Agent skills

AI & Agents 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
4,965 found
2,4492,496 · page 52 / 104
source-locked-verificationNo Inference / Source-Locked Verification. Forces Claude to answer ONLY from user-provided materials and/or online sources…lawve-aiSource MapsExpert skill for generating and consuming source maps for debugging compiled codea5c-aiwritessource-verifyThis skill should be used when the user asks to 'verify sources', 'check citations', 'fact-check footnotes', 'verify quotes'…majiayu000spacy-nerspaCy NER model training and entity extraction for conversational AIa5c-aiwritesspacy-nerspaCy NER model training and entity extraction for conversational AImajiayu000writesspawnSkills for spawning external processes - AI coding agents and generic CLI commands in new terminal windows. Parent skill category…majiayu000cfn-agent-spawningAgent process spawning with provider configuration and executionmajiayu000speak-responseVocalize Claude's last response using local Qwen3-TTS. Default voice is the Oracle (deep, resonant Dune narrator). Use --preset…majiayu000split-decisionWhen facing architectural decisions, technology choices, or strategic trade-offs, present options as a structured comparison and…majiayu000spring-ai-alibabaProvides comprehensive guidance for Spring AI Alibaba including Alibaba Cloud AI services integration, model APIs, and AI…majiayu000spring-aiProvides comprehensive guidance for Spring AI including AI model integration, prompt templates, vector stores, and AI…majiayu000stagentdescription: A multimodal LLM-based AI agent for deep spatial transcriptomics research, capable of dynamic code generation…majiayu000start-researchStart a research exploration using the technical-research skill. For early-stage ideas, feasibility checks, and broad exploration…majiayu000state-syncState synchronization skill for delta compression and interpolation.a5c-aiwritesstationUse Station CLI (`stn`) for AI agent orchestration - creating agents, running tasks, managing environments, and deploying agent…majiayu000steam-sdkSteamworks skill for achievements and cloud saves.a5c-aiwritessteamworks-networkingSteam P2P networking skill for lobbies and relay servers.a5c-aiwritessteering-behaviorsSteering behaviors skill for flocking, avoidance, and group movement.a5c-aiwritessteeringsteering skill Trigger terms: steering, project memory, codebase analysis, auto-update context, generate steering, architecture…majiayu000writesstory-senseDiagnose what any story needs regardless of its current state. This skill should be used when a writer is stuck, evaluating story…majiayu000structured-outputsStructured Outputs ensure that an LLM's response always conforms to a predefined JSON schema. This moves beyond simple prompt…majiayu000substanceSubstance Painter/Designer skill for baking and material export.a5c-aiwritessuggest_model次のタスクの内容(コーディング、リサーチ、リファクタリングなど)に応じて、最適なLLMモデルを提案するmajiayu000super-agent-orchestratorAutonomous system combining Cognitive Nexus patterns, Mastermind forensics, and Repo Operator completion.majiayu000superclaude-flagsProvides flag definitions and usage rules when double-dash flags (--flag-name) detected in user prompt - describes execution…majiayu000superclaude-prompt-generatorExpert SuperClaude prompt engineering assistant that analyzes user needs and crafts optimal prompts using the full SuperClaude…majiayu000supervisor-agentCourt-grade intake supervisor. Extracts structured facts, parties, issues, timeline, jurisdiction hints, and missing fields from…majiayu000surface-energyThis skill group covers the calculation of surface energies and the prediction of equilibrium crystal shapes via the Wulff…majiayu000surrealfsSurrealFS virtual filesystem for AI agents. Rust core + Python agent (Pydantic AI). Persistent file operations backed by…majiayu000sva-assertionsSpecialized skill for creating and debugging SystemVerilog assertions for FPGA verificationa5c-aiwritesswarm-orchestrationMulti-agent swarm formation and coordinated execution with topology-aware agent deployment, consensus protocols, and anti-drift…a5c-aiwritesSwift/SwiftUI DevelopmentExpert skill for native iOS development with Swift and SwiftUIa5c-aiswiftdataSwiftData skills — class inheritance patterns for hierarchical models, type-based querying, polymorphic relationships, and…rshankrasswing-traceExposes Claude's reasoning chain as an auditable, decomposable artifact. Quick mode (default) gives assumption inventory +…majiayu000writesswitch-modelタスクの複雑さに応じて Claude のモデルを自動的に切り替える。複雑なタスク(アーキテクチャ設計、大規模リファクタリング、難解なバグ修正)では opus を、単純なタスク(小さな修正、フォーマット、簡単な質問)では sonnet…majiayu000writesswitch-sdkNintendo Switch SDK skill for Joy-Con features.a5c-aiwritessync-comparisonsSync cross-agent comparison (Dimension 8) across all analysis docsmajiayu000synthesizing-product-evidenceUse when synthesizing product evidence is required during research work, especially when the result must be traceable…casioreview20-glitchsystem-promptsWrite system prompts, tool docs, and agent definitions. Combines research-backed prompt engineering (+15-30% measured…majiayu000system-promptsWrite system prompts, tool docs, and agent definitions. Combines research-backed prompt engineering (+15-30% measured…majiayu000szz-bug-introducing-commit-identifierIdentifies bug-introducing commits using SZZ-style analysis based on bug-fixing commits, commit history, and code blame…majiayu000taxonomyExtract Federated Taxonomy tags from text. LLM extracts candidates, deterministic validation filters to known vocabulary. Returns…majiayu000writesteam-ultra-analyzeDeep collaborative analysis team skill. All roles route via this SKILL.md. Beat model is coordinator-only (monitor.md). Structure…majiayu000teammateSpawn or manage voice teammates. Each teammate is a separate Claude personality in its own tmux pane.majiayu000tech-decisionThis skill should be used when the user asks to "기술 의사결정", "뭐 쓸지 고민", "A vs B", "비교 분석", "라이브러리 선택", "아키텍처 결정", "어떤 걸 써야 할지"…majiayu000technology-selectionGuides technology selection and implementation of AI and ML features in .NET 8+ applications using ML.NET…majiayu000tensorboard-visualizerTensorboard Visualizer - Auto-activating skill for ML Training. Triggers on: tensorboard visualizer, tensorboard visualizer Part…majiayu000writestensorflow-model-trainerBuild tensorflow model trainer operations. Auto-activating skill for ML Training. Triggers on: tensorflow model trainer…majiayu000writes
← Prev52 / 104Next →
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