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
2,3532,400 · page 50 / 104
scienceworld-process-monitorThis skill observes the state of an active apparatus and its contents to track progress. Use when you need to periodically check…zjunlpscienceworld-room-explorerPerforms an initial survey of a room to identify all visible objects, containers, devices, and their states using the 'look…zjunlpscienceworld-room-navigatorTeleports the agent to a specified room within the ScienceWorld environment. Use when the agent needs to move between different…zjunlpscienceworld-room-scannerThis skill performs a 'look around' action to scan and describe the current room's contents, including visible objects…zjunlpscienceworld-target-locatorThis skill determines the most likely location for a target object based on domain knowledge and environmental clues. Use when…zjunlpscienceworld-temperature-measurerThis skill uses a thermometer on a substance to measure its temperature. It should be triggered when the agent needs to determine…zjunlppufferlibThis skill should be used when working with reinforcement learning tasks including high-performance RL training, custom…majiayu000tooluniverseUse this skill when working with scientific research tools and workflows across bioinformatics, cheminformatics, genomics…majiayu000shapModel interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine…majiayu000sympyUse this skill when working with symbolic mathematics in Python. This skill should be used for symbolic computation tasks…majiayu000torchdrugPyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery…majiayu000scikit-learnMachine learning in Python with scikit-learn. Use for classification, regression, clustering, model evaluation, and ML pipelines.majiayu000scillmLLM completions (text and VLM) via scillm/Chutes.ai. Two main patterns: (1) VLM for image/figure/table description, (2) Text for…majiayu000writesscoping-product-researchUse when scoping product research is required during research work, especially when the result must be traceable, independently…casioreview20-glitchscoring-contextual-creativityUse when scoring contextual creativity is required during creativity work, especially when the result must be traceable…casioreview20-glitchscreen-effectsFull-screen effect skill for damage indicators.a5c-aiwritessearch-conversationsSearch past Claude Code conversations. Use when user says "search conversations", "find that chat", "what did we discuss", "where…majiayu000search-guide搜索工具调用决策指南。明确定义 Agent 何时应调用搜索工具(如实时信息、具体事实),何时应依赖内部知识。作为参考规范,优化 Agent 的工具使用策略。majiayu000securing-automation-credentialsUse when securing automation credentials is required during automation product work, especially when the result must be…casioreview20-glitchsecuring-extension-storageUse when securing extension storage is required during browser-extensions product work, especially when the result must be…casioreview20-glitchselecting-model-providerUse when selecting model provider is required during meta work, especially when the result must be traceable, independently…casioreview20-glitchselecting-winning-conceptUse when selecting winning concept is required during product work, especially when the result must be traceable, independently…casioreview20-glitchself-customizeCustomize your own agent — add capabilities, install packages, add MCP servers, edit code or CLAUDE.md. Use when the user asks…majiayu000self-evolving-agentDarwin Gödel Machine patterns for self-improving AI agents with open-endedmajiayu000semantic-code-analyzerLLM-powered semantic analysis of code diffs to detect business-logic trojansa5c-aiwritessemantic-kernelBuild AI applications with Microsoft Semantic Kernel. Create plugins, planners, and memory systems. Use for enterprise AI…majiayu000semantic-kernelBuild AI applications with Microsoft Semantic Kernel. Create plugins, planners, memory systems, and AI orchestration. Use for…majiayu000semantic-search-setupSetup vector embeddings and semantic search for document collections. Use for AI-powered similarity search, finding related…majiayu000senior-computer-visionComputer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision…majiayu000senior-computer-visionComputer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision…majiayu000senior-ml-engineerWorld-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch…majiayu000sensor-fusionExpert skill for multi-sensor fusion and state estimation using Kalman filtering. Implement EKF/UKF, configure…a5c-aiwritessensor-fusionExpert skill for multi-sensor fusion and state estimation using Kalman filtering. Implement EKF/UKF, configure…majiayu000writesSensor Fusion Lidar PointcloudThis skill covers the implementation of core software systems for autonomous vehicles and drones, including sensor fusion…majiayu000session-analyzerAnalisa sessoes do Claude Code para extrair learnings e persistir conhecimento. Le arquivos de sessao em ~/.claude/projects/ e…majiayu000writessession-analyzerAnalisa sessoes do Claude Code para extrair learnings e persistir conhecimento. Le arquivos de sessao em ~/.claude/projects/ e…majiayu000writessession-behaviorCore behavioral guidelines and interaction patterns for the agent. This skill provides the foundation for how the agent should…majiayu000session-bootstrapUniversal init prompt — every agent spawned into an AgentOps repo runs `ao session bootstrap` first.majiayu000session-insightsAnalyze past Claude Code sessions to extract patterns, metrics, and recommendations.majiayu000session-managementManage agent sessions including initialization, handoffs, revival (seance), and persistent identity for Polecats and Crew agents.a5c-aiwritessession-replayAnalyze claude-trace JSONL files for session health, patterns, and actionable insights. Use when debugging session issues…majiayu000session-searchSearch through historical Claude sessions for code, conversations, and commands. Use when user asks about previous sessions, past…majiayu000session-trendsAnalyze trends across session metrics. Computes windowed aggregates, deltas, and compares against MEMORY.md findings. Use…oliver-kriskashader-effectsCommon shader effects skill for dissolve, outline, hologram, toon, water, fire effects.a5c-aiwritesshader-optimizationShader performance optimization skill for instruction counting, GPU profiling, and rendering efficiency.a5c-aiwritesshadow-techniquesShadow mapping skill for cascaded shadows, contact hardening, and optimization.a5c-aiwritesshap-explainerSHAP-based model explainability skill for feature attribution, summary plots, and interaction analysis.a5c-aiwritesshap-explainerSHAP-based model explainability skill for feature attribution, summary plots, and interaction analysis.majiayu000writes
← Prev50 / 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