Explore AI Agent Skills & Claude Prompts
Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.
Enter through keywords, occupations, creators, and GitHub sources to see what kinds of skills are emerging across domains.
Use the same catalog through the API
Connect 381,784 public skills to your own search, analytics, or agent workflow with the REST API.
Querying local SQLite index...
graphhopper
by javimoschGraphHopper routing
pilot-chat
by TeoSlayerSend and receive text messages between agents over the Pilot Protocol network. Use this skill when: 1. You need direct 1:1 communication with another agent 2. You want to ask a question or exchange short text messages 3. You need simple request-response interactions Do NOT use this skill when: - You need to transfer files (use pilot-send-file) - You want to broadcast to multiple agents (use pilot-broadcast) - You need task assignment features (use pilot-task-assign)
pilot-announce-capabilities
by TeoSlayerBroadcast structured capability manifests to the network. Use this skill when: 1. Advertising services, resources, or APIs your agent provides 2. Publishing structured capability metadata (specs, pricing, SLAs) 3. Making your agent discoverable by specific capabilities Do NOT use this skill when: - You only need simple tags (use set-tags in pilot-protocol instead) - You need to discover other agents (use pilot-discover instead) - You need to establish trust (use pilot-trust instead)
pilot-archive
by TeoSlayerIndex and search historical data exchanges, messages, and file transfers over Pilot Protocol. Use this skill when: 1. You need to search through past messages and file transfers 2. You want to maintain searchable history of all agent communications 3. You need to audit or analyze historical data exchange patterns Do NOT use this skill when: - You need real-time data access (use pilot-stream-data instead) - You need active file synchronization (use pilot-sync instead) - You need current inbox messages (use pilotctl inbox directly)
pilot-broadcast
by TeoSlayerPublish messages to all trusted peers on a topic over the Pilot Protocol network. Use this skill when: 1. You need to send an announcement to all trusted agents 2. You want to publish status updates to subscribers 3. You need network-wide notifications or alerts Do NOT use this skill when: - You need private 1:1 messaging (use pilot-chat) - You need to send files (use pilot-send-file) - You want to target specific agents (use pilot-chat)
pilot-certificate
by TeoSlayerIssue and verify Ed25519-signed capability certificates for Pilot Protocol agents. Use this skill when: 1. You need to issue capability proofs or authorization certificates 2. You want to verify agent capabilities using cryptographic signatures 3. You need delegated authorization with time-limited certificates Do NOT use this skill when: - You only need basic trust establishment (use pilotctl trust) - You need long-term credentials (use pilot-keychain) - You're implementing PKI (certificates are capability-based, not identity-based)
pilot-consensus
by TeoSlayerDistributed voting and agreement protocols for multi-agent decision making. Use this skill when: 1. Multiple agents need to agree on a value or decision 2. You need Byzantine fault-tolerant consensus in a swarm 3. You want to coordinate distributed transactions or state changes Do NOT use this skill when: - A single leader can make decisions (use pilot-leader-election) - You only need eventual consistency (use pilot-gossip)
pilot-discover
by TeoSlayerAdvanced agent discovery by tags and status. Use this skill when: 1. Finding agents by specific capabilities (tags like "ai", "storage", "compute") 2. Looking up detailed agent information and metadata 3. Filtering connected peers by tag substring Do NOT use this skill when: - You need to establish trust (use pilot-trust instead) - You need to connect to a known agent (use pilot-connect instead) - You need to visualize the network (use pilot-network-map instead)
pilot-event-log
by TeoSlayerPersistent NDJSON event logging with rotation, compression, and retention policies. Use this skill when: 1. You need persistent storage of event streams 2. You need log rotation and compression for long-term retention 3. You need to audit event history with timestamps 4. You need to export events for external analysis Do NOT use this skill when: - You need real-time event processing (use pilot-event-bus instead) - You need short-term replay (use pilot-event-replay instead) - You need filtered logs (use pilot-event-filter first, then log)
pilot-event-replay
by TeoSlayerRecord and replay event streams for debugging, testing, and audit purposes. Use this skill when: 1. You need to capture event streams for later analysis 2. You need to replay events to test downstream consumers 3. You need to debug event-driven workflows 4. You need to audit event history with timestamps Do NOT use this skill when: - You need real-time event forwarding (use pilot-event-bus instead) - You need long-term storage with rotation (use pilot-event-log instead) - You need filtering before recording (use pilot-event-filter first)
pilot-formation
by TeoSlayerDeploy predefined network topologies (star, ring, mesh, tree) for structured swarms. Use this skill when: 1. You need specific communication patterns (star coordinator, ring consensus) 2. You want to minimize connection overhead with structured topologies 3. You need hierarchical organization (tree) for scaling Do NOT use this skill when: - Ad-hoc peer discovery is sufficient (use pilot-swarm-join) - Topology changes frequently (use dynamic mesh)
pilot-heartbeat-monitor
by TeoSlayerDetect agent failures and trigger automatic task redistribution or re-election. Use this skill when: 1. You need to detect when swarm members become unreachable 2. You want to trigger failover actions on agent failure 3. You need health monitoring for load balancing or leader election Do NOT use this skill when: - Agents can safely fail without recovery (fire-and-forget tasks) - Network partitions are rare and acceptable (use simpler ping checks)
Browse Agent Skills by Occupation
23 major groups · 867 SOC occupations
Browse by Category
Explore agent skills organized by their primary use case
Explore the agent skills ecosystem by occupation and creator
SkillMD is not just a keyword search box. It is an open map that organizes public skills by occupation, creator, and repository, helping you see which workflows, judgment criteria, and domain habits people are writing for AI agents.
