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...
audit-render
by thoughtfulllcAudit the browser rendering pipeline for scissor/clipping bypass bugs. Use when touching browser-buffer.ts, canvas-painter.ts, or adding new visual features.
create-component
by thoughtfulllcGuide for creating a new UI component in @gridland/ui. Covers file structure, focus integration, keyboard handling, theme usage, JSDoc, export registration, and documentation.
debug-layout
by thoughtfulllcDiagnose layout issues in Gridland components. Spawns the layout-debugger agent with the relevant component. Use when a component renders incorrectly or layout looks wrong.
review
by thoughtfulllcQuick review of recently changed files. Runs contract-guardian and framework-compliance in parallel. Use after every significant edit before committing.
review-full
by thoughtfulllcFull review of changed files using all 4 agents in parallel — contract-guardian, framework-compliance, docs-mirror, dependency-auditor. Optionally includes layout-debugger for component changes. Run before opening a PR.
review-docs
by thoughtfulllcDocumentation-focused review. Runs docs-mirror and dependency-auditor in parallel. Use after writing or updating documentation, demo components, or MDX pages.
release-check
by thoughtfulllcPre-release checklist. Runs all 4 agents plus snapshot regression test, TypeScript check, and semver confirmation. Run before publishing a new package version.
production-ready
by thoughtfulllcReview a component for production readiness as a UI framework. Assesses code quality, patterns, tests, docs, and API design. Produces a prioritized fix plan. Use before shipping a new or updated component to users.
sync-context
by thoughtfulllcUpdate context files to reflect current codebase state — new components, changed APIs, new patterns, and reasoning behind non-obvious decisions. Routes updates to the correct file based on what changed. Run after any significant design change before committing.
draft-missing-answers
by thoughtfulllcWalk every application markdown file under applications/in-review/, find Q&A sections that are empty, TODO placeholders, or `[partial - pending: ...]` essays whose pending stubs have since been filled, and re-synthesize them using the same gap-analysis + synthesis logic as /find-roles (identity verbatim, essay synthesis from satisfied inputs in the SCHEMA.md checklist). Skip any section with substantive user-revised content, all demographic sections, and any section whose required answer-bank inputs are still stubs. Use after /seed-answer-bank fills stubs that /find-roles generated, to bulk-rewrite the affected applications without touching the user's manual edits.
add-application
by thoughtfulllcAdd a single application by URL. The user pastes one job posting link; the skill fetches the JD, drafts answers from the Answer Bank, and writes one markdown file at applications/in-review/<company>/<ats-id>-<title-slug>.md so it surfaces immediately on the dashboard's Applications page. Auto-adds the company at companies/interested/<slug>.md if it isn't tracked yet. Refuses to duplicate an existing application. Single-target counterpart to /find-roles. Use whenever the user pastes a job URL, says "add this application", "track this job", "draft an application for this", or otherwise names one specific posting they want drafted.
add-company
by thoughtfulllcAdd a single company to the local Companies tree by name (and optional URL), auto-filling HQ, Industry tags, and Remote Policy from research. Writes a new markdown file at companies/interested/<slug>.md. Use whenever the user says "add company X", "track company Y", or otherwise wants to log one specific company they already have in mind. Status defaults to `interested`. This is the lightweight, single-target counterpart to `/find-companies` (which does deep N-company research) — use this when the user names ONE company; use `/find-companies` when they want suggestions / batch research.
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.