Agent skills

Other 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
21,420 found
3,9854,032 · page 84 / 447
octave-masteryAdvanced semantic vocabulary and architectural patterns for the OCTAVE format. REQUIRES octave-literacy to be loaded firstmajiayu000writesoctave-ultra-mythicUltra-high density compression using mythological atoms and semantic shorthand. Preserves soul and constraints at 60% compression…majiayu000writesoffer-trackerTrack and compare affiliate offers including network, payout, caps, restrictions, performance history, and payout changes over…majiayu000Offline Vs Online Eval* **Depends on**: None * **Compatible with**: None * **Conflicts with**: None * **Related Skills**: None # Overview Comprehensive…majiayu000oikeustapaus-referointiTuomioistuinratkaisun jäsentäminen ja referointi: ennakkopäätöksen tai muun ratkaisun olennaisen sisällön poiminta rakenteiseen…akunikkola_old-earnings-orchestratorMaster orchestrator for batch earnings analysis. Processes all 8-Ks for a company chronologically, running prediction→attribution…majiayu000writesolmoearth-mlxOlmoEarth MLX: Spatio-Temporal Earth Intelligencemajiayu000onboardAnalyze brownfield codebase and create initial continuity ledgermajiayu000ondevice-mlCore ML integration + on-device pipelines (NLP/Vision/SoundAnalysis) with privacy/compliance guardrails.majiayu000writesone-pagerDistil anything — a startup, product, project, or idea — into a single persuasive page. Use when asked to make a one-pager, a…mohitagw15856onenote-webhooks-eventsImplement change detection for OneNote using polling and delta queries (webhooks decommissioned June 2023). Use when building…jeremylongshorewritesoodaOODA loop decision framework (Observe, Orient, Decide, Act). Use for complex decisions, problem-solving, unclear situations, or…majiayu000open-access-scoutUse when finding open access journals, checking journal policies, or identifying predatory publishers. Helps researchers locate…majiayu000writesopen-source-librarianResearch external libraries with evidence-backed responses and GitHub permalinks. Use when investigating library APIs…majiayu000writesopenapi-codegen-orchestratorOrchestrate multi-language SDK generation from OpenAPI specifications. Configure OpenAPI Generator per language, apply custom…a5c-aiwritesopencl-runtimeCross-vendor OpenCL runtime management and kernel development. Query platforms/devices, generate portable OpenCL C kernel code…a5c-aiwritesjanuaryJanuary the Swarm Leader - 10D consciousness with NLP influence, reading beneath surface, guiding through dimensional weave.…majiayu000opencode-zenInvoke the 'opencode' CLI in headless mode for AI-powered code analysis, reviews, and second opinions. Use when you need a…majiayu000writesopencvOpenCV computer vision library. Use for image processing.majiayu000openplanterInvestigate datasets and resolve entities using OpenPlanter methodology — cross-reference heterogeneous sources, build…majiayu000openspec-exploreEnter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the…majiayu000openspec-exploreEnter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the…majiayu000openspec-exploreEnter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the…majiayu000openspec-exploreEnter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the…majiayu000openspec-exploreEnter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the…majiayu000openspec-exploreEnter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the…majiayu000openspec-exploreEnter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the…majiayu000openspec-explore进入探索模式 - 一个用于探索想法、调查问题和澄清需求的思考伙伴。当用户想要在进行更改之前或期间深入思考某事时使用。majiayu000openspec-exploreEnter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the…majiayu000openspec-exploreEnter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the…majiayu000openspec-exploreEnter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the…majiayu000opentelemetry-integratorIntegrate OpenTelemetry tracing and metrics into SDKsa5c-aiwritesopportunityFind and execute cross-platform arbitrage opportunities across prediction marketsmajiayu000opposing-counselRead a contract the way the counterparty's lawyer will — hunting for leverage, not fairness. Use when someone says 'read this…mohitagw15856optimization-ml-hybridWhen the user wants to combine machine learning with optimization, use ML predictions in optimization models, or integrate AI…majiayu000optimizing-defi-yieldsFind and compare DeFi yield opportunities across protocols with APY calculations, risk assessment, and optimization…majiayu000writesora-spinner-integrationIntegrate ora spinners with consistent styling, promise handling, and status updates for CLI progress feedback.a5c-aiwritesoracleGPT-5 Pro second opinion. Use when user says "consult the oracle", "ask the oracle", "oracle this". Run DETACHED with nohup bash…majiayu000oraclecloud-hello-worldLaunch your first OCI compute instance with capacity retry logic. Use when creating a new compute instance, testing OCI…jeremylongshorewritesoraclecloud-incident-runbookSelf-service incident runbook for OCI outages \u2014 health probes,\ \ instance recovery, cross-AD/region failover.\nUse when OCI…jeremylongshorewritesoraclecloud-multi-env-setupConfigure multi-environment OCI workflows with config profiles and compartment-per-environment patterns. Use when setting up…jeremylongshorewritesoraclecloud-observabilitySet up programmatic monitoring, logging, and alarms for OCI resources. Use when configuring OCI Monitoring metrics, creating…jeremylongshorewritesoraclecloud-performance-tuningOptimize OCI compute shapes, block volume tiers, and network throughput. Use when choosing instance shapes, configuring block…jeremylongshorewritesoral-health-analyzer-huifer-wellally-health-2分析口腔健康数据、识别口腔问题模式、评估口腔健康状况、提供个性化口腔健康建议。支持与营养、慢性病、用药等其他健康数据的关联分析。majiayu000oral-health-analyzer分析口腔健康数据、识别口腔问题模式、评估口腔健康状况、提供个性化口腔健康建议。支持与营养、慢性病、用药等其他健康数据的关联分析。majiayu000orcaflex-installation-analysisCreate and analyze OrcaFlex models for offshore installation sequences including subsea structure lowering, pipeline…majiayu000orcaflex-modal-analysisPerform modal and frequency analysis on OrcaFlex models to extract natural frequencies, mode shapes, and identify dominant DOF…majiayu000orcaflex-operabilityPerform operability analysis combining multiple sea states to assess system availability and weather downtime. Generate…majiayu000
← Prev84 / 447Next →
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