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...
anysearch
by PZQ-ship-itReal-time search engine supporting web search, vertical domain search (23 domains), parallel batch search, and URL content extraction.
paper-term-glossary-builder
by PZQ-ship-itBuild beginner-friendly, source-grounded glossaries for academic papers, research PDFs, paper-derived HTML digests, literature review notes, and technical reading workflows. Use when Codex is asked to extract difficult terminology from a paper, explain paper-specific meanings, verify uncertain definitions with web search or AnySearch, create nested prerequisite-term explanations, produce a glossary.md/glossary.html, or help new readers understand dense research jargon.
codex-deep-interview
by PZQ-ship-itUse when a task is ambiguous, underspecified, or likely to branch into multiple valid implementations; clarify intent, constraints, non-goals, and acceptance criteria before planning or editing. Inspired by oh-my-codex deep-interview, adapted for native Codex IDE/VS Code without OMX runtime state.
human-ai-async-work-planner
by PZQ-ship-itPlan what the human should do while Codex or another AI/code agent is running. Use before or during long-running AI tasks, background coding-agent work, tests, builds, rendering, searches, generation, benchmark jobs, or any workflow where the user may have their own queue, hidden context, limited attention, or interruptible tasks to advance asynchronously.
image-to-editable-ppt
by PZQ-ship-it当用户提供一张或多张幻灯片图片、图片版 PPT/PPTX 或 PDF，并要求转成可编辑 PowerPoint/PPTX、重建幻灯片对象、保留页面备注或做可编辑化复刻时使用。
ppt-production-brief
by PZQ-ship-itCreate, review, or freeze the first human-confirmed production brief for a manuscript-to-PPT workflow. Use when Codex must clarify audience, scene preset, rubric or committee expectations, duration, slide count, materials, template policy, assertion-evidence preference, visual policy, editability, QA thresholds, non-goals, or acceptance criteria before any fact grounding, storyboard, asset planning, PPTX generation, or render QA.
ppt-render-qa-loop
by PZQ-ship-itRender a generated PPTX through PowerPoint COM or an approved fallback, inspect screenshots, write a QA report, and stop for human acceptance or repair routing. Use only after a confirmed deck build manifest exists.
scenario-agent-run-optimizer
by PZQ-ship-itAnalyze and optimize a scenario-specific AI agent from runtime logs, traces, eval outputs, system prompts, tool schemas, or failure reports. Use when the user asks Codex to inspect another agent system's behavior, diagnose agent failures, evaluate runs, compare before/after agent traces, find root causes, improve system prompts or tool policies from evidence, or design an optimization loop for non-code or domain-specific agents.
software-engineering-report-reviewer
by PZQ-ship-itReview software engineering reports, graduation project reports, course design reports, and LaTeX/PDF/Markdown drafts for software-engineering document norms. Use when checking whether requirements, problem definition, RQs, architecture, module design, detailed design, implementation, testing, experiments, figures, traceability, and evidence are placed in the right sections and meet common software engineering report expectations.
ai-lab-blog-intel
by PZQ-ship-itCollect, crawl, normalize, and synthesize AI company and laboratory research blog intelligence from first-party RSS/Atom feeds, sitemaps, public HTML indexes, and optional third-party search/API helpers. Use when Codex needs no-required-key monitoring or auditable reports for OpenAI, Anthropic, Google DeepMind, Google Research, Meta AI, Microsoft Research, NVIDIA Research, Apple Machine Learning Research, Allen AI, Stanford HAI, BAIR, MIT CSAIL, CMU ML, or similar fifth-priority "company and lab research blog" channels.
hkust-gz-faculty-intel
by PZQ-ship-itCrawl and integrate HKUST(GZ) public faculty profile data by Hub and one or more Thrust areas. Use when Codex needs to collect faculty lists, emails, titles, profile URLs, identifiers, jobs, acting heads, or optional profile details from facultyprofiles.hkust-gz.edu.cn for selected HKUST(GZ) hubs/thrusts and export normalized JSON/CSV.
ppt-content-fidelity-qa-stage
by PZQ-ship-itVerify source fidelity before deck generation in a manuscript-to-PPT workflow. Use after confirmed production brief, fact ledger, defense narrative, storyboard, speaker notes/rehearsal, defense Q&A/backup plan, asset/layout plan, and any required academic figure prompt exist, and before image generation that depends on the final plan, PPTX generation, or render QA. This stage checks whether slide claims, notes, Q&A answers, backup slides, visual decisions, and generated-visual prompts are grounded in the confirmed fact ledger and must stop for human confirmation or repair routing.
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.