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...
ferpa-anonymizer
by JJuice22Anonymizes student data in any document or text to ensure FERPA compliance before using it with AI tools, sharing with third parties, or including in professional portfolios. Trigger this skill whenever the user mentions student data, student records, session notes, coaching observations, progress reports, IEP data, assessment results, case studies, or any content that might contain personally identifiable information (PII) about minors or students. Also trigger when the user says "make this FERPA-safe", "anonymize this", "remove student names", "de-identify this document", "can I share this with AI?", or asks whether a document is safe to use in AI tools. Works on pasted text, uploaded .docx, .pdf, .txt, and .xlsx files. Produces a clean anonymized version with a secure local mapping key so pseudonyms stay consistent across a session.
iep-session-notes
by JJuice22Converts raw therapist or teacher session observations, voice memo transcripts, bullet-pointed notes, or stream-of-consciousness logs into structured, legally appropriate IEP progress notes and service documentation. Trigger this skill whenever the user mentions writing up session notes, documenting IEP progress, logging service minutes, recording intervention data, writing progress toward IEP goals, noting student performance in pull-out or push-in services, or any task involving documentation of services for students with disabilities. Also trigger when the user pastes raw observation notes and asks to "clean this up", "turn this into a note", or "write this professionally". Works with pasted text, voice memo transcripts, bullet lists, and uploaded .docx or .txt files. Always anonymize student names before producing output unless the user has confirmed FERPA-safe context.
parent-communication-translator
by JJuice22Rewrites school communications — letters home, progress reports, IEP meeting summaries, discipline notices, policy documents, newsletters, and emails — into plain language that is accessible, culturally responsive, and free of education jargon. Also translates communications for families whose primary language is not English. Trigger this skill whenever the user wants to make a school document more accessible, translate a letter home, simplify a progress report for a parent, rewrite a form in plain language, make an IEP summary understandable to a non-educator, remove jargon from a school communication, or write a parent email that won't alienate families. Also trigger when the user asks "how do I say this to a parent?", "can you make this less scary?", "rewrite this for families", or "translate this to Spanish" (or any other language). Works with pasted text or uploaded .docx files.
student-data-dashboard
by JJuice22Interprets, summarizes, and visualizes student assessment data from any common K-12 assessment tool — DIBELS, iReady, STAR, NWEA MAP, state assessments, progress monitoring probes, benchmark screeners, or teacher-created assessments. Trigger this skill whenever the user pastes or uploads student data, wants to make sense of assessment results, needs to present data to parents or staff, wants to identify students for intervention, asks what the data means, wants a data summary for an IEP or team meeting, needs to track progress over time, or asks about data trends. Also trigger when the user says "help me understand this data", "what does this tell me?", "who needs intervention?", or "how do I explain this to parents?" Works with pasted tables, uploaded .xlsx or .csv files, or verbal descriptions of data. Always applies FERPA anonymization before producing outputs unless user confirms safe context.
substitute-lesson-plan-builder
by JJuice22Generates complete, self-contained substitute lesson plans from any existing lesson, unit, or subject description — with enough detail that a non-specialist substitute teacher can deliver quality instruction without additional support. Trigger this skill whenever the user needs a sub plan, is preparing for an absence, needs emergency lesson plans, wants to leave instructions for a substitute teacher, needs a lesson that can run itself, or asks "what can I leave for a sub?" Also trigger when the user says "I need a sub plan for tomorrow", "I'm going to be absent", "help me write sub plans", or "I need something a sub can do with my class." Works with existing lesson content, a topic description, or just a grade level and subject — even with minimal input, this skill produces a complete, functional plan.
lesson-plan-differentiator
by JJuice22Adds research-based differentiation layers to any existing lesson plan, activity, or assignment using Universal Design for Learning (UDL) principles, MTSS tiered support structures, and evidence-based accommodation strategies. Trigger this skill whenever the user mentions differentiating a lesson, adding accommodations or modifications, making a lesson accessible for all learners, adapting a lesson for IEP students or ELL students or advanced learners, adding scaffolds or extensions, making a lesson UDL-compliant, or asking how to meet the needs of diverse learners. Also trigger when the user pastes a lesson plan and says "help me differentiate this", "make this work for all my kids", "add supports for my struggling students", or "what can I do for my students with IEPs?" Works with pasted lesson plans, uploaded .docx files, or verbal descriptions of a lesson.
rubric-generator
by JJuice22Builds complete, standards-aligned, student-facing rubrics for any assignment, project, essay, presentation, lab report, discussion, or performance task. Trigger this skill whenever the user wants to create a rubric, needs to assess student work, asks how to grade something fairly, wants to build a scoring guide, needs to align an assignment to standards, asks about performance criteria, or wants a tool to give students before they begin an assignment. Also trigger when the user says "build me a rubric for this", "how should I grade this assignment?", "I need criteria for this project", "make a scoring guide", or "how do I make this rubric student- friendly?" Works with pasted assignment descriptions, uploaded .docx files, or verbal descriptions of what students are expected to produce.
science-of-reading-analyzer
by JJuice22Audits any reading lesson, curriculum material, decodable text, leveled reader, instructional strategy, or assessment against the Science of Reading evidence base. Trigger this skill whenever the user asks whether something is Science of Reading-aligned, wants to evaluate a reading program or curriculum, asks about phonics scope and sequence, wants to know if a strategy is evidence-based, mentions balanced literacy vs. structured literacy, asks about Scarborough's Reading Rope or the Simple View of Reading, wants to improve a reading lesson or intervention, or asks whether a text or approach is appropriate for a struggling reader. Also trigger when the user shares a reading lesson or passage and asks "is this good?", "does this follow the Science of Reading?", "what's missing?", or "how should I teach this differently?" Works with pasted lessons, uploaded documents, or verbal descriptions of instructional practice.
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.