Agent skills

Code Review & Quality skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
2,936 found
1,4891,536 · page 32 / 62
auditing-and-economics-researchUse when targeting 《审计与经济研究》(Auditing and Economics Research — 南京审计大学主办、专家匿名审稿、不收审稿费/版面费的审计经济双月刊) or deciding whether a Chinese…brycewang-stanfordaussenwirtschaft-antidumping-erstattung-reviewWenn es um Antidumping-Erstattung und Review: Margenkorrektur und Rueckforderung in Außenwirtschaft, Sanktionen, Zoll und CBAM…Klotzketteauto-paper-improvement-loopAutonomously improve a generated paper via GPT-5.4 xhigh review → implement fixes → recompile, for 2 rounds. Use when user says…brycewang-stanfordwritesauto-review-loopAutonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive…brycewang-stanfordwritesauto-setupAuto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use…rohitg00automated-review-guideAI-assisted peer review tools, workflows, and quality standardsbrycewang-stanfordautomatischer-aktualisiererWenn es um /automatischer-aktualisierer — Automatische Aktualisierung mit Diff-Review in Kanzlei-Builder-Hub geht: prüft Frist…Klotzketteautonomous_non_fiction_book_writerOperates as an autonomous expert author to write high-quality, long-form non-fiction books using a strict JSON command interface.…ECNU-ICALKautonomous-prOtonom PR yasam dongusu. PR olustur, CI bekle, hata varsa duzelt, review feedback'i uygula, merge'e hazirla. Budget ve zaman…vibeevalautonomous_wikipedia_error_reviewerAutonomous agent that retrieves Simple English Wikipedia articles, identifies grammatical, factual, and clarity errors, and…ECNU-ICALKautopilot-statusCheck campaign autopilot status. Use when: health scores, auto-corrections, guardrail review, campaigns needing attention.indranilbanerjeeautoresearchAutonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics…githubavv-pruefungWenn es um AVV-Review – Auftragsverarbeitungsvertrag Art. 28 DSGVO in Datenschutzrecht geht: prüft Frist, Form, Zuständigkeit…Klotzketteb1VS-Enhanced Literature Review Strategist - Comprehensive support for multiple review methodologies Full VS 5-Phase process…brycewang-stanfordb2VS-Enhanced Evidence Quality Appraiser - Prevents Mode Collapse with context-adaptive quality assessment Enhanced VS 3-Phase…brycewang-stanfordbabysitWatch a pull request or review cycle until it is ready to merge. Use when asked to babysit, monitor, or keep checking PR…thedotmackbatch-all-issuesResolve every open issue one at a time: fact-check each with web research, close the ones that need no action, and run the…dyoshikawabatch-all-scrap-issuesResolve every open maintainer-scrap issue one at a time: fact-check each with web research, close the ones that need no action…dyoshikawabatchBatch job-application filler. Given several job URLs (or a urls.txt file), run the assisted-apply flow for each in its own…extrasmall0batch-review-prs-awaiting-maintainerBatch-triage open pull requests: list PRs with prs-awaiting-maintainer, review each with review-pr, then post-review-comments…dyoshikawabcftools-variant-manipulationCLI for VCF/BCF: filter, merge, annotate, query, normalize, compute stats. Core post-variant-calling: quality filtering…BioTender-maxbefore-you-buildReview product risk before coding by checking demand, alternatives, channels, switching costs, and failure signals.sickn33behavioral-modesAI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.sickn33benchmarking-clinical-nerScore an OpenMed clinical or biomedical NER model against a user-supplied gold corpus with entity-level precision, recall, and…maziyarpanahibess-power-quality-emvWenn es um Power Quality, EMV und Netzrückwirkungen in Energierecht geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente…Klotzkettebid-tender-reviewAnalyse a construction bid or tender package for scope gaps, risk-shifting exclusions, unit-rate red flags, and front-loading in…mohitagw15856bilingual-contract-reviewWenn es um Bilingual Contract Review in Common-Law-Kompass für deutsche Wirtschaftsjuristen geht: entwickelt Verhandlungsziel…Klotzkettebjps-literature-positioningUse when positioning a British Journal of Political Science (BJPS) manuscript against the literature so it reads as a…brycewang-stanfordbjps-review-processUse to understand how the British Journal of Political Science (BJPS) evaluates a manuscript — double-blind review with at least…brycewang-stanfordblock-no-verify-hookConfigure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use…wshobsonblog-strategyBlog strategy development including topic cluster architecture with hub-and-spoke design, audience mapping, competitive landscape…AgriciDanielblog-strategyBlog strategy development including topic cluster architecture with hub-and-spoke design, audience mapping, competitive landscape…Infrasity-LabsblueprintTurn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step…mturacbrag-docKeep a running brag document of your accomplishments so reviews and promo cases write themselves. Use when asked to start or…mohitagw15856brag-sheetTurn vague "what did I do?" into evidence-backed impact statements for performance reviews, self-reviews, promotion packets, and…githubbrainstormingThe Socratic spec-refinement front of /feature, and the planning front of /sprint. Routed to BEFORE any code — it takes a…arbiterForgebrooks-lintAI code reviewer grounded in classic software engineering books for catching design smells, coupling issues, and architectural…sickn33buildWorkflow orchestrator that chains existing skills for feature developmentparcadeibulletin-of-the-american-meteorological-societyUse when targeting the Bulletin of the American Meteorological Society (BAMS) or deciding whether a broad-interest…brycewang-stanfordbun-developmentFast, modern JavaScript/TypeScript development with the Bun runtime, inspired by [oven-sh/bun](https://github.com/oven-sh/bun).sickn33Business English Translation PracticeGenerates short translation exercises tailored for foreign company work environments and provides detailed review, optimization…ECNU-ICALKbusiness-health-diagnosticDiagnose SaaS business health across growth, retention, efficiency, and capital. Use when preparing a business review or…deanpetersbusiness-operations-skillsUse when running, diagnosing, or designing internal business operations — process documentation, vendor SLAs, capacity planning…alirezarezvanibuyer-job-intent-analysisRecover source-bound buyer jobs, struggling moments, desired progress, forces, workarounds, information acts, journey states…elvisunC++ Code Issue FinderActs as a C++ developer to identify and explain issues, bugs, or compilation errors in provided code snippets.ECNU-ICALKТестер и исправитель C-кода с оптимизацией под слабое CPUАнализирует C-код (особенно FFmpeg/RKNN) на ошибки и баги, оптимизирует вычисления для однопроцессорных систем. Соблюдает строгие…ECNU-ICALKca-debugInvestigate-then-decide root-cause analysis for a defect whose cause is unknown. No code changes — exits to $ca-fix, $ca-adr, or…arbiterForgeca-prOpen a pull request the only sanctioned way — clear every BLOCK-level review finding, then stage the PR. Never a direct write to…arbiterForge
← Prev32 / 62Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going