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...
github-activity-analyzer
by changkunComprehensive GitHub contribution analysis for any time period. Use when user asks about recent work, wants to review their contributions, needs a status update, or requests activity summary. Supports flexible formats: relative time (days/weeks/months/years), full years (2025), specific date ranges (2024-10-01 to 2024-12-31), and from-date-to-today. Provides detailed insights into PRs, commits, code reviews, and technical themes.
wrapup
by changkunFinalize a completed spec — verify all tasks are done, update the parent spec with Outcome and Design Evolution sections, update specs/README.md status, and commit. Use when all tasks in a spec are implemented and the spec needs its completion write-up.
validate-specs
by changkunValidate all specs against the document model rules — check required frontmatter fields, valid status/track/effort values, DAG acyclicity, dispatch consistency, orphan detection, and status consistency. Use to catch structural issues across the spec tree.
status
by changkunReport current status across all specs — what's done, in progress, blocked, and what's next. Reads reality (spec files, task files, git history) instead of relying on manually maintained status tables.
wf-review-impl
by changkunReview an implementation against its spec or task. Check that acceptance criteria are met, no unintended changes were made, and tests cover the requirements. Use after implement-spec or after a task completes.
wf-review-breakdown
by changkunValidate a task breakdown for correctness — check dependency ordering, task sizing, gap coverage, and boundary conflicts. Use after wf-spec-breakdown to catch issues before implementation.
refine
by changkunRefine a spec markdown file by removing already-completed items and updating remaining items to reflect the current project state. Optionally accepts feedback after the file path to guide specific changes (e.g., rewrite scope, change priorities, add/remove items). Use when a spec has drifted from reality and needs to be brought up to date.
implement-spec
by changkunImplement a design spec from specs/ — reads the spec, plans the work, implements each item with tests and docs, then commits. Use when the user says "implement spec", "build spec", or references a spec file to implement.
check-impact
by changkunAnalyze what existing code and specs a proposed change will affect. Use before implementing a spec to understand blast radius, identify risks, and find specs that need updating.
wf-spec-dispatch
by changkunDispatch a validated spec to the task board. Validates prerequisites, resolves dependency wiring, creates the task, and updates the spec's dispatched_task_id atomically. Also supports undispatching (cancel + clear link). Use when a spec is ready for execution.
wf-spec-diff
by changkunCompare a completed task's implementation against its source spec. Produces a structured divergence report — which acceptance criteria were satisfied, which diverged, and what was implemented but unspecified. Appends an Outcome section to the spec. Use after a dispatched task completes.
add-code-comments
by changkunGo through the entire Go codebase, improve code comments, add logic explanations for non-trivial implementations, document uncommented exported symbols, and note any discovered bugs in BUGS.md without fixing them. Uses parallel sub-agents grouped by package area.
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.