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...
acestep
by EnconvoUse ACE-Step API to generate music, edit songs, and remix music. Supports text-to-music, lyrics generation, audio continuation, and audio repainting. Use this skill when users mention generating music, creating songs, music production, remix, or audio continuation.
voicebox
by EnconvoText-to-speech voice toolkit. DEFAULT ACTION: When called with text (e.g. /voicebox hello), IMMEDIATELY run: uv run $SKILL_DIR/scripts/voicebox.py generate "Calm Narrator" "<text>" --play. Do NOT ask questions, do NOT greet the user — just generate and play the speech. Also supports: voice cloning, multi-speaker conversations, recording, and transcription.
multi-style-web-design
by EnconvoStudio-grade single-page web design with **swappable design shells across 16+ styles** (auto-picked by industry or manually chosen) and an opt-in **3D / motion / special-effects toolkit** (depth displacement, tilt+sheen, glass refraction, volumetric slices, light caustics, particle samplers, three.js on demand). Designs with the taste of a tier-1 studio (Apple / Pentagram / Bureau Borsche / Linear / Vercel / Aesop / Klim / Order / MSCHF). Picks aesthetic direction BEFORE writing code, pulls palette from the actual subject, ships portable single-folder static sites with built-in navigation (3 tiers), 7-language i18n via [data-i18n] slots, and zero build step. Use for personal brand sites, founder portfolios, product landings, company about pages, launch teasers, lookbooks, lesson microsites, annual reports, or any one-page site — or when the user asks for "fancy website", "multi-style website", "3D website", "Apple-style depth", "portrait website", "product landing", "brand site", "公司官网", "产品落地页", or provides
spark-tts
by EnconvoGenerate speech from text using iFlytek's Spark TTS model locally on Apple Silicon via mlx-audio. Supports Chinese and English with controllable gender, pitch, and speed. Also supports voice cloning from a 3-second reference audio clip. Use when: user asks to "generate Chinese speech", "中文语音合成", "TTS in Chinese", "spark tts", "clone my voice", "read this in Chinese", or needs Chinese text-to-speech locally. Preferred over Voxtral for Chinese/CJK content. Lightweight 0.5B model (~1GB).
ai-tutor
by EnconvoReal-person tutor mode for any topic. Plans a stepped curriculum, actively drives the learning surface (web pages via browser-use, native macOS apps via computer-use), and teaches by *pointing at the real screen* — not by dumping textbook walls of text. Speaks in short conversational turns sized for TTS, asks eye-exercises after each concept, opens the matching Obsidian deep-dive note one step at a time, and logs the full curriculum into the user's Obsidian vault for later self-study. Use when the user says "teach me X", "be my tutor", "walk me through X like I'm a newbie", "tutor mode", "/ai-tutor", or hands you a live app/webpage and asks you to teach against it.
self-improvement
by EnconvoCaptures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
lux-fashion-advisor
by EnconvoTeam-wide luxury fashion advisor. Reads any agent's profile (IDENTITY.md + MEMORY.md), cross-references SS26 runway intelligence, decides what to wear based on day of week + time of day + occasion, then builds the optimised generation prompt. Activates when user says 'what should I wear', 'fashion advice', 'style me', 'outfit today', 'plan my outfit', 'consult luxury brands', 'selfie', or any portrait request. Covers ALL occasions — work, social, travel, holiday, morning through late night. Each agent reads their own workspace. When no occasion or day is specified, the agent makes its own decision based on current day, time, and season.
grok-video-gen
by EnconvoGenerate videos using Grok AI via Chrome browser automation. Supports T2V (text-to-video) and I2V (image-to-video) with reference image uploads. Uses grok.com/imagine. Use when user says "Grok video", "create video with Grok", or wants AI video generation through Grok.
mtv-maker
by EnconvoFull end-to-end MTV music video creator. From a song concept and optional character reference photo, produces a complete cinematic MTV: (1) writes lyrics and generates music with ACE-Step, (2) generates cinematic scene images, (3) animates with I2V (Grok/Seedance), (4) assembles clips with audio and crossfade transitions, (5) transcribes audio for accurate lyric timing, (6) burns synced lyric subtitles + opening/ending credits with branding. Use when user says "make an MTV", "create a music video", "generate MTV", "/mtv", or describes a song they want turned into a full visual music video.
screen-to-promo
by EnconvoTurn screen recordings into polished videos — marketing promos, user guides, product demos, and more. Goal-aware pipeline: detects user intent, selects strategy, recommends a plan, then executes. Full pipeline: intent detection → strategy selection → source analysis → storyboard planning → source prep → VO generation → frame-by-frame compositing → audio mixing → final encode. Supports animated presenters (AI animal/character with rembg cutout), per-word caption sync (pop, karaoke, static styles), multi-zoom animations, overlay dissolve transitions, time-mapped VO-to-source sync, CJK-aware captions, and letterbox-aware cropping. Use when: (1) user has screen recordings and wants a polished video — marketing, tutorial, demo, or changelog, (2) user says "make a promo video", "tutorial from this recording", "TikTok video", "marketing video", "user guide", "highlight reel", (3) user provides .mov/.mp4 screen recordings to turn into any kind of video with narration and captions.
video-creativity
by EnconvoTier-1 creative agency for end-to-end video production. Owns creative direction, scriptwriting, rich-media generation (T2I/I2I/T2V/I2V), music, word-synced captions, HyperFrames rendering, and QA — delivers a broadcast-quality MP4. Use when user says "make me a video", "product reel", "brand film", "60-second explainer", "cinematic intro". User describes the idea; this skill owns the rest. Never ships AI-slop.
video-prompt-enhancer
by EnconvoTransform simple video prompts into cinematic, structured prompts for AI video generation (Veo 3, Seedance, Grok, Kling, Runway, etc). Adds real camera/lens specs, camera movement, and anti-AI directives without overriding creative intent. Use when: user says 'enhance video prompt', 'make video realistic', 'video prompt', or when a basic video prompt needs upgrading.
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.