Review & quality
19,178 rows, by stacks then stars
1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid
KhaledSaeed18/dotclaude/.claude-plugin/plugins/engineering/skills/grill-with-docs Skill
4★ repoStress-test a plan against the project's existing domain model by challenging terminology, surfacing contradictions with code, and updating CONTEXT.md and ADRs inline as decisions crystallise. Use when a plan or design needs to be checked against the project's documented domain model before implementation.
KhaledSaeed18/dotclaude/.claude-plugin/plugins/engineering/skills/verify-completion Skill
4★ repoGate every "it works / it's fixed / tests pass / done" claim behind fresh evidence — run the actual verifying command, read its output, and only then state the result. Use before committing, opening a PR, marking a task complete, handing off to or trusting a subagent, or otherwise asserting that work succeeded.
KhaledSaeed18/dotclaude/.claude-plugin/plugins/git/skills/changelog Skill
4★ repoGenerate a changelog or release notes from Git history, grouped by change type, written in user-facing language, with issue/PR links and breaking changes called out. Conventional-Commits aware and Keep a Changelog formatted; respects any existing CHANGELOG or tooling. Use when preparing release notes or updating CHANGELOG.md.
KhaledSaeed18/dotclaude/.claude-plugin/plugins/git/skills/finish-branch Skill
4★ repoWrap up a completed development branch by verifying tests pass, detecting the workspace state, then presenting clear merge / PR / keep / discard options and executing the chosen one safely — including correct worktree and branch cleanup. Use when implementation is done, tests should be green, and you need to integrate or put away the work.
KhaledSaeed18/dotclaude/.claude-plugin/plugins/git/skills/git-commit Skill
4★ repoCommit work the right way by gathering full repo state, respecting the project's commitlint/pre-commit/branch rules, staging only understood files, and writing a conventional-commit message whose body explains why. Use when committing, branching, or pushing changes.
KhaledSaeed18/dotclaude/.claude-plugin/plugins/git/skills/git-undo Skill
4★ repoRecover safely from Git mistakes such as discard, unstage, amend, reset, revert, restore lost commits via reflog, recover deleted branches, and fix bad rebases. Chooses the least-destructive fix and protects against data loss. Use when something in Git went wrong and needs undoing.
KhaledSaeed18/dotclaude/.claude-plugin/plugins/git/skills/git-worktrees Skill
4★ repoSet up an isolated workspace for feature work so the current branch and working tree stay untouched — detecting existing isolation first, preferring the platform's native worktree tooling, and falling back to git worktrees only when nothing native exists. Use before starting feature work that needs isolation, or before executing an implementation plan.
KhaledSaeed18/dotclaude/.claude-plugin/plugins/git/skills/merge-conflict Skill
4★ repoResolve Git merge, rebase, cherry-pick, revert, and stash conflicts safely by understanding both sides and the operation in progress before integrating, then verifying the result builds and passes tests. Use when a merge/rebase/cherry-pick stops with conflicts or "needs merge".
KhaledSaeed18/dotclaude/.claude-plugin/plugins/git/skills/pr-description Skill
4★ repoGenerate a clear, reviewer-friendly pull-request description from a diff, covering what changed, why, risk, and how it was tested. Use when opening a pull request or writing/improving a PR body.
KhaledSaeed18/dotclaude/.claude-plugin/plugins/productivity/skills/grill-me Skill
4★ repoRelentlessly stress-test a plan, design, architecture, idea, or strategy until all critical decisions are resolved. Use when a plan, design, or decision needs adversarial stress-testing before committing to it.
KhaledSaeed18/dotclaude/.claude-plugin/plugins/productivity/skills/standup-summary Skill
4★ repoGenerate a standup or weekly-review update from actual work evidence - commits, branches, PRs, and issues across one or more repositories - grouped into done / in progress / blocked / next, written in plain human sentences rather than commit-message-speak. Use when preparing a daily standup, a weekly review, a sprint update, or answering "what did I work on this week".
