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...
5d-verify
by tapaniaMulti-layer verification of implementation against spec and intent. Use when: (1) After BUILD phase in 5D-SDD workflow, (2) Implementation is complete and needs validation, (3) User asks to 'test,' 'verify,' or 'check' the implementation, (4) Before considering a feature done. This phase catches errors at multiple levels and routes fixes appropriately.
5d-thinking
by tapaniaStrategic multi-dimensional thinking framework for analysis and problem-solving. Use when tasks require: (1) Complex problem analysis, (2) Breaking through mental limitations, (3) Evaluating ideas from multiple perspectives, (4) Understanding root causes, (5) Generating novel insights, (6) Strategic planning, or when the user asks for deep analysis, wisdom, creative solutions, or references '5D thinking,' 'multi-dimensional analysis,' or 'strategic genius' thinking.
5d-tasks
by tapaniaBreak gap analysis into sequenced, actionable tasks. Use when: (1) After GAP ANALYSIS phase in 5D-SDD workflow, (2) User is ready to start implementation, (3) Gaps are identified but not yet organized into work items, (4) User asks for 'task list,' 'breakdown,' or 'what to do first.' This phase creates the implementation roadmap.
5d-build
by tapaniaExecute implementation tasks with quality and awareness. Use when: (1) After TASKS phase in 5D-SDD workflow, (2) Tasks are defined and sequenced, (3) User is ready to write code, (4) User asks to 'implement,' 'build,' or 'code' a task. This phase produces working code while maintaining connection to spec intent.
5d-gap-analysis
by tapaniaAnalyze the gap between current state and specification to identify all required changes. Use when: (1) After SPEC phase in 5D-SDD workflow, (2) Spec exists and implementation is about to begin, (3) User asks 'what needs to change' or 'what's the delta,' (4) Assessing scope of work. This phase prevents surprise discoveries during implementation.
5d-orient
by tapaniaPre-development orientation and assumption mapping for spec-driven development. Use when: (1) Starting a new feature or project, (2) User says 'let's build X' without prior analysis, (3) Beginning any 5D-SDD workflow, (4) User wants to 'think through' an idea before planning. This phase prevents wasted effort by surfacing hidden assumptions and identifying all relevant domains before committing to a direction.
5d-plan
by tapaniaConvert expanded thinking into a concrete, multi-perspective plan. Use when: (1) After SPAR phase in 5D-SDD workflow, (2) User is ready to define what will be built, (3) User asks to 'write up the plan' or 'document what we're building,' (4) Transitioning from exploration to commitment. This phase creates the authoritative description of intent before technical specification.
5d-refine
by tapaniaStress-test the plan through adversarial review and edge case analysis. Use when: (1) After PLAN phase in 5D-SDD workflow, (2) User wants to 'validate,' 'review,' or 'check' a plan, (3) Before committing significant resources to implementation, (4) Plan exists but hasn't been challenged. This phase catches plan-level errors before they become code-level errors.
5d-reflect
by tapaniaExtract learning from completed work to improve future cycles. Use when: (1) After VERIFY phase shows feature complete, (2) End of development iteration, (3) User asks for 'retrospective,' 'lessons learned,' or 'what went well/wrong,' (4) Before starting next major feature. This phase prevents repeating mistakes and compounds learning.
5d-sdd
by tapania5D Spec-Driven Development - A complete methodology for building software through structured phases. Use when: (1) User wants to build something non-trivial, (2) User mentions '5D' or 'spec-driven development,' (3) Starting a new project or feature that needs careful planning, (4) User wants a structured approach to development. This skill orchestrates the full workflow across 10 phases from orientation to reflection.
5d-spar
by tapaniaStructured sparring to challenge and expand thinking before planning. Use when: (1) User has an idea but hasn't stress-tested it, (2) After ORIENT phase in 5D-SDD workflow, (3) User asks to 'think through,' 'challenge,' or 'poke holes' in an idea, (4) User seems certain too early—needs perspective expansion. This phase prevents building the wrong thing by forcing multi-perspective examination.
5d-spec
by tapaniaConvert refined plan into technical specification with architectural decisions. Use when: (1) After REFINE phase in 5D-SDD workflow, (2) User is ready for technical design, (3) Moving from 'what' to 'how,' (4) User asks for 'technical spec,' 'architecture,' or 'design doc.' This phase bridges business intent and implementation detail.
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.