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
1,5371,584 · page 33 / 62
ca-refactorRestructure code with behavioral parity proven through unmodified pre-existing tests, then refactor. No behavior change.arbiterForgeca-reviewReview a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound…arbiterForgeca-standupDaily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only…arbiterForgecanvasPresent HTML on connected OpenClaw node canvases, navigate/eval/snapshot, and debug canvas host URLs.Health-Yangcapacity-planningProduce a capacity planning document for a service covering traffic forecasts, resource requirements, and scaling strategy. Use…mohitagw15856car-review-processUse when you need to understand how Contemporary Accounting Research (CAR) evaluates a manuscript — the double-anonymous…brycewang-stanfordcastai-debug-bundleCollect CAST AI diagnostic bundle for support tickets and troubleshooting. Use when preparing a support case, collecting agent…jeremylongshorecav-author-responseUse when drafting a CAV (Computer Aided Verification) author response (rebuttal) for a paper that has passed the two-stage…brycewang-stanfordcav-review-processUse when reasoning about how a CAV (Computer Aided Verification) submission is evaluated, covering the two-stage reviewing…brycewang-stanfordcav-workflowUse when planning a CAV (Computer Aided Verification) project timeline from venue and category selection through submission, the…brycewang-stanfordcc-peer-review-revisionUse when responding to Cancer Cell (Cell Press) reviewer reports — planning new experiments, writing a point-by-point response…brycewang-stanfordcc-workflowUse when deciding which cc-* sub-skill to invoke next, or when sequencing a Cancer Cell (Cell Press) manuscript from scope check…brycewang-stanfordccs-review-processUse when explaining or planning around ACM CCS peer review, the two-cycle HotCRP workflow, decision categories including minor…brycewang-stanfordceq-literature-reviewUse when positioning a 《经济学(季刊)》 (China Economic Quarterly, CEQ) manuscript's contribution against the literature — benchmarking…brycewang-stanfordcfe-literature-reviewUse when drafting or revising the literature-review section for a Journal-of-Finance-and-Economics (《财经研究》) manuscript.…brycewang-stanfordchange-quizAfter a working session, produce a report on what changed plus a quiz the user must pass before merging. Use when the user asks…Neeeophyteechannel-registryUse when the user asks to register/query a social channel, record channel state, cadence, governance, voice adaptation, UGC…aaron-he-zhuchat-reviewWenn es um Chat-Review in Internal Investigations in Internal Investigations Praxis geht: ordnet Sachverhalt, Norm, Beweislast…KlotzkettecheckRun the unified pre-publish quality gate on marketing content — hallucination detection, claim verification, brand voice scoring…indranilbanerjeewriteschemical-society-reviewsUse when targeting Chemical Society Reviews (Chem Soc Rev) or deciding whether a chemistry review manuscript fits this RSC venue.…brycewang-stanfordchi-artifact-evaluationUse when packaging the artifacts behind an ACM CHI paper — prototypes, study instruments, codebooks, datasets, analysis code —…brycewang-stanfordchi-review-processUse when interpreting the ACM CHI Papers review pipeline — 1AC and 2AC roles, the A/ARR/RR/RRX/X recommendation scale…brycewang-stanfordchi-workflowUse when planning an ACM CHI submission cycle end to end — the single September deadline, two-round review with a five-week…brycewang-stanfordchina-accounting-reviewUse when targeting 《中国会计评论》(China Accounting Review — 北京大学等高校发起、依托北京大学光华管理学院、实行匿名审稿的会计学术季刊) or deciding whether a Chinese…brycewang-stanfordchina-public-administration-reviewUse when targeting 《公共管理评论》(China Public Administration Review — 教育部主管、清华大学主办的公共管理学术季刊, 2004 年创刊, 匿名评审) or deciding whether a…brycewang-stanfordchina-rural-economyUse when targeting 《中国农村经济》(China Rural Economy — 中国社会科学院农村发展研究所主办、CASS 主管的三农经济旗舰月刊, 1985 年创刊, 双向匿名、零审稿/版面费) or deciding whether…brycewang-stanfordchina-rural-surveyUse when targeting 《中国农村观察》(China Rural Survey — 中国社会科学院农村发展研究所主办的三农双月刊, CN11-3586/F, 双向匿名、零审稿/版面费, 需中英文摘要) or deciding whether a…brycewang-stanfordchinese-code-review中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。jnMetaCodechinese-journal-of-managementUse when targeting 《管理学报》(Chinese Journal of Management — 华中科技大学主办、教育部主管的全国性管理学月刊, 2004 年创刊, 双向匿名审稿) or deciding whether a…brycewang-stanfordchinese-public-administrationUse when targeting 《中国行政管理》(Chinese Public Administration — 国务院办公厅主管、中国行政管理学会主办, 不收版面费/审稿费) or deciding whether a Chinese…brycewang-stanfordchinese-review-of-financial-studiesUse when targeting 《金融评论》(Chinese Review of Financial Studies — 中国社会科学院金融研究所主办、2009 年创刊、不收版面费的金融学术双月刊) or deciding whether a…brycewang-stanfordchn-084-quality-crisis-and-recallWenn es um Quality Crisis And Recall in China-Wirtschaftsverkehr geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und…Klotzketteci-review-processUse to understand how Critical Inquiry (CI) evaluates a submission — peer review plus close reading by the editors-in-chief in…brycewang-stanfordci-scholarly-positioningUse to situate a Critical Inquiry (CI) essay within the conversations it enters across the arts and humanities. CI is…brycewang-stanfordci-workflowUse as the entry point for any Critical Inquiry (CI) essay. Routes to the right CI sub-skill based on where you are in the…brycewang-stanfordcikm-artifact-evaluationUse when packaging the code, datasets, knowledge graphs, prompts, and demo systems around a CIKM paper — choosing the artifact…brycewang-stanfordcisco-ios-patternsCisco IOS and IOS-XE review patterns for show commands, config hierarchy, wildcard masks, ACL placement, interface hygiene, and…mturaccjc-review-process在需要理解或预判《计算机学报》(Chinese Journal of Computers, CJC)…brycewang-stanfordcjms-literature-reviewUse when building the literature review and contribution positioning for a 《中国管理科学》 (Chinese Journal of Management Science)…brycewang-stanfordcjms-topic-selectionUse when choosing or vetting a topic for a 《中国管理科学》 (Chinese Journal of Management Science) manuscript — testing fit with the…brycewang-stanfordcjms-writing-styleUse when polishing structure and house style for a 《中国管理科学》 (Chinese Journal of Management Science) manuscript — the prescribed…brycewang-stanfordclarity-gatePre-ingestion verification for epistemic quality in RAG systems. Ensures documents are properly qualified before entering…sickn33claude-academic-workflow-guideClaude Code template for LaTeX, Beamer, and R research workflowsbrycewang-stanfordclay-common-errorsDiagnose and fix the most common Clay errors and integration issues. Use when encountering Clay errors, debugging failed…jeremylongshoreclay-debug-bundleCollect Clay debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support…jeremylongshoreclean-codePrinciples and practices for writing readable, maintainable, and testable codecosmicstack-labsclean-codeThis skill embodies the principles of \"Clean Code\" by Robert C. Martin (Uncle Bob). Use it to transform \"code that works\"…sickn33cli-reviewRuns a Greptile CLI review for the current local branch, installing or authenticating the CLI when needed, then summarizes JSON…alvinunreal
← Prev33 / 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