KhaledSaeed18/dotclaude/.claude-plugin/plugins/testing/skills/webapp-testing Skill
4★ repoVerify a web application works correctly in a real browser using Playwright. Covers page navigation, form submission, user interactions, console error detection, screenshot capture, and responsive layout checking. Use when you need to confirm a UI feature actually works end-to-end, catch regressions after a change, verify a form flow completes, or check that the page is free of console errors. Requires Node.js; installs Playwright if not already present.
KhaledSaeed18/dotclaude/skills/engineering/adversarial-reviewer Skill
4★ repoReview code through three hostile personas - the Saboteur, the New Hire, and the Security Auditor - each required to find at least one issue. Use when a standard review feels too comfortable, when code is going into a critical path, when a previous review missed bugs that later surfaced, or when you want coverage across correctness, clarity, and security in a single pass.
KhaledSaeed18/dotclaude/skills/engineering/api-design-review Skill
4★ repoReview an API contract (REST or GraphQL) before or while it is implemented, checking resource naming, HTTP semantics, status codes, error shape, pagination, versioning, idempotency, and backward compatibility, and producing concrete revisions rather than abstract advice. Use when designing new endpoints, changing an existing API's surface, or reviewing a PR that adds or modifies API routes.
KhaledSaeed18/dotclaude/skills/engineering/code-review-response Skill
4★ repoProcess code-review feedback with technical rigour — understand each point, check it against the actual codebase, and respond with reasoning or implementation rather than reflexive agreement. Use when you receive review comments (from a human, the code-reviewer agent, or any reviewer) and are about to act on them, especially if any feedback seems unclear or wrong.
KhaledSaeed18/dotclaude/skills/engineering/grill-with-docs Skill
4★ repoStress-test a plan against the project's existing domain model by challenging terminology, surfacing contradictions with code, and updating CONTEXT.md and ADRs inline as decisions crystallise. Use when a plan or design needs to be checked against the project's documented domain model before implementation.
KhaledSaeed18/dotclaude/skills/engineering/verify-completion Skill
4★ repoGate every "it works / it's fixed / tests pass / done" claim behind fresh evidence — run the actual verifying command, read its output, and only then state the result. Use before committing, opening a PR, marking a task complete, handing off to or trusting a subagent, or otherwise asserting that work succeeded.
KhaledSaeed18/dotclaude/skills/productivity/grill-me Skill
4★ repoRelentlessly stress-test a plan, design, architecture, idea, or strategy until all critical decisions are resolved. Use when a plan, design, or decision needs adversarial stress-testing before committing to it.
KhaledSaeed18/dotclaude/skills/productivity/standup-summary Skill
4★ repoGenerate a standup or weekly-review update from actual work evidence - commits, branches, PRs, and issues across one or more repositories - grouped into done / in progress / blocked / next, written in plain human sentences rather than commit-message-speak. Use when preparing a daily standup, a weekly review, a sprint update, or answering "what did I work on this week".
KhaledSaeed18/dotclaude/skills/testing/webapp-testing Skill
4★ repoVerify a web application works correctly in a real browser using Playwright. Covers page navigation, form submission, user interactions, console error detection, screenshot capture, and responsive layout checking. Use when you need to confirm a UI feature actually works end-to-end, catch regressions after a change, verify a form flow completes, or check that the page is free of console errors. Requires Node.js; installs Playwright if not already present.
KhaledSaeed18/dotclaude/skills/version-control/changelog Skill
4★ repoGenerate a changelog or release notes from Git history, grouped by change type, written in user-facing language, with issue/PR links and breaking changes called out. Conventional-Commits aware and Keep a Changelog formatted; respects any existing CHANGELOG or tooling. Use when preparing release notes or updating CHANGELOG.md.
KhaledSaeed18/dotclaude/skills/version-control/finish-branch Skill
4★ repoWrap up a completed development branch by verifying tests pass, detecting the workspace state, then presenting clear merge / PR / keep / discard options and executing the chosen one safely — including correct worktree and branch cleanup. Use when implementation is done, tests should be green, and you need to integrate or put away the work.
