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
3,8413,888 · page 81 / 447
moai-core-expertise-detectionEnterprise AI-powered user expertise detection with behavioral analysis, communication pattern recognition, code complexity…majiayu000moai-core-personasAdaptive communication patterns and role selection based on user expertise level and request type. Use for personalized user…majiayu000moai-domain-mlEnterprise Machine Learning specialist with TensorFlow 2.20.0, PyTorch 2.9.0, Scikit-learn 1.7.2 expertise. Master AutoML, neural…majiayu000writesmoai-domain-mlEnterprise Machine Learning specialist with TensorFlow 2.20.0, PyTorch\ \ 2.9.0, \nScikit-learn 1.7.2 expertise. Master AutoML…majiayu000moai-foundation-earsEnterprise EARS (Evaluate, Analyze, Recommend, Synthesize) Framework with AI-powered requirements engineering, Context7…majiayu000writesmoai-learning-optimizerIntelligent learning system optimizer that analyzes session patterns, identifies improvement opportunities, and continuously…majiayu000writesMobile Performance ProfilingMobile app performance analysis and optimizationa5c-aiMobile Testing FrameworksComprehensive mobile testing framework expertisea5c-aimobility-analysisTransit and mobility site analysis — subway, bus, bike, pedestrian infrastructure, walk scores, and airport access from an…majiayu000writesmoc-curatorSuggest MOC updates and new MOCs based on semantic clustering. Use when asked to "curate MOCs", "update maps", "find clusters"…majiayu000writesmodeUse when the user wants to change optimization aggressiveness, switch between aggressive/balanced/thorough modes, or adjust…majiayu000writesmodernContemporary editorial style with serif typography, minimal palettes, and clean layouts for polished digital products.bergsidemoebius-inversionMöbius inversion on posets and lattices: alternating sums, chromatic polynomials, incidence algebras, and centrality predicates.majiayu000molecular-dynamicsRun and analyze molecular dynamics simulations with OpenMM and MDAnalysis. Set up protein/small molecule systems, define force…majiayu000molecular-dynamicsRun and analyze molecular dynamics simulations with OpenMM and MDAnalysis. Set up protein/small molecule systems, define force…K-Dense-AImolecular-dynamicsRun and analyze molecular dynamics simulations with OpenMM and MDAnalysis. Set up protein/small molecule systems, define force…LeonChaoXmolfeatMolecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to…majiayu000molfeatMolecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to…majiayu000writesmonitor-etf-holdings-drawdown-risk偵測「商品價格上漲、但對應實物 ETF/信託持倉卻下滑」的背離現象,並用多指標交叉驗證,評估是否存在實物供給緊張/交割壓力風險。majiayu000monitor-experimentMonitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or…majiayu000writesmonitor-experimentMonitor running experiments, check progress, collect results. Use when user says \"check results\", \"is it done\", \"monitor\"…majiayu000monorepo-managementBuild efficient, scalable monorepos that enable code sharing, consistent tooling, and atomic changes across multiple packages and…sickn33monorepo-managementMaster monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with…wshobsonmoollmThe soul of MOOLLM — self-explanation, help, navigation, philosophymajiayu000moonshot-detect-uncertaintyDetects missing requirements and generates clarification questions. Use after classification/complexity to decide if user input…majiayu000motif-analysisGuide for de novo and known motif enrichment analysis of ENCODE ChIP-seq and ATAC-seq peaks using HOMER and MEME Suite. Use when…majiayu000motor-controlMotor control algorithms and driver implementationa5c-aiwritesMOVA: wf_cycle_compute_compare_basic (wrapper)Deterministically compare wf_cycle runs as a Proof of Invariance step: compute metrics, score the double-run, and write canonical…majiayu000mqtt-diagnosisDiagnose MQTT publishing issues between CaptureLora.py and mqtt_grid_web.py. Check topic distribution, connection stability, and…majiayu000bio-metabolomics-msdial-preprocessingMS-DIAL-based metabolomics preprocessing as alternative to XCMS. Covers peak detection, alignment, annotation, and export for…majiayu000msix-package-generatorGenerate MSIX packaging configuration with manifest, assets, and signing for Windows applicationsa5c-aiwritesmtls-configurationConfigure mutual TLS (mTLS) for zero-trust service-to-service communication. Use when implementing zero-trust networking…wshobsonmulti-depot-vrpWhen the user wants to solve Multi-Depot VRP (MDVRP), optimize routes from multiple warehouses/depots, or handle multi-facility…majiayu000multi-lens-thinkingUse when facing complex problems, making decisions, seeking creative solutions, or when single-perspective thinking feels…majiayu000multi-platform-search-searchapiMulti-platform search - YouTube, Amazon, eBay, Walmart, TikTok, Instagram, and moregooseworks-aimultimodal-medical-imagingAnalyzes medical images (X-ray, MRI, CT) using multimodal LLMs to identify anomalies and generate reports.majiayu000musik-app-beiDatenbankrecht für Musik-, Film- und Bildarchive: §§ 87a-87e UrhG für Mediendatenbanken, Schichtenschutz…majiayu000mutually-exclusive-group-handlerGenerate logic for handling mutually exclusive argument groups with clear error messages and validation in CLI applications.a5c-aiwritesmuutoksenhakuMuutoksenhaku hallintopäätökseen Suomen hallintoprosessissa: oikaisuvaatimus, hallintovalitus hallinto-oikeuteen ja valitus…akunikkolamuutoksenhaku-tuomioonMuutoksenhaku yleisen tuomioistuimen tuomioon oikeudenkäymiskaaren (4/1734) mukaan: valitus käräjäoikeuden tuomiosta…akunikkolamvvm-toolkit-diWire CommunityToolkit.Mvvm ViewModels into Microsoft.Extensions.DependencyInjection. Covers the .NET Generic Host composition…githubmvvm-toolkit-messengerCommunityToolkit.Mvvm Messenger pub/sub for decoupled communication between ViewModels (or any objects). Covers…githubmy-personality-isPersonality-tuned AI for the Is (The Encourager) DISC type. Adapts AI tone, structure, and feedback to be warm, supportive, and…majiayu000my-personality-s-cPersonality-tuned AI for the SC (The Stabilizer) DISC type. Adapts AI tone, structure, and feedback to be consistent, thorough…majiayu000my-personality-sPersonality-tuned AI for the S (The Supporter) DISC type. Adapts AI tone, structure, and feedback to be patient, reliable, and…majiayu000my-personality-scPersonality-tuned AI for the Sc (The Planner) DISC type. Adapts AI tone, structure, and feedback to be methodical, structured…majiayu000mythril-symbolicSymbolic execution analysis using Mythril for deep vulnerability detection in smart contracts. Supports configurable transaction…a5c-aiwritesn8n-node-configurationOperation-aware node configuration guidance. Use when configuring nodes, understanding property dependencies, determining…sickn33
← Prev81 / 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