Claude skills and agent skills

fleetdmSkill

review-pr

fleetdm/fleet/.claude/skills/review-pr/SKILL.md

Review a Fleet pull request for correctness, Go idioms, SQL safety, test coverage, and conventions. Use when asked to "review PR" or "review pull request".

jaredpalmerSkill

thermonuclear-code-review

jaredpalmer/kev/.agents/skills/thermonuclear-code-review/SKILL.md

Extremely strict structural review of a Kev branch or PR (code-judo simplifications, spaghetti growth, files past 1k lines, boundaries, duplication of canonical helpers). Use when asked to review a PR, audit a diff, or run a "thermonuclear" or deep code quality review on this repo.

No other project uses it yet

CodeWithCJSkill

pr-review

CodeWithCJ/SparkyFitness/.agents/skills/pr-review/SKILL.md

Use whenever the user asks to review, vet, or sanity-check a pull request, or to act on the review comments already on one — a GitHub PR URL pasted with little or no instruction, a bare PR number, "review this PR", "is this PR safe", "can I merge this", "check this contribution", "any issues with #1234", "check the bot comments", "fix the CodeRabbit findings", "address the review comments", "update the PR if required". Runs the standing SparkyFitness review: supply-chain, phishing and code-provenance checks first, then architecture alignment with AGENTS.md and agent-docs, then logic, then the state of existing review-bot and reviewer threads. Reports to the terminal only.

CodeWithCJSkill

pr-review

CodeWithCJ/SparkyFitness/.claude/skills/pr-review/SKILL.md

Use whenever the user asks to review, vet, or sanity-check a pull request, or to act on the review comments already on one — a GitHub PR URL pasted with little or no instruction, a bare PR number, "review this PR", "is this PR safe", "can I merge this", "check this contribution", "any issues with #1234", "check the bot comments", "fix the CodeRabbit findings", "address the review comments", "update the PR if required". Runs the standing SparkyFitness review: supply-chain, phishing and code-provenance checks first, then architecture alignment with AGENTS.md and agent-docs, then logic, then the state of existing review-bot and reviewer threads. Reports to the terminal only.

payloadcmsSkill

ui4-review

payloadcms/payload/.agents/skills/ui4-review/SKILL.md

Review UI4 CSS migrations for proper token usage. Checks that CSS variables are used instead of hardcoded values.

MicrosoftSkill

pr-review

microsoft/vscode-docs/.github/skills/pr-review/SKILL.md

Verify the technical accuracy of a vscode-docs pull request against the VS Code source code in microsoft/vscode. Use when reviewing a docs PR for factual correctness: setting names, command IDs, default values, API shapes, keybindings, versioned availability, and described behavior.

baserowSkill

review-pr

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

Review a Baserow pull request, branch, or diff against its actual base the way the maintainers do. Use when asked to review, deeply review, re-review, or triage review comments on a PR, including follow-up rounds on the same PR.

kieranklaassenSkill

ce-doc-review

kieranklaassen/compound-engineering-plugin/skills/ce-doc-review/SKILL.md

Review requirements, plans, or specs with role-specific lenses. Use when the user wants to improve an existing planning document.

dlt-hubSkill

review-pr

dlt-hub/dlt/.claude/skills/review-pr/SKILL.md

Analyze a GitHub pull request including diff, comments, related issues, and local code context

dograh-hqReads credentialsSkill

review-pr

dograh-hq/dograh/.agents/skills/review-pr/SKILL.md

Review a Dograh pull request, branch diff, or pasted patch for repo-specific security and correctness risks that are not obvious from generic FastAPI, Next.js, or Python conventions. Use when the user asks to review a PR, audit a diff, check whether changes are safe to merge, review their own changes, or asks what to look for in a Dograh PR. Focus on tenant isolation, route auth, webhook signing and org derivation, DB layering, worker-sync, migrations, generated SDK usage, and test hazards.

Yeachan-HeoSkill

omc-review

Yeachan-Heo/oh-my-claude-sisyphus/skills/review/SKILL.md

Evaluate finished work for defects, risk, and simplification before it ships

videojsSkill

review-api

videojs/video.js/.agents/skills/review-api/SKILL.md

Review Video.js TypeScript APIs without editing code. Use for inference, state, extensibility, composition, packaging, or architecture audits.

areal-projectSkill

review-pr

areal-project/AReaL/.agents/skills/review-pr/SKILL.md

Read-only pull request review workflow with risk analysis, targeted checklists, and Codex subagent consultation.

pytorchSkill

pr-review

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

Review torchtitan pull requests the way the maintainers do -- question the problem and design first, push for minimal code, explain the change with a concrete example, then check correctness. Use when reviewing a PR or branch, when asked to "review", "review again", "review my review", or to evaluate a maintainer's comments.

NousResearchSkill

sdlc-review

NousResearch/hermes-agent/skills/devops/sdlc-review/SKILL.md

Review Kanban handoffs and route verified outcomes.

dotnetSkill

api-review

dotnet/aspnetcore/.github/skills/api-review/SKILL.md

Author and file a separate ASP.NET Core API review issue from an originating issue and an implementation pull request or commits. USE FOR writing API review issues, preparing api-ready-for-review proposals, filling API proposal templates, creating API review descriptions from issues and code changes, "fill out the API review", "prepare API review", or opening a pull request that changes public API. DO NOT USE FOR reviewing API design decisions, approving APIs, implementing APIs, or general code review.

RLinfSkill

review-pr

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

Reviews an RLinf pull request for correctness, design, code reuse, tests, and docs against RLinf's code and design patterns and the docs style guide, reports the findings in a fixed format, and, after asking, posts them as one GitHub review with a main comment that answers the review questions and inline comments with suggested fixes. Use when the user asks to review a PR, check a PR before merge, or post review comments.

utmappSkill

utm-review

utmapp/UTM/.agents/skills/utm-review/SKILL.md

Review pending UTM changes before they are submitted. Runs a standard correctness/quality code review of the current branch's diff AND audits it against UTM's contribution rules in CONTRIBUTING.md and AGENTS.md — scope discipline, commit/PR format, AI attribution, logging hooks, generated files, UI/design philosophy, and platform compatibility. Use this before opening or updating a UTM pull request, whenever the user asks to review UTM changes, or when the user runs /utm-review. The /utm-submit workflow expects this to have been run on the current changes first.

open-metadataSkill

connector-review

open-metadata/OpenMetadata/skills/connector-review/SKILL.md

Review an OpenMetadata connector against golden standards. Runs multi-agent analysis covering architecture, code quality, type safety, testing, and performance. When a PR number is given, automatically posts the quality summary to the PR description and a detailed review as a PR comment.

zerx-labSkill

pr-review

zerx-lab/FluxDown/.cursor/skills/pr-review/SKILL.md

Review、补完并合并 FluxDown 的 GitHub PR：PR 拉到 .worktrees/pr-<N> 隔离检查， 从功能 / 性能 / 完整性三个角度审查后分级处理——方向错误直接关闭，实现逻辑错误评论退回， 格式化 / 冲突 / 缺少几条测试等小问题直接修好推回 PR 分支再合并，结束必清理 worktree。 关键词：PR, pull request, review, 审查, 代码评审, 合并 PR, merge, 处理 PR, 贡献者, contributor, 补测试, 解决冲突, 推回 PR 分支, maintainer edits