KhaledSaeed18/dotclaude/skills/version-control/git-commit Skill
4★ repoCommit work the right way by gathering full repo state, respecting the project's commitlint/pre-commit/branch rules, staging only understood files, and writing a conventional-commit message whose body explains why. Use when committing, branching, or pushing changes.
KhaledSaeed18/dotclaude/skills/version-control/git-undo Skill
4★ repoRecover safely from Git mistakes such as discard, unstage, amend, reset, revert, restore lost commits via reflog, recover deleted branches, and fix bad rebases. Chooses the least-destructive fix and protects against data loss. Use when something in Git went wrong and needs undoing.
KhaledSaeed18/dotclaude/skills/version-control/git-worktrees Skill
4★ repoSet up an isolated workspace for feature work so the current branch and working tree stay untouched — detecting existing isolation first, preferring the platform's native worktree tooling, and falling back to git worktrees only when nothing native exists. Use before starting feature work that needs isolation, or before executing an implementation plan.
KhaledSaeed18/dotclaude/skills/version-control/merge-conflict Skill
4★ repoResolve Git merge, rebase, cherry-pick, revert, and stash conflicts safely by understanding both sides and the operation in progress before integrating, then verifying the result builds and passes tests. Use when a merge/rebase/cherry-pick stops with conflicts or "needs merge".
KhaledSaeed18/dotclaude/skills/version-control/pr-description Skill
4★ repoGenerate a clear, reviewer-friendly pull-request description from a diff, covering what changed, why, risk, and how it was tested. Use when opening a pull request or writing/improving a PR body.
jkm-4314/claude-code-skills/peer-review Skill
4★ repoUse when Claude completes a spec or code implementation and needs independent review, or when the user invokes /peer-review. Triggers automatically after spec writing or code completion for production projects. Only bypass when user explicitly opts out.
Finishing a development branch
izyanrajwani/agent-skills-library/skills/finishing-a-development-branch Skill
no license4★ repoGit branch completion workflow. Use when implementation is complete, tests pass, and a feature branch needs to be integrated via merge, pull request, or cleanup.
The same file is in 8 other repositories
izyanrajwani/agent-skills-library/skills/receiving-code-review Skill
no license4★ repoAssesses and responds to incoming code review feedback on PRs (reviewer comments, requested changes), especially when suggestions are unclear, technically questionable, or scope-expanding. Use before implementing review suggestions to align on intent and keep changes minimal.
The same file is in 8 other repositories
izyanrajwani/agent-skills-library/skills/requesting-code-review Skill
no license4★ repoUse when you need to request a code review for a PR/MR and want a consistent review brief (context, scope, risk areas, test instructions, acceptance criteria) before merge.
The same file is in 8 other repositories
izyanrajwani/agent-skills-library/skills/using-git-worktrees Skill
no license4★ repoGit worktree–based workspace isolation for parallel or non-disruptive development. Use when work must occur without modifying or interfering with the current working tree.
The same file is in 8 other repositories
Verification before completion
izyanrajwani/agent-skills-library/skills/verification-before-completion Skill
no license4★ repoVerification discipline for completion claims. Use when about to assert success, claim a fix is complete, report tests passing, or before commits and PRs. Enforces evidence-first workflow.
The same file is in 8 other repositories
openEHR/ai-plugins/plugins/openehr-specs/skills/review Skill
4★ repoReview an openEHR specification document for quality, completeness, and convention compliance in `specifications-XX` repos. This skill should be used when the user asks to review, lint, or quality-check an openEHR spec, validate its conventions, or run a pre-release review. Not for archetype/template review (openehr-assistant plugin), the governance process (use governance), or non-openEHR documents.
akhilkannur/marketing-agent-blueprints/skills/api-endpoint-validator Skill
no license4★ repoEnsure the demo never breaks. This agent reads a list of API endpoints from a CSV, tests them for speed and response structure, and generates a 'Green/Red' status report for the team.
akhilkannur/marketing-agent-blueprints/skills/audience-overlap-checker Skill
no license4★ repoAre your showing the same ad to the same person in two different ad sets? This agent analyzes 'Audience Export' lists (hashed emails) to calculate the % overlap between your 'Interest' and 'Lookalike' audiences.
