for bounded fixes to prose, tests, documentation, or CI, and focused deeper review when the changed behavior or risk requires it.

No other project uses it yet

shopwareDeletes or force-pushesSkill

sw-review

shopware/shopware/.agents/skills/sw-review/SKILL.md

Review a Shopware 6 GitHub pull request or local diff, as a general review, a focused security, architecture, code-style, UX or maintainer review, or automated reviewer feedback. Picks topic guides (BC, platform scope, cache lifetime, queue) from the changed code. Not for writing PR text, CI failures, or fixes.

GoogleSkill

adk-review

google/adk-python/.agents/skills/adk-review/SKILL.md

Reviews the uncommitted changes in an adk-python working tree and reports correctness, design, public-API stability, test, sample and documentation gaps as a prioritized findings report, fixing them only when asked. Use when the user asks to review local changes, wants a self-review before opening a pull request, asks whether a change breaks the public API or needs tests, samples or docs, or asks what is wrong with the current diff. Required for changes to public APIs, core architecture (Runner, Workflow, BaseNode), new features and major refactors. Don't use for a single style nit (use adk-style), for diagnosing a failing test or a misbehaving agent at runtime (use adk-debug), or for wording a commit message or PR description (use adk-git).

CrowdDotDevSkill

review-pr

CrowdDotDev/crowd.dev/.claude/skills/review-pr/SKILL.md

Review a pull request against CDP architecture standards — fetches PR diff, verifies previous comments are addressed, validates PR metadata (title, branch, issue reference, size), runs a code-standards enforcer against every file in `.claude/rules/` and `.claude/hooks/guard-protected-files.sh`, and drafts inline review comments with suggested fixes. NEVER auto-posts comments or submits reviews — always presents a draft in the terminal for user approval before any comment lands on the PR. Use when reviewing PRs, checking PR quality, validating code changes, or when the user says "review", "check this PR", or "audit code".

pgmpySkill

review-pr

pgmpy/pgmpy/.agents/skills/review-pr/SKILL.md

Use when reviewing a pgmpy pull request, branch or diff, or when asked to check changes before a human commits them.

ClickHouseSkill

review-pr

ClickHouse/clickhouse-go/.claude/skills/review-pr/SKILL.md

Review a numbered GitHub pull request for correctness, API safety, Go idioms, and protocol coverage, then post inline comments plus one updating summary. Use only when the user asks to review an open PR by number. For a local or pre-PR diff, do not use this skill — apply review-core.md in this directory instead.

dotnetSkill

reviewing-msbuild-code

dotnet/msbuild/.github/skills/reviewing-msbuild-code/SKILL.md

Reviews MSBuild code changes using a 24-dimension methodology. Activates for code review, PR review, pull request analysis, design review, architecture review, code quality assessment, or style check of MSBuild code. Covers backwards compatibility, ChangeWave discipline, performance, allocation awareness, test coverage, error message quality, logging, string comparison, API surface, target authoring, cross-platform correctness, code simplification, concurrency, naming, SDK integration, evaluation model integrity, correctness, dependency management, security, and build infrastructure.