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...
provider-adapter-design
by orange-dotApply when adding, changing, or reviewing provider behavior across Gmail (Gmail API), Office 365 (Microsoft Graph), or IMAP/SMTP. Keeps provider-specific protocol details behind src/server/mail/adapters/types.ts MailProviderAdapter. Triggers on edits to src/server/mail/adapters/, src/server/auth/oauth.ts, src/app/api/connect/, src/app/api/mail/.
smoke-path-mail
by orange-dotCanonical smoke path for this project. Mirrors the lab_tools smoke-path contract. `npm run check` is the fast proof; `npm run check && npm run test:e2e` is the heavy proof. Invoked by /mail-smoke and by test-runner.
evidence-bundle
by orange-dotAt the end of a cooperation, gather sources (touched specs + commits + plan artifacts), outputs (logs, test reports, lint), and health checks into .cooperations/evidence/<task-id>/. Mirrors lab_tools/evidence.py EvidenceBundle.
code-reviewer
by orange-dotReview C# .NET 10 code for quality, best practices, Azure Durable-specific rules, and security. Use for code reviews, PR reviews, security audits. Triggers on: review code, code review, PR review, security review, check code quality.
skill-orchestrator
by orange-dotOrchestrate the full implementation workflow: implement -> architecture review -> code review. Use when you need a complete implementation with reviews. Triggers on: full implementation, implement with review, implement and review, complete workflow.
ai-email-triage
by orange-dotApply when changing AI summary, draft, or priority behavior. Keeps Anthropic-path output and deterministic-fallback-path output structurally identical so the UI cannot tell them apart. Triggers on edits to src/server/ai/, src/app/api/ai/.
mobile-pwa-review
by orange-dotApply when changing UI layout, manifest, service worker, icons, theme color, or any path affecting PWA installability and mobile usability. Triggers on edits to src/components/MailApp.tsx, src/app/layout.tsx, src/app/globals.css, public/manifest.webmanifest, public/sw.js, public/icon.svg.
azure-durable-implementer
by orange-dotImplement Azure Durable Functions following opus45design.md architecture. Use for creating orchestrations, activities, entities, event ingress functions, and Service Bus/Cosmos DB integrations. Triggers on: implement, create, build, add function, new orchestration, new activity, new entity.
handoff-discipline
by orange-dotApply at every role transition in a cooperation. Writes a handoff JSON under .cooperations/handoffs/ that mirrors the Handoff struct in workspace/platform/cooperations/internal/types/types.go. No specialist agent may act without a current handoff naming it as ToRole.
arch-reviewer
by orange-dotReview Azure Durable Functions implementations against Modular Monolith principles and opus45design.md architecture. Use for architecture reviews, design validation, scalability assessment. Triggers on: review architecture, arch review, design review, validate architecture, check design.
security-token-review
by orange-dotApply when changing credentials, OAuth, IMAP, env handling, API auth, or any path that touches secrets. Triggers on edits to src/server/security/crypto.ts, src/server/auth/oauth.ts, .env.example, next.config.mjs, src/app/api/connect/.
pipeline-phase
by orange-dotFive-phase pipeline definitions for cooperations, mirroring lab_tools/runner_pipeline.py PHASES and APPROVAL_TRANSITIONS. Defines per-phase role, sandbox, artifact filename, checkpoint gate, and allowed transitions.
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.