akhilkannur/marketing-agent-blueprints/skills/backlink-toxicity-checker Skill
no license4★ repoNot all links are good. This agent audits a list of backlinks for 'Risk Signals' (High Spam Score, Irrelevant TLD, Foreign Language anchor text) and creates a disavow file for Google.
akhilkannur/marketing-agent-blueprints/skills/bad-review-poacher Skill
no license4★ repoUnhappy customers are the easiest leads to close. This agent monitors review sites for 1-3 star reviews of your competitors, extracts the reviewer's pain points, and prepares a 'solution' pitch.
Lion-1209/Lion-Skills/skills/commit-message Skill
4★ repoGit 改动需编写规范提交信息时。
Lion-1209/Lion-Skills/skills/verify-and-fix Skill
4★ repo交付前需验证完成,或修 bug 需修病因不修症状时。
tuoxie2046/claude-code-research-skills/plugins/academic-research-skills/academic-pipeline Skill
no license4★ repoOrchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow.
tuoxie2046/claude-code-research-skills/plugins/academic-research-skills/deep-research Skill
no license4★ repoUniversal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題.
tuoxie2046/claude-code-research-skills/plugins/nature-skills/plugins/nature-skills/skills/nature-response Skill
no license4★ repoDraft, audit, or revise point-by-point reviewer response letters for Nature-family manuscript revisions. Use when the user provides reviewer comments, editor decision letters, revision notes, response drafts, or asks how to respond to major/minor revision requests, rebuttal letters, response to reviewers, peer-review reports, 审稿意见回复, 逐点回复, 修回信, 大修回复, 小修回复, or 如何回复 reviewer.
tuoxie2046/claude-code-research-skills/plugins/nature-skills/plugins/nature-skills/skills/nature-reviewer Skill
no license4★ repoSimulate a Nature-style reviewer assessment from the referee perspective rather than an author rebuttal. Use when the user wants a pre-submission review, reviewer report, peer-review style critique, novelty/significance/technical soundness assessment, reviewer-style manuscript evaluation, 审稿人视角评估, 预审稿意见, or Nature reviewer report. Return 3 reviewer reports plus a cross-review synthesis, grounded only in the local Nature reviewer source basis.
tuoxie2046/claude-code-research-skills/plugins/nature-skills/skills/nature-response Skill
no license4★ repoDraft, audit, or revise point-by-point reviewer response letters for Nature-family manuscript revisions. Use when the user provides reviewer comments, editor decision letters, revision notes, response drafts, or asks how to respond to major/minor revision requests, rebuttal letters, response to reviewers, peer-review reports, 审稿意见回复, 逐点回复, 修回信, 大修回复, 小修回复, or 如何回复 reviewer. Also trigger on general peer-review response needs during academic writing/revision even without the word "Nature", such as replying to reviewers for any journal, writing a rebuttal/response letter, handling revision comments, and Chinese phrasings like 回复审稿人、审稿回复、返修、 修改稿回复、写rebuttal、回应审稿意见、应对审稿.
The same file is in 2 other repositories
tuoxie2046/claude-code-research-skills/plugins/nature-skills/skills/nature-reviewer Skill
no license4★ repoSimulate a Nature-style reviewer assessment from the referee perspective rather than an author rebuttal. Use when the user wants a pre-submission review, reviewer report, peer-review style critique, novelty/significance/technical soundness assessment, reviewer-style manuscript evaluation, 审稿人视角评估, 预审稿意见, or Nature reviewer report. Return 3 reviewer reports plus a cross-review synthesis, grounded only in the local Nature reviewer source basis. Also trigger on general pre-submission review requests during academic writing even without the word "Nature", such as getting a mock peer review for any journal, critiquing a draft as a reviewer would, assessing novelty/rigor before submission, and Chinese phrasings like 审稿人视角、模拟审稿、预审、帮我审一下论文、投稿前自审、审稿意见模拟、找论文问题.