Then follow creators and GitHub repositories back to the source: compare the skills a team maintains, whether the repo is active, and how the README frames the work before you open, install, or reuse anything.
Use it three ways: learn an unfamiliar field by occupation, study how creators organize skills, then use source context to decide what is worth opening or reusing.
01 Map a field
Browse 23 occupation groups and 867 SOC roles to learn what skills exist in adjacent domains and how they break down real work.
02 Follow creators
Use creator and repository pages to inspect maintained skill collections, recent updates, and source context before trusting a result.
03 Search with sources
Search 1.7M+ collected skills, then use occupation tags, creators, and GitHub source context to decide what is worth opening.
Start with the occupation map, then follow creators and repositories back to real code. SkillMD helps explain why a skill is worth opening, not only what it is named.
Standardizing Agent Capabilities with SKILL.md and Model Context Protocol (MCP)
In the rapidly evolving landscape of artificial intelligence, LLM agents (Large Language Model agents) have transitioned from simple text predictors to autonomous problem solvers. To orchestrate complex, multi-step agentic workflows, developers require a standardized format to specify agent capabilities, prompt instructions, system rules, and database bindings. This is where SKILL.md and the Model Context Protocol (MCP) have emerged as standard developer paradigms. SkillMD serves as the central directory for indexing, exploring, and sharing these critical agent configurations.
Our open-source registry currently tracks over 1.7 million collected SKILL.md configurations and system prompts. By compiling agent configurations from active developers on GitHub, we bridge the gap between prompt engineering research and production execution. Whether you are building agents with Anthropic's Claude Code, OpenAI's GPT-4, Google's Gemini, or local models using Ollama and LlamaIndex, standardized skill definitions ensure your agents behave predictably across different runtime environments.
What is the Model Context Protocol (MCP)?
The Model Context Protocol (MCP) is an open-source standard designed to connect LLMs to data sources, developer tools, and external environments. MCP establishes a bidirectional communication channel between client applications (like Cursor, Claude Desktop, or custom agent systems) and servers hosting data or capabilities. Standardizing instructions via SKILL.md enables LLMs to query databases, read local files, execute terminal commands, and integrate third-party APIs. SkillMD allows you to find ready-to-run MCP servers and prompt instructions for various occupations and technical tasks.
The Structure of a Professional SKILL.md File
A valid SKILL.md configuration is designed to be easily read by humans and parsed by LLMs. It contains precise system instructions, trigger conditions, required parameters, and execution examples. Below is the typical architectural blueprint of a professional agent skill:
- Metadata & Core Scope: Declares the name of the skill, author details, target models, and a description of the capability.
- Triggers & Intent Detection: Details semantic triggers that help the agent decide when to invoke this skill.
- System Prompts: Explicit system-level instructions that direct the agent's behavior, personality, safety guardrails, and formatting preferences.
- Capabilities & Tools: Lists the files, databases, or APIs the agent must access to complete the tasks.
- Few-Shot Examples: Demonstrates real inputs and outputs, helping the model generalize behavior through in-context learning.
Optimizing Agent Workflows for Modern LLMs
Writing effective agent skills requires deep knowledge of prompt engineering. With the release of advanced reasoning models like Claude 3.5 Sonnet, ChatGPT o1, and DeepSeek-V3, prompt templates must focus on structured thinking. Developers are encouraged to use XML tags (e.g., <thought>, <context>, and <rules>) to isolate execution boundaries. Standardized prompts prevent agents from suffering from context drift, ensuring that long-running tasks remain aligned with the initial system parameters.
Exploring by SOC Occupations and Creator Profiles
What makes SkillMD unique is its taxonomy. Instead of simple text search, we parse and organize files according to the Standard Occupational Classification (SOC) system. This means you can discover skills written for Computer and Mathematical roles, Business and Financial operations, Legal, Design, and and Educational Instruction fields. By tracking creator profiles, developers can study how different teams organize their custom instructions, compare version updates, and fork public configs for specialized enterprise use cases.
SkillMD operates as a high-performance index running on a fast Go backend and a highly responsive Astro SSR frontend. All search queries execute in milliseconds, featuring smart debouncing to prevent multiple API requests while keeping user data secure. Join our community of developers to standardize your AI agent instructions and optimize your LLM prompting workflows today.
Frequently Asked Questions
A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.