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...
legacy
by RebelliousSmileScans Rust code for edition-specific patterns and deprecated APIs, then migrates to a target edition (2015 → 2018 → 2021 → 2024) or updates breaking crate API changes (tokio 0.x → 1.x, diesel 1.x → 2.x, failure → anyhow/thiserror, futures 0.1 → async/await). Detects extern crate declarations, old module syntax (mod.rs), try!() macro, pre-NLL borrow patterns, and deprecated std APIs. Use when the user says "migrate to Rust 2021", "upgrade edition", "this is old Rust", "update tokio", "replace failure crate", or when rustc produces edition warnings. Do NOT use for dependency management (Cargo), performance optimization (web-optimize), or general refactoring unrelated to Rust edition/API compatibility.
storyboard
by RebelliousSmileIdentifies key visual moments in a chapter and generates detailed illustration briefs (for an artist or an image AI). Use when planning illustrations for a chapter, generating image prompts from narrative content, or building a visual brief from a scene. Do NOT use for writing or correcting chapter text — use write or review instead; do NOT use for defining the writing style — use tone-finder instead.
sniff
by RebelliousSmilePython stack detector. Reads requirements.txt, pyproject.toml, setup.py, Pipfile, and sentinel files (manage.py) to detect the framework (Django, FastAPI, Flask), ORM (Django ORM, SQLAlchemy), and capabilities including ActivityPub federation (activitypub/ module + httpx + cryptography). Uses a three-tier model: capability pivots (Python idioms) are loaded at audit time by /sc-python:audit and never written to disk; perf pivots (for web-optimize), data pivots (for data-optimize), and AP pivots (for ap-optimize) are installed selectively to .claude/rules/07-quality/. Emits a pivot manifeste for use by /sc-python:audit. Reports gaps when a capability is detected but no matching plugin pivot exists. Do NOT use to update a single rule manually — edit it directly instead.
rpg
by RebelliousSmilePrépare le côté MJ d'une campagne de JDR solo dans le coffre Obsidian — écriture de scénarios et préparation de campagne : synopsis, fronts/horloges, PNJ, factions, lieux, prep de session, accroches. Complète `pc` (fiches de personnage-joueur) et `solo-mc` (jeu en direct) : on prépare ici, on joue avec solo-mc. Utiliser quand l'utilisateur invoque /obsidian:rpg avec une intention de scénario ou de prep de campagne. NE PAS utiliser pour jouer en direct (scene/oracle/roll → solo-mc), pour gérer la fiche de PJ (→ pc), ni pour de la fiction narrative non-JDR (→ plugin writing).
diffuse
by RebelliousSmileProduit les éléments de design répétables que le LLM réutilise sans refaire la création graphique. Définit l'élément en forme NEUTRE (consomme le manifeste, vocabulaire fermé), puis rend en HYBRIDE : (1) BASELINE adaptateur interne HTML+CSS (universel, sans pivot) ; (2) PIVOT technique vers sc-<techno>:design-bridge quand présent, pour un rendu natif idiomatique (block pattern WP via sc-php, composant Vue/React via sc-js). Chaque rendu passe sous le gate enforce (lint vert obligatoire avant clôture). Absorbe ex-wireframe, ex-component, ex-export-wordpress.
design-bridge
by RebelliousSmileRéceptacle du pivot design pour PHP/WordPress. Reçoit le spec du contrat de pivot (plugins/design/references/sc-pivot-contract.md) émis par design:enforce ou design:diffuse, et réalise nativement : (1) enforce → linter PHP/WP idiomatique (PHPCS ruleset ou script PHP + wiring pre-commit) dérivant strictement du spec ; (2) diffuse → élément neutre rendu en block pattern WordPress FSE + theme.json. Jamais invoqué directement — uniquement appelé via le pivot de design:enforce/04-pivot ou design:diffuse/03-pivot.
design-bridge
by RebelliousSmileRéceptacle du pivot design pour JavaScript/TypeScript. Reçoit le spec du contrat de pivot (plugins/design/references/sc-pivot-contract.md) émis par design:enforce ou design:diffuse, et réalise nativement : (1) enforce → règle ESLint ou script Node.js validant les classes et tokens CSS, dérivant strictement du spec + wiring pre-commit ; (2) diffuse → élément neutre rendu en composant Vue 3 SFC ou React idiomatique. Jamais invoqué directement — uniquement appelé via le pivot de design:enforce/04-pivot ou design:diffuse/03-pivot.
adjust
by RebelliousSmilePivot de l'entonnoir. Arbitre les incohérences entre maquettes, directions ou pistes issues de destructure (motif dominant gagne ; gate humain sur les cas non tranchables), puis fige le contrat : canonise les tokens, écrit le manifeste components.json (vocabulaire fermé, 2e couche), marque la charte comme figée et bumpe la version. Explicitement rejouable : un re-figeage bumpe la version et déclenche la réconciliation dans enforce.
extract-pdf
by RebelliousSmileMulti-session pipeline for extracting content from large PDF files and distributing it into reference source documents under sources/. Use when importing an existing PDF (rulebook, novel, source document) into a by-game domain (R) across multiple sessions. Do NOT use for web research — use `writing:research` instead; do NOT use for writing new content — use `writing:write` instead. Do NOT use to produce final canon — run `lore-extract` (lore) and `rules-keeper` (rules) on the resulting sources/ files to ventilate into canon/.
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.