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
1,9692,016 · page 42 / 104
openai-agentsBuild AI agents with OpenAI Agents SDK, tool registration, conversation history, and stateless execution. Use when creating AI…majiayu000openai-agentsExpert guidance for building AI agents with the OpenAI Agents SDK, from simple single-agent systems to complex multi-agent…majiayu000openai-agents-setupInitialize and configure OpenAI Agents SDK for building AI-powered chatbots. Uses NATIVE MCP integration via…majiayu000writesopenai-agentsYou are an expert in the OpenAI Agents SDK (formerly Swarm), the official framework for building multi-agent systems. You help…majiayu000openai-llmInvoke OpenAI models for text generation, reasoning, and code tasks using the Python openai SDK. Supports gpt-4o (multimodal), o1…majiayu000openai-prompt-engineerGenerate and improve prompts using best practices for OpenAI GPT-5 and other LLMs. Apply advanced techniques like…majiayu000openloomi-loopopenloomi's Loop — the proactive execution brain that runs inside the OpenLoomi desktop app. Use this skill to inspect state, run…melandlabsopenloomi-memoryopenloomi Memory tools - search and manage the holistic context (people, projects, decisions, knowledge base, chat insights).…melandlabsopenrouterAccess 100+ AI models via OpenRouter. Route between providers, manage costs, and use fallbacks. Use for multi-model AI…majiayu000openrouterAccess 100+ AI models via OpenRouter. Route between providers, manage costs, and use fallbacks. Use for multi-model AI…majiayu000opentelemetry-llmOpenTelemetry instrumentation for LLM applications with distributed tracinga5c-aiwritesopentrons-protocol-agentGenerates executable Python protocols for Opentrons OT-2 and Flex robots from natural language descriptions.majiayu000operating-enterprise-supportUse when operating enterprise support is required during enterprise product work, especially when the result must be traceable…casioreview20-glitchoperating-saas-supportUse when operating saas support is required during saas product work, especially when the result must be traceable, independently…casioreview20-glitchoperational-modesDefines operational modes for agent work - planning (read-only analysis), editing (full write access), and interactive (guided…majiayu000optimize-agents-mdOptimize AGENTS.md and rules for token efficiency. Auto-invoked when user asks about improving agent instructions, compressing…majiayu000optimize-prompt-goalOptimizes prompts for goal effectiveness - ensures instructions serve the stated goal, prevents missteps, improves efficiency.…majiayu000optimize-prompt-precisionIteratively optimizes prompts for precision - eliminates ambiguities, resolves conflicts, adds missing definitions. Use when…majiayu000optimizing-claude-mdUse when CLAUDE.md is bloated or ineffective. Use when Claude ignores instructions, file exceeds 150 lines, response formatting…majiayu000optimizing-context-budgetUse when optimizing context budget is required during meta work, especially when the result must be traceable, independently…casioreview20-glitchoptimizing-instructionsUse when instruction files (skills, prompts, CLAUDE.md) are too long or need token reduction while preserving capability.majiayu000optimizing-mobile-batteryUse when optimizing mobile battery is required during mobile product work, especially when the result must be traceable…casioreview20-glitchoptimizing-promptsExecute this skill optimizes prompts for large language models (llms) to reduce token usage, lower costs, and improve…majiayu000writesoptuna-hyperparameter-tunerOptuna integration skill for automated hyperparameter optimization with advanced search strategies, pruning, multi-objective…a5c-aiwritesoptuna-study-creatorCreate optuna study creator operations. Auto-activating skill for ML Training. Triggers on: optuna study creator, optuna study…majiayu000writesoptuna-study-creatorOptuna Study Creator - Auto-activating skill for ML Training. Triggers on: optuna study creator, optuna study creator Part of the…majiayu000writesopus-extended-thinkingLeverage Claude Opus 4.5's extended thinking capabilities for deep reasoning, complex analysis, and multi-step synthesis. Use…majiayu000Oracle ADK ExpertBuild production agentic applications on OCI using Oracle Agent Development Kit with multi-agent orchestration, function tools…majiayu000Oracle ADK ExpertBuild production agentic applications on OCI using Oracle Agent Development Kit with multi-agent orchestration, function tools…majiayu000oracleBest practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).majiayu000oracleBest practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).majiayu000oraclecloud-query-transformQuery OCI metrics with MQL and create monitoring alarms via the Python SDK. Use when building dashboards, querying…jeremylongshorewritesoral-argumentPrepare a lawyer for an adversarial proceeding the way Neal Katyal's "Harvey" prepared him for the SCOTUS tariffs argument…lawve-aiorchardcore-ai-a2a-clientSkill for configuring the CrestApps A2A Client feature in Orchard Core. Covers adding remote A2A hosts, authentication, assigning…majiayu000orchardcore-ai-a2a-hostSkill for configuring the CrestApps A2A Host feature in Orchard Core. Covers exposing Agent AI Profiles as A2A agents, host…majiayu000orchardcore-ai-chat-interactionsSkill for configuring AI Chat Interactions in Orchard Core using the CrestApps module. Covers ad-hoc chat sessions, prompt…majiayu000orchardcore-ai-chat-interactionsSkill for configuring AI Chat Interactions in Orchard Core using the CrestApps module. Covers ad-hoc chat sessions, prompt…majiayu000orchardcore-aiSkill for configuring AI integrations in Orchard Core. Covers AI service registration, MCP enablement, prompt configuration, and…majiayu000orchardcore-aiSkill for configuring AI integrations in Orchard Core. Covers AI service registration, MCP enablement, prompt configuration, and…majiayu000orchardcore-ai-mcp-clientSkill for configuring CrestApps MCP client connections in Orchard Core. Covers SSE and Stdio transports, authentication, recipes…majiayu000orchestrateCoordinate focused subagents on substantial work, keep their ownership non-overlapping, and integrate verified results. Use for…sickn33ota-firmware-updateOver-the-air firmware update implementation expertise for embedded systems. Expert skill for delta updates, image signing, update…a5c-aiwritesoutlinesGuarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models…majiayu000output-style-builderCreates structured output formats (JSON/YAML/Markdown-KV/XML) and response style scope configurations via accuracy-token tradeoff…majiayu000output-stylesUnderstanding output styles in Claude Code (deprecated feature). Use when user asks about customizing Claude's behavior, output…majiayu000overnightAutonomous background agent — give it a big coding goal, walk away, come back to a branch of working code. Decomposes, executes…majiayu000p2p-networkingPeer-to-peer networking skill for NAT punch-through and relay servers.a5c-aiwrites用人单位劳动合规公司端劳动用工合规 Skill。用于用人单位日常劳动合规、员工手册/规章制度/劳动合同更新、工资工时问答、内部劳动政策起草,以及公司在解除、调岗、降薪、处罚、员工投诉或仲裁前的风险预判。用户提到公司劳动合规、员工手册、规章制度、薪酬制度、考勤制度、加班费、发薪…pa1nrui1
← Prev42 / 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