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
2,2092,256 · page 47 / 62
loop-itAutomated issue loop with checkpoint/resume: fetch open GitHub issues → dependency-aware topological sort → implement each issue…smallnestLyrics Quality Rating and AnalysisRate song lyrics on a 1-100 scale based on specific criteria including lyricism, imagery, evocative qualities, poetic technique…ECNU-ICALKm365-agents-tsMicrosoft 365 Agents SDK for TypeScript/Node.js. Build multichannel agents for Teams/M365/Copilot Studio with AgentApplication…microsoftm365-agents-tsMicrosoft 365 Agents SDK for TypeScript/Node.js.sickn33maintain-codex-wikiMaintain a review-first engineering wiki with provenance, citation-aware queries, explicit capture and promotion, and…sickn33makepad-referenceThis category provides reference materials for debugging, code quality, and advanced layout patterns.sickn33management-reviewUse when targeting 《管理评论》(Management Review — 中国科学院大学主办的管理学术月刊, 全程匿名审稿) or deciding whether a Chinese management manuscript fits…brycewang-stanfordmandantenkommunikation-redteam-qualitygateWenn es um Liquiditätskommunikation Red-Team und Quality-Gate in Liquiditätsplanung — Power geht: zerlegt Ergebnis, Frist…Klotzkettemariadb-operator-commentPost a comment (or a formal PR review) to a GitHub issue or pull request in mariadb-operator/mariadb-operator. Use whenever the…mariadb-operatormariadb-operator-pr-reviewPerform a structured maintainer-style PR review for the mariadb-operator repository. Gathers PR context, triages the change, and…mariadb-operatormarket-gap-analysisIdentify underserved market gaps and unmet customer needs in e-commerce. Analyzes competitor blind spots, review pain points…nexscope-aimaster-thesis-reviewGenerate master's thesis review reports (硕士论文评阅意见) calibrated to a given score. Outputs academic evaluation and…brycewang-stanfordwritesmathfin-review-processUse when navigating the Mathematical Finance (Wiley) review process — single-blind editor screening, associate-editor handling…brycewang-stanfordmatplotlib-scientific-plottingLow-level Python plotting for scientific figures: publication-quality line, scatter, bar, heatmap, contour, 3D; multi-panel…BioTender-maxmcp-builderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through…composio-communitymcp-builderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through…ECNU-ICALKmcp-builder-msUse this skill when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript…sickn33mcp-tool-developerBuild Model Context Protocol (MCP) servers and tools from scratch. Full-stack MCP development with TypeScript/Python, testing…sickn33md-to-pdf-academicConvert Markdown to publication-quality PDF with LaTeX math renderingbrycewang-stanfordmdpr-skillReview MDPR Markdown presentation workflows with semantic hints, visual checks, and deterministic renderer boundaries.sickn33med-researcher-guideMulti-agent system for biomedical literature review and synthesisbrycewang-stanfordmeeting-follow-up-pipelineTurn a completed meeting into a debrief, decisions, action items, ready-to-send follow-up drafts, and proposed writebacks. Use…zapiermeeting-prepPrepare briefings for today's meetings \u2014 attendee research, email\ \ history, past meeting notes, LinkedIn, and company…jeremylongshorewritesmemory-to-skillTurn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill…zilliztechwritesmeta-github-pr-watch-digestInspect the user's open GitHub PRs / failing CI / new issues via `gh`, summarize into 3 buckets (to-review / awaiting-me /…opensquillameta-sales-lead-researcherUse this meta-skill instead of answering directly when the user wants account research, lead qualification, company/person…opensquillameta-short-dramaUse this meta-skill instead of answering directly when the current user asks to generate an AI short-drama or 短剧 from a topic.…opensquillameta-synthesis-guideConduct qualitative meta-synthesis and evidence synthesis methodsbrycewang-stanfordmgsci-review-processUse to understand how Management Science (INFORMS) review and decisions work — the Department/area-editor desk screen…brycewang-stanfordmicro-review-processUse when reasoning about how a MICRO submission is judged — the double-blind HotCRP pipeline from the April deadline through the…brycewang-stanfordmidjourney_illustration_prompt_expertGenerates high-quality English Midjourney prompts for illustrations, strictly preserving user subjects while integrating artistic…ECNU-ICALKgsd:milestone-summaryGenerate a comprehensive project summary from milestone artifacts for team onboarding and reviewdavepoonwritesmind-citation-and-styleUse when formatting references and applying the MIND house style to a Mind article. Mind provides a MIND Stylesheet and requires…brycewang-stanfordmind-review-processUse to understand how Mind evaluates a submission — triple-anonymous peer review, quality as the sole criterion, the role of…brycewang-stanfordmind-revision-and-responseUse when responding to a Mind decision — a revise-and-resubmit, a reject-with-encouragement, or referee reports to address before…brycewang-stanfordmind-submissionUse when running the final pre-submission preflight for Mind via ScholarOne — preparation for triple-anonymous review, the…brycewang-stanfordminutes-prepInteractive meeting preparation — builds a relationship brief and talking points before a call. Use when the user says "prep me…silversteinminutes-release-notesDraft user-facing Minutes release notes for a version from the commit range, recent GitHub releases, and the repository release…silversteinminutes-weeklyWeekly meeting synthesis — themes, decision arcs, stale commitments, and what deserves your attention next week. Use when the…silversteinmisq-rebuttalUse after a MIS Quarterly revision decision to plan the revision and draft the point-by-point response — prioritizing the Senior…brycewang-stanfordmisq-review-processUse to understand how MIS Quarterly's editorial process works and to read a decision letter — the double-anonymous model, the…brycewang-stanfordmisq-submissionUse for the final pre-submission preflight of a MIS Quarterly manuscript — confirming the ScholarOne workflow, Word-file format…brycewang-stanfordmistral-ci-integrationConfigure Mistral AI CI/CD integration with GitHub Actions and prompt testing. Use when setting up automated testing, prompt…jeremylongshorewritesmistral-common-errorsDiagnose and fix Mistral AI common errors and exceptions. Use when encountering Mistral errors, debugging failed requests, or…jeremylongshoremistral-debug-bundleCollect Mistral AI debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing…jeremylongshoremistral-sdk-patternsApply production-ready Mistral AI SDK patterns for TypeScript and Python. Use when implementing Mistral integrations, refactoring…jeremylongshorewritesmksc-rebuttalUse when drafting the revision and response letter after a Marketing Science revise-and-resubmit — structuring point-by-point…brycewang-stanfordmksc-review-processUse when understanding how Marketing Science evaluates a manuscript — the double-anonymous Senior-Editor / Associate-Editor…brycewang-stanford
← Prev47 / 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