Agent skills

Skills matching “agent”

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
1,221 found
1,0091,056 · page 22 / 26
agentic-evalPatterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and…githubagentic-jujutsuQuantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordinationruvnetagentic-osBuild persistent multi-agent operating systems on OpenAI Codex. Covers kernel architecture, specialist agents, slash commands…mturacagentic-workflowsRoute gh-aw workflow design/create/debug/upgrade requests to the right prompts.dotnetagentic-workflowsRoute gh-aw workflow design/create/debug/upgrade requests to the right prompts.githubagentica-claude-proxyGuide for integrating Agentica SDK with Claude Code CLI proxyparcadeiwritesagentica-promptsWrite reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguityparcadeiagentica-sdkBuild Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integrationparcadeiwritesagentica-serverAgentica server + Claude proxy setup - architecture, startup sequence, debuggingparcadeiwritesagentisch-fristen-form-und-zustaendigkeitWenn es um Agentisch: Fristen, Form, Zuständigkeit und Rechtsweg in patentrecherche geht: prüft Frist, Form, Zuständigkeit…Klotzketteagentische-datenbank-rechercheWenn es um agentische-datenbank-recherche in patentrecherche geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und…Klotzketteagentkit-seoRoute broad or ambiguous AgentKit SEO work to the right module while keeping context scoped. Use when a request spans multiple…rohitg00agentlas-auto-activationUse when adding or auditing local runtime behavior that turns a project folder into an Agentlas-aware workspace with .agentlas…agentlas-aiagentlas-core-engine-meta-agentUse when creating a single Agentlas agent, creating a multi-agent team, or packaging an existing local/external agent into…agentlas-aiagentlas-packagingUse when converting, repairing, or packaging an existing local or external agent/team into Agentlas architecture for local…agentlas-aiagentlas-security-scanUse when an agent folder must pass the Agentlas Cloud 2-stage security scan (static rules + BYOK LLM judgment) before private…agentlas-aiagentmailEmail infrastructure for AI agents. Create accounts, send/receive emails, manage webhooks, and check karma balance via the…sickn33agentphoneBuild AI phone agents with AgentPhone API. Use when the user wants to make phone calls, send/receive SMS, manage phone numbers…sickn33agentql-automationAutomate Agentql tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQagentsUse when designing, deploying, or debugging a Butterbase Agent (declarative LLM/tool graph), registering an MCP server for tool…butterbase-aiagents-md-protocolCreate or review an AGENTS.md file so coding agents get stable repo-local policy, and handoff rules. Use when a repo lacks…stevesolunagents-md-reviseCapture learnings from the current session into the project-rules file (AGENTS.md, CLAUDE.md, or local override) so future…waybarriosagents-mdThis skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up…sickn33agents-v2-pyBuild container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted…sickn33agentsop-map-reduce-fanoutDecision protocol for the map-reduce / dynamic fan-out pattern in LM pipelines — "given list L, run f(item) for each item in…agentsopeagentsop-output-format-by-modelPick an LM output format per (task x consumer x model) rather than by reflex: different formats carry different cognitive load…agentsopeagentsop-state-reducerTool skill for declaring reducers on LangGraph state keys so parallel writes merge instead of crashing. Activates whenever a…agentsopeagentur-abnahme-vergabeWenn es um Agentur, Abnahme, Vergabe in Barrierefreiheit Web Checker geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und…Klotzketteagentur-marketing-agbWenn es um Agentur Marketing AGB in AGB-Recht-Prüfer geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und nächsten…KlotzketteagenturmodellWenn es um Wachstum Zusammenarbeit und Rechtsform: Prüft leadagentur in Solo-Selbstständige Praxis geht: prüft Frist, Form…Klotzketteagenturvertrag-exklusivitaet-fotoWenn es um Influencer-Recht: Agenturvertrag – Exklusivität, Provision und Kündigung in Influencer-Recht geht: ordnet Sachverhalt…Klotzketteagenty-automationAutomate Agenty tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQai-agent-designComprehensive guide to designing, building, and operating AI agents. Covers agent architecture, tool use patterns, memory…cosmicstack-labsai-agent-papers-guideCurated 2024-2026 AI agent research papers collectionbrycewang-stanfordai-agents-architectExpert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent…sickn33ai4s-agentUse when the user wants an end-to-end AI4S research pipeline — broad direction or specific topic in, full research package out…ai4s-researchantigravity-agent-managerConfigure and orchestrate parallel agents using the standalone Antigravity 2.0 Agent Manager and Antigravity IDE.sickn33Article Architect and Multi-Agent PlannerGenerates a comprehensive plan and specific instructions for multiple AI agents to collaboratively write an article based on…ECNU-ICALKArticle Architect for Multi-Agent Content GenerationDeconstructs article specifications into detailed, individual prompts for multiple AI agents to write cohesive sections, ensuring…ECNU-ICALKautonomous-agent-harnessTransform OpenAI Codex into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task…mturacautonomous_agent_json_frameworkConfigures an autonomous AI agent to execute tasks efficiently using a strict JSON command interface, comprehensive tool usage…ECNU-ICALKautonomous-agent-patternsDesign patterns for building autonomous coding agents, inspired by [Cline](https://github.com/cline/cline) and [OpenAI…sickn33autonomous-agents-papers-guideDaily-updated collection of autonomous AI agent papersbrycewang-stanfordautonomous-agentsAutonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without…sickn33autonomous_json_agent_with_memory_and_toolsOperates as an autonomous agent with limited short-term memory, utilizing specific commands for web search, memory management…ECNU-ICALKaws-agentic-aiAWS Bedrock AgentCore comprehensive expert for deploying and managing AI agents at scale. Use when working with any AgentCore…sickn33azure-ai-agents-persistent-dotnetAzure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and…microsoftazure-ai-agents-persistent-dotnetAzure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and…sickn33
← Prev22 / 26Next →
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