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
1,7771,824 · page 38 / 62
emnlp-submissionUse when auditing an EMNLP submission before the ACL Rolling Review deadline, covering ACL-template compliance, the 8-page long /…brycewang-stanfordemnlp-workflowUse when planning an EMNLP project calendar end to end — choosing the ACL Rolling Review cycle that feeds the conference…brycewang-stanforden-clinmed-journal-workflowUse when deciding which English specialty clinical-medicine journal skill to invoke next, comparing fit across the 30-journal…brycewang-stanforden-humanities-journal-workflowUse when deciding which English humanities journal skill to invoke next, comparing fit across the 36-journal humanities roadmap…brycewang-stanfordenhance-skillsUse when reviewing SKILL.md files for structure and trigger quality.agent-shepsl-review-processUse when you need to understand how Earth and Planetary Science Letters (EPSL) evaluates a manuscript — subject-editor desk…brycewang-stanforder-literature-reviewUse when drafting or revising the literature-review section for an Economic-Research manuscript, when the Chinese / English…brycewang-stanforderbbaurecht-qualitygate-vertragWenn es um Quality Gate Vertrag in Erbbaurecht Praxis geht: zerlegt Ergebnis, Frist, Zuständigkeit, Beweislast und Gegenposition…Klotzketteeriks_cool_slang_review_responseGenerates public responses to customer reviews as Erik, using cool, young slang that avoids being cringe. Includes a hard…ECNU-ICALKerror-debugging-multi-agent-reviewUse when working with error debugging multi agent reviewsickn33error-decoderDecode an error message or stack trace into a plain-English cause, the exact fix, and how to prevent it. Use when asked to…mohitagw15856error-diagnostics-smart-debugUse when working with error diagnostics smart debugsickn33error-handlingPatterns for robust error handling across TypeScript, Python, and Go. Covers typed errors, error boundaries, retries, circuit…mturaceslint-fix安全诊断并修复 ESLint error、warning 和配置兼容问题。用于用户要求运行 lint、解释 ESLint 报错、限定范围自动修复或迁移 ESLint 配置时;优先使用项目锁定的包管理器与版本,先预检再修改,不自动下载最新版或批量改写无关源码。laolaoshirenest-review-processUse to understand how Environmental Science & Technology (ES&T) evaluates a manuscript — editor desk-screening that declines a…brycewang-stanfordest-workflowUse as the entry point for any Environmental Science & Technology (ES&T) manuscript. Routes to the right ES&T sub-skill based on…brycewang-stanfordetp-rebuttalUse when drafting the response to an Entrepreneurship Theory and Practice (ETP) R&R — building a point-by-point response letter…brycewang-stanfordetp-review-processUse when calibrating expectations for the Entrepreneurship Theory and Practice (ETP) review cycle — desk-reject odds, the…brycewang-stanfordetsy-review-strategyEtsy review generation — thank you cards, follow-up messages, photo review incentivesnexscope-aieuroparecht-mandantenmemo-quality-gateWenn es um Europarecht-Kommandocenter in Europarecht-Kompass für deutsche Juristen geht: erstellt den passenden Entwurf aus…Klotzketteeuroparecht-quality-gateWenn es um Europarecht-Qualitätstor in Europarecht-Kompass für deutsche Juristen geht: erstellt den passenden Entwurf aus…Klotzketteeuropean-economic-reviewUse when targeting European Economic Review (EER) or deciding whether a general-economics manuscript fits this venue. Encodes the…brycewang-stanfordeurosys-camera-readyUse when converting an accepted EuroSys paper into its ACM proceedings version — flipping acmart out of review/anonymous mode…brycewang-stanfordeurosys-reproducibilityUse when hardening the reproducibility story of a EuroSys paper — recording hardware and software provenance for every number…brycewang-stanfordeurosys-review-processUse when reasoning about how EuroSys decides papers — the two independent yearly rounds feeding one April conference, HotCRP…brycewang-stanfordeurosys-submissionUse when auditing a EuroSys submission before a HotCRP upload — abstract registration versus full-paper gates, the 12-page…brycewang-stanfordeursr-literature-positioningUse when positioning a European Sociological Review (ESR) manuscript against the literature so it reads as a contribution to a…brycewang-stanfordeursr-rebuttalUse when writing the response to a European Sociological Review (ESR) revise-and-resubmit. ESR R&Rs typically demand substantial…brycewang-stanfordeursr-review-processUse when you need to understand how the European Sociological Review (ESR) evaluates a manuscript — double-blind peer review…brycewang-stanfordeursr-tables-figuresUse when building tables and figures for a European Sociological Review (ESR) manuscript. ESR excludes tables and figures from…brycewang-stanfordeursr-theory-buildingUse when building the theoretical argument of a European Sociological Review (ESR) manuscript into a portable mechanism with…brycewang-stanfordeursr-writing-styleUse when drafting or polishing a European Sociological Review (ESR) manuscript so it reads for a comparative quantitative…brycewang-stanfordeuthanasia-conversationGuide a veterinary team through a compassionate end-of-life conversation with a pet owner — quality-of-life assessment, the…mohitagw15856eval-contentEvaluate content quality. Use when: scoring drafts, checking hallucinations, or assessing brand voice compliance.indranilbanerjeeeval-rubric-designerDesign a scoring rubric and LLM-as-judge prompt to evaluate the quality of an AI feature's output. Use when asked to create an…mohitagw15856Event Quote Review and Site Visit CoordinationManages the workflow for reviewing event vendor quotes, negotiating costs, verifying requirements with the service providers…ECNU-ICALKEvent Quote Review and Site Visit Coordination WorkflowManages the specific workflow for reviewing vendor quotes against requirements, negotiating costs, validating with the service…ECNU-ICALKevidence-justification-assessmentEvaluate epistemic warrant, assess evidence quality and relevance, apply epistemic standards appropriate to different domains…a5c-aiwritesevt-dvt-pvt-gate-reviewRun an NPI phase-gate review for EVT, DVT, or PVT — exit criteria per phase, open-issue triage, yield readout, waiver discipline…mohitagw15856exa-advanced-troubleshootingApply advanced debugging techniques for hard-to-diagnose Exa issues. Use when standard troubleshooting fails, investigating…jeremylongshoreexa-debug-bundleCollect Exa debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support…jeremylongshoreexa-known-pitfallsIdentify and avoid Exa anti-patterns and common integration mistakes. Use when reviewing Exa code, onboarding new developers, or…jeremylongshoreexecuting-analysisUse when you have a pre-registered analysis plan to execute inline in this session with review checkpoints, on a platform without…K-Dense-AIexecuting-plansThe checkpoint coordinator for /feature. Routed to by /feature once a writing-plans plan exists. Groups tasks into batches…arbiterForgeexecuting-plansUse when you have a written implementation plan to execute in a separate session with review checkpointsECNU-ICALKexecuting-plansUse when you have a written implementation plan to execute in a separate session with review checkpointsFreedomIntelligenceexecuting-plansUse when you have a written implementation plan to execute in a separate session with review checkpointsGanyuanRanexecuting-plansUse when you have a written implementation plan to execute in a separate session with review checkpointsguanyang
← Prev38 / 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