sdlc-review
NousResearch/hermes-agent/skills/devops/sdlc-review/SKILL.md
Review Kanban handoffs and route verified outcomes.
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.
NousResearch/hermes-agent/skills/devops/sdlc-review/SKILL.md
Review Kanban handoffs and route verified outcomes.
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.
RLinf/RLinf/.agents/skills/review-pr/SKILL.md
Reviews an RLinf pull request for correctness, design, and code reuse against RLinf's design patterns, runs the check of every area the PR touches (code, docs, install) through those skills and the reproduction when the host can, reports the findings in a fixed format, and, when the user asks, 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.
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.
Steady4 mentions in 2 weeks
1 project uses a version of this
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.
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
Steady2 mentions in 2 weeks
195 projects use a version of this
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".
gluestack/gluestack-ui/.claude/skills/review-pr/SKILL.md
Pre-submission PR checklist for gluestack-ui contributions
185 projects use a version of this
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.
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".
195 projects use a version of this
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.
Steady17 mentions in 2 weeks
37 projects use a version of this
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.
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-changeimplement-change
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".
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.
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.
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.
Steady3 mentions in 2 weeks
185 projects use a version of this
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
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.
Steady2 mentions in 2 weeks
No other project uses it yet
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.
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.