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...
leo-writing-voice
by leonardoacostaLeo's writing voice — for Teams/Slack/email drafts, chat replies, and any user-facing prose written on Leo's behalf. Covers register (peer vs stakeholder), cadence (split-send, inline data), Southern-casual greetings, and structural rules. Load this BEFORE drafting any message to a human on Leo's behalf.
svgl
by leonardoacostaFind and embed SVG brand logos from svgl.app when building UI. Use this skill whenever you're creating web interfaces, dashboards, landing pages, wireframes, or HTML artifacts that reference brