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...
speech-sdk
by Jellypod-IncHow to use @speech-sdk/core for text-to-speech and multi-speaker conversations across providers. Use this skill whenever the user wants to generate speech audio, convert text to speech, stream TTS output, build a multi-speaker podcast or dialogue, get word-level timestamps / alignment for TTS, clone a voice, control speech speed, swap output format, apply pronunciation rules, or integrate @speech-sdk/core. Also trigger on imports from '@speech-sdk/core' or its subpath exports.
arts-crafts
by Jellypod-IncPlan age-calibrated craft projects for kids ages 2-10 — supply list, step-by-step instructions, safety notes, mess level, prep time, variations, cleanup, and learning connections. Use whenever a teacher or parent asks for a classroom or home craft. Triggers on "craft for pre-k about fall leaves", "easter craft ideas for 2nd grade", "simple paper craft with my 5 year old", "thanksgiving class craft no scissors", "rainy day low-mess craft for 4 year old", "valentine's day craft for 20 second graders", "craft using only construction paper and glue", "mother's day kindergarten craft", "ocean animals 1st grade craft", "15-minute preschool craft", "earth day recycled-materials craft", "what can I make with my 3 year old", and similar K-5 / PreK project requests. Redirects copyrighted-character requests (Elsa, Bluey, Mickey, Pokémon) to the underlying theme. Does not fetch stock photos — uses italicized visual-description cues per step instead.
jellypod-api
by Jellypod-IncHow to use the Jellypod API to create AI-powered podcasts programmatically — creating hosts, uploading sources, generating episodes, and publishing. Use this skill whenever someone wants to build with the Jellypod API, integrate Jellypod into an application, generate podcast content programmatically, automate podcast production, or interact with any Jellypod endpoint. Also use when someone mentions AI podcasts, podcast generation APIs, or turning text into podcast episodes via code.
socratic-tutor
by Jellypod-IncTutors a student through a problem via guiding questions without ever handing over the answer. Triggers on phrases like "help me understand", "I'm stuck on my homework", "tutor me through this", "walk me through how to solve", "explain step by step", "I don't get why", "I need to understand X for my exam", or teacher phrasings like "tutor my 7th grader on fractions, don't just give the answer", "Socratic-style tutor this student". Refuses to complete assignments. Offers hint-ladder mode when the student hits a wall and recap-learnings mode at session end. Calibrates to grade level K-2 through grad school.
concept-map
by Jellypod-IncTurn a topic, chapter, or pasted source into a visual graph — mind maps, concept maps, prerequisite trees, cause-effect networks, taxonomies, process flows, or timelines. Triggers on student phrasings like "mind map of the french revolution", "concept map for photosynthesis", "show me how these ideas relate", "visualize this chapter", "map out the relationships in this reading", "map my notes", and on teacher phrasings like "diagram of this chapter for my 7th graders", "prerequisite tree for calculus", "cause and effect map of WWI", "draw a taxonomy of vertebrates", "flowchart the scientific method", "timeline of the civil rights movement", "markmap of these notes". Emits Mermaid (default), Graphviz DOT, or Markmap syntax plus an optional rendered PNG/SVG via the bundled renderer — falls back to syntax + install hints when renderers are missing. Calibrates node count and vocabulary to grade level.
rubric
by Jellypod-IncTurn an assignment prompt into a ready-to-use grading rubric (a.k.a. scoring guide / grading guide) with zero blank cells. USE THIS SKILL when a teacher, professor, TA, or parent says "I need a rubric for…", "make me a scoring guide", "how should I grade this?", "build an analytic rubric", "holistic rubric for a narrative", "4-point mastery rubric", "rubric aligned to Bloom's / DOK / SOLO / CCSS / NGSS", "turn this assignment into a rubric", "student-facing rubric I can hand out", "grading criteria for [project]", "help me grade this essay", "what should I look for when grading", or "rubric for my kid's homeschool project". Handles K-2 through graduate, analytic or holistic, points or qualitative. Outputs markdown table + CSV with fully populated descriptors in every cell.
circle-time
by Jellypod-IncPlan circle time, morning meeting, or opening routine for PreK-2 classrooms. Use this whenever a teacher asks for a preschool, kindergarten, 1st grade, or 2nd grade morning meeting, greeting, song, calendar/weather, theme discussion, movement activity, story time, SEL check-in, or closing ritual. Triggers on "plan circle time for monday", "morning meeting for kindergarten about feelings", "preschool circle time songs", "what should we do for circle time about fall", "calendar and weather for 1st grade morning meeting", "PreK morning meeting plan for the letter B", "give me a 15 minute circle time about apples", "2nd grade morning meeting SEL check-in", "circle time plan rainy day indoor", "kindergarten greeting song and story", "morning meeting routine for first week of school", "transition songs for preschool circle time", "PreK circle time about community helpers", and similar PreK-2 morning-meeting requests. Produces a full, ready-to-run plan with original lyrics set to public-domain tunes, picture-book su
lesson-plan
by Jellypod-IncOne-shot standards-aligned lesson plans — Common Core, NGSS, TEKS, IB, Cambridge, state frameworks. Takes a topic, grade, and duration; returns a fully formatted plan with objectives, standards, materials, Gradual Release pedagogy (I do / we do / you do), 13 sections, and ELL/SPED/Gifted differentiation. Covers K-12, college, and homeschool. USE THIS SKILL when the user says "write a lesson plan," "I need a lesson on X for Y grade," "plan a lesson," "45-minute lesson on," "Common Core lesson," "NGSS lesson," "emergency sub plan," "homeschool lesson," "multi-day unit," "IB MYP lesson," "first-year-teacher SOS," "TEKS-aligned lesson," or any phrase combining a topic + a grade + a duration. Output: markdown with YAML footer for sibling-skill handoff; optional PDF.
use-speech-sdk
by Jellypod-IncHow to use the @speech-sdk/core library for text-to-speech generation with multiple providers (OpenAI, ElevenLabs). Use this skill whenever the user wants to generate speech audio, convert text to speech, work with TTS providers, use generateSpeech, or integrate speech-sdk into their application. Also trigger when you see imports from '@speech-sdk/core', '@speech-sdk/core/openai', or '@speech-sdk/core/elevenlabs' in the codebase.
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.