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...
workflow-orchestration
by vxcozyDisciplined task execution with planning, verification, and self-improvement loops. Use when starting non-trivial tasks (3+ steps), fixing bugs, building features, refactoring code, or when rigorous execution with quality gates is needed. Includes subagent delegation, lessons tracking, and staff-engineer-level verification.
sanitize
by vxcozyRun a 12-point security audit on a git repo — checks for private keys, API tokens, .env files, config files with secrets, plaintext passwords, RPC URLs with embedded keys, wallet addresses, console.log leaks, .gitignore gaps, and test files with real credentials.
jobs-ive-design-architect
by vxcozyPremium UI/UX design architect with Steve Jobs and Jony Ive's design philosophy. Audits every screen, component, and pixel of an app, then delivers a phased design plan for approval. Use when: "audit the design", "design review", "UI audit", "make this feel premium", "polish the UI", "run the Jobs filter", "check visual consistency", or any request to improve visual quality, spacing, typography, hierarchy, or feel without changing functionality. Does NOT write features or touch functionality. Proposes everything. Implements nothing without approval.
compounder
by vxcozyWeekly review partner that compounds productivity gains over time. Tracks velocity, logs friction, sets next-week targets, recognizes patterns across weeks, and feeds insights back to the audit for the next loop. Use when you want a weekly review, need to identify friction, want to see patterns, or want to update your system map. Part of the architect-system loop. Outputs to system/compounder/week-{date}.md.
analyst
by vxcozySenior engineering analyst for code review, plan review, and automation review. Four-lens review covering architecture, code quality, reliability, and performance, each scored 1-10. Delivers APPROVE, REVISE, or REJECT verdicts. Use when you need a code review, plan review, quality check, or want to verify work before shipping. Part of the architect-system loop. Reads from system/blueprints/ and source code. Outputs to system/reviews/.
architect
by vxcozySolution architect that creates implementation blueprints before building. Maps 2-3 approaches ranked by simplicity, creates phased build plans with rollback points, and checks dependencies. Use when you need to design a solution, create a blueprint, plan before building, or take a task from the audit and need an implementation plan. Part of the architect-system loop. Reads from system/audit-report.md. Outputs to system/blueprints/.
refinery
by vxcozyConvergence loop that iteratively improves work until quality thresholds are met. Scores, diagnoses specific weaknesses, rewrites, re-scores, and repeats until all dimensions reach 8/10 or diminishing returns are detected. Use when you want to refine or iterate on work, after the analyst gives a REVISE verdict, or when output quality is below your bar. Part of the architect-system loop. Outputs to system/refinery-log.md.
audit
by vxcozyProductivity analyst that maps your workflow, scores tasks by time cost and energy drain, and builds a prioritized 4-week automation plan. Use when you want to audit your workflow, figure out what to automate, do a productivity review, identify high-leverage tasks, feel overwhelmed and need to prioritize, or after the compounder surfaces new friction. Part of the architect-system loop. Outputs to system/audit-report.md.
architect-system
by vxcozyMaster orchestrator for the 5-step productivity loop. Runs audit, architect, analyst, refinery, and compounder in sequence or individually. Use when you want to run the full loop, start the system, check system status, resume from where you left off, or run a specific step. Manages state, sequencing, and skill chaining. Supports full loop, single step, resume, and status-only modes.
analyst
by vxcozySenior engineering analyst for code review, plan review, and automation review. Use when: (1) "review this", "analyze the code", "check this plan", (2) After implementation to verify quality, (3) "is this good enough?", (4) Before marking a task complete, (5) Reviewing a blueprint from /architect, (6) Reviewing output from /refinery. Four-lens review: architecture, code quality, reliability, performance. Reads from system/blueprints/ and source code. Outputs to system/reviews/.
architect
by vxcozySolution architect that creates implementation blueprints before building. Use when: (1) "architect this", "design a solution", "blueprint for", (2) Taking a task from the audit report and need an implementation plan, (3) "how should I build this?", "plan before building", (4) Before any non-trivial implementation. Reads from system/audit-report.md. Outputs to system/blueprints/.
architect-system
by vxcozyMaster orchestrator for the 5-step productivity system. Runs the full audit-architect-analyst-refinery-compounder loop or individual steps. Use when: (1) "run the full loop", "start the system", "architect system", (2) "run step N", "run audit", "run architect", (3) "what step am I on?", "system status", "where am I in the loop?", (4) "continue", "resume", "next step". Manages state, sequencing, and skill chaining across all 5 steps.
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.