The same file is in 2 other repositories
tuoxie2046/claude-code-research-skills/skills/research-paper-writing Skill
no license4★ repoImprove academic paper writing quality for ML/CV/NLP-style papers with clear section structure, paragraph flow, and reviewer-facing presentation. Use when drafting or revising Abstract, Introduction, Related Work, Method, Experiments, or Conclusion; polishing figures/tables; checking claim-support alignment; or performing self-review before submission.
The same file is in 20 other repositories
Epistates/sparX/.claude/skills/review Skill
4★ repoAnalyze post-publish X performance and extract lessons. Use when the user wants to review how their posts performed, analyze engagement data, understand what worked, or improve future content based on past results.
Epistates/sparX/.claude/skills/test Skill
4★ repoVerify sparX setup is working correctly. Use when the user wants to check their installation, test skills, or troubleshoot setup issues.
Imran-ml/claude-skills/.claude/skills/review-pr Skill
no license4★ repoUse this skill when the user wants to review a pull request, check a PR for issues, or get feedback on a GitHub PR. Triggered by "review PR", "check PR", "review pull request", or "/review-pr <number>".
toolbox-playground/super-claudio/skills/software-development Skill
4★ repoSoftware development skill. Use when the user wants to build, code, automate, or deploy anything technical. Covers backend APIs, databases, workflow automation, scripts, free public APIs, and hosting/deployment. Trigger on backend: "build an API", "REST API", "database schema", "Supabase", "Firebase", "PostgreSQL", "MongoDB", "FastAPI", "Express", "Fastify", "GraphQL", "Node.js server", "Python API", "Prisma", "ORM", "authentication backend", "serverless functions". Trigger on automation: "automate this", "connect these apps", "n8n", "Make.com", "Zapier", "when X happens do Y", "no-code automation", "schedule a script", "webhook", "automate posting", "IFTTT", "auto-post to Instagram", "batch processing", "automate email". Trigger on free APIs: "free API for X", "public API", "build a weather app", "NASA API", "real-time data", "open data", "free data source", "API without credit card", "government API". Trigger on deployment: "deploy my app", "Docker", "Railway", "GitHub Actions", "CI/CD", "hosting", "go live", "containerize", "VPS setup". Trigger on git/GitHub: "create a PR", "open a pull request", "GitHub CLI", "gh pr", "gh issue", "connect Claude to GitHub", "GitHub MCP", "commit message", "git workflow", "manage issues", "review a PR", "GitHub Actions workflow", "release on GitHub". Do NOT trigger for: frontend/UI design (use design skill), media generation (use media-content-creation).
davccavalcante/supreme-coding-guidelines-skill.ah/skills/supreme-diagramming Skill
no license4★ repoLiving-diagram companion for Product Engineers, Software Architects, LLM Architects, Tech Leads, Technical Writers, DevOps, and AI Researchers who need architecture, flow, ERD, sequence, class, C4, and state diagrams that stay in sync with the repository. Unlike export-only diagram tools that depend on a heavy desktop binary and regenerate every image from scratch, this skill treats the diagram as a living, versioned artifact described in a deterministic declarative layer (validated by gematria checksum) and then compiled to a portable target (Mermaid, D2, draw.io XML, Excalidraw) with no proprietary lock-in. It applies a describe-first pipeline (natural language becomes a declarative diagram spec, the spec is validated deterministically, then compiled to the requested format), inverts the fragile vision-first verification of legacy tools by doing deterministic structural and aesthetic checks first and using model vision only as last-resort reinforcement, keeps the diagram as a file next to the code so it is diffed in pull requests and evolved rather than recreated, remembers prior diagrams to evolve them across sessions, degrades gracefully (Mermaid or D2 text when no renderer is present, never a hard failure), and embeds the seven craft lessons of the best SKILL.md authoring — lean main file with demand-loaded references, an explicit boundary of when not to use (redirect freehand sketches to Excalidraw or tldraw, redirect throwaway inline snippets to plain Mermaid), self-verification before delivery, graceful degradation, environment anticipation across macOS/Linux/Windows and headless servers, surgical repair of known renderer defects documented by cause, honest versioned changelog, and trigger-clear activation. Requires ah-parser. Output mode follows user preference at parser activation; user code, diagram source, and committed artifacts are always preserved verbatim. Deterministic validation over probabilistic vision, living artifact over one-shot export, portable format over proprietary lock-in.
