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...
mlew-facilitation
by aws-samplesML Enablement Workshop のファシリテーションを行います。「MLEWをはじめる」「ワークショップを始めたい」「次に進んで」などのリクエストで起動し、ワークショップの各ステップを順番にガイドします。プロンプトの実行、進捗管理、事前準備の確認を自動で行います。
titan-nova-mme-migration
by aws-samplesMigrates Python code from Amazon Titan Embeddings models (Titan Text Embedding V2 and Titan Multimodal Embeddings G1) to the Amazon Nova Multimodal Embeddings model (Nova MME) on Amazon Bedrock. Handles all API differences including the new request schema, dimension mapping, client-side text+image fusion workaround, embeddingPurpose optimization, and normalization/binary embedding behavior changes. Use this skill whenever the user mentions: - Migrating from Titan embeddings to Nova embeddings - amazon.titan-embed-text-v2, amazon.titan-embed-image-v1, titan-embed, Titan Text V2, Titan Multimodal G1, or Titan MME in the context of migration - amazon.nova-2-multimodal-embeddings-v1 or Nova MME as a migration target - "update my embeddings model", "switch from Titan to Nova", "upgrade embedding model" - Any code that calls bedrock.invoke_model with a titan-embed model ID Also trigger when the user pastes Titan embedding code and asks how to use Nova instead, even if they don't say "migration" explicitly.
gemini-to-nova
by aws-samplesMigrate Gemini 2.0/2.5/3.x Python code and prompts to Amazon Nova 2 Lite. Use when converting Gemini Python API code (google-genai or google-generativeai SDK) to Nova 2 Lite (boto3 Bedrock Runtime), rewriting Gemini prompts for Nova format, or migrating function calling, structured output, multimodal, or reasoning features from Gemini to Nova.
nova2-prompt
by aws-samplesRewrite and optimize prompts for Amazon Nova 2 Lite. Handles both text/agentic and multimodal use cases (images, video, documents). Applies the correct inference config (temperature, reasoning mode) per use case. For multimodal cases, enforces the critical system-prompt limitation. Use this skill when the user wants to migrate, convert, or optimize a prompt specifically for Nova 2 Lite. Do NOT use this for Nova 1 — use /nova1-prompt instead.
nova1-prompt
by aws-samplesRewrite and optimize prompts for Amazon Nova 1 models (Nova Micro, Lite, Pro, Premier). Use this skill when the user wants to migrate, convert, or optimize a prompt specifically for Nova 1. Do NOT use this for Nova 2 — use /nova2-prompt instead.
nova-migrate
by aws-samplesMigrate an application from any LLM to Amazon Nova 1 or Nova 2 end-to-end. Orchestrates prompt optimization (delegates to /nova1-prompt or /nova2-prompt), captures a baseline from the source model, evaluates the migrated prompt against a task-derived rubric, and runs a refine loop that re-optimizes when Nova regresses against the baseline. Supports user-provided tests (JSONL or YAML), pre-recorded baselines (no API keys needed), or synthetic test generation. Use this skill when a user wants to port an existing prompt or app to Nova and needs confidence that quality is preserved or improved.
text-agent-to-nova-sonic-voice
by aws-samplesMigrate any text-based agent to a Nova Sonic voice agent using Strands BidiAgent. Covers two layers: (1) Frontend — browser WebSocket client with Web Audio API for mic capture and audio playback, (2) Orchestrator — FastAPI + Strands BidiAgent server that takes the text agent's system prompt and tools and runs them as a real-time speech-to-speech agent. TRIGGER when: user wants to add voice to an existing text agent; user asks about converting a chatbot to a Nova Sonic voice agent; user mentions text-to-voice migration, Strands BidiAgent, or Nova Sonic voice agent. SKIP when: user is building a text-only agent; user wants TTS/STT without a live agent loop; user is asking about deployment or infrastructure.
kiro-cli
by aws-samplesSpawn Kiro CLI via background process for code-related tasks. Use when user mentions "kiro", "kiro-cli", or needs to work with code — writing, modifying, reading, analyzing, reviewing, debugging, explaining, or understanding codebases. This includes building features, fixing bugs, refactoring, writing tests, code review, and exploring unfamiliar code.
s3-files
by aws-samplesUpload and share files via Amazon S3 with time-limited pre-signed URLs. Generate download links, create upload pages for receiving files, and manage secure file sharing without exposing S3 buckets publicly.
system-prompt-writer
by aws-samplesThis skill should be used when writing or improving system prompts for AI agents, providing expert guidance based on Anthropic's context engineering principles.
tool-creator
by aws-samplesThis skill should be used when users want to create a new tool for the Strands SDK agent system. It supports creating both agent-as-a-tool (complex agents wrapped as tools) and regular tools (simple function-based tools). Use this skill when users request to create, build, or add a new tool.
readme-generator
by aws-samplesThis skill should be used when users want to create or improve README.md files for their projects. It generates professional documentation following the Deep Insight/Strands SDK style - comprehensive yet focused, with clear structure and practical examples.
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.