tuliosousapro/SaaS-blueprint/skills/conventional-commits Skill
4★ repoEnforces Conventional Commits format for git commit messages. Use when formatting commits or validating message structures. For git commands, see git-control.
tuliosousapro/SaaS-blueprint/skills/git-control Skill
4★ repoStandardizes git operations, branch management, and disaster recovery. Use when committing, branching, or resolving conflicts. For commit formatting, see conventional-commits.
tuliosousapro/SaaS-blueprint/skills/idea-validator Skill
4★ repoStructured validation framework that scores product ideas. Use when evaluating problem severity, willingness-to-pay, or founder-market fit. For market intelligence, see market-research.
Dragoon0x/product-skills/skills/strategy/market-validation Skill
no license4★ repoTest assumptions before committing resources. Generates lean validation plans, fake door tests, and interview scripts. Use before building anything expensive or when there's no evidence anyone wants what's being built.
cfregly/gpu-perf-tune/plugins/profile-and-optimize/skills/inference-capacity-sizing Skill
4★ repoAgent Skills and an MCP server for GPU performance profiling, benchmarking, optimization, and reporting, with an inference focus.
cfregly/gpu-perf-tune/plugins/profile-and-optimize/skills/inference-known-good-config Skill
4★ repoCapture + enforce per-model KNOWN-GOOD serving configs: the REQUIRED serve flags (boot-blockers / crash-at-high-c / deploy-correctness workarounds) plus the champion + the bug each flag avoids, in one queryable registry (perf-tune-report/configs/known-good-configs.yaml) so a hard-won workaround (e.g. Qwen3-Next's gdn_prefill_backend=triton on vLLM 0.22) is NEVER re-discovered the hard way. These are NOT well-known upstream defaults -- several are field-discovered workarounds where the upstream `auto` path is actively broken on the target hardware. `record` after a champion is found, `check` (fail-closed) before any deploy/ship. Keep the registry private -- never post an entry publicly. Triggers on "known-good config", "required flags for <model>", "did we capture the flag combo", "register the config", "check the deploy config", "config drift", "what flags does <model> need", or any combination of "known-good / required / champion config" with "record / check / register / capture / drift / flags / serve".
nataliacorrea03/claude-code-skills/skills/meta-prompt Skill
4★ repoBuilds ready-to-paste Meta AI (Muse Spark) prompts for reading Instagram, Facebook, and Threads directly. Describe a research goal (find micro-influencers or ambassadors, find videos to react to, monitor brand mentions, scan niche trends, check saturation, mine comments, tear down a competitor, verify handles, study a creator's voice before a pitch) and this skill asks a few clarifying questions, fills the variables (niche, follower range, brand, time window, etc.), and outputs a copy-paste prompt for the meta.ai app. It also hands out the Hook Machine, a full multi-turn workflow that analyzes a creator's top reels, extracts why the winners win, builds a grading rubric, then generates, grades, and rewrites hooks. It never calls Meta AI itself and never invents capabilities. Trigger on "/meta-prompt", "build a meta ai prompt", "meta prompt for <goal>", "find microinfluencers on instagram", "find videos to react to", "monitor mentions of <brand>", "what's trending on instagram for <niche>", "hook machine", "analyze a creator's hooks", "build a hook rubric", or any request to research Instagram creators, content, or brands that would be run inside Meta AI.
SteveVitali/agent-skills/skills/review-pr Skill
4★ repoReview someone else's GitHub PR as a Staff Engineer and post a high-precision review — mechanical grounding (CI, local verification), focused design + security passes, calibrated severity labels, inline comments with suggestion blocks. Use when asked to review a PR, give feedback on a PR, or act as a code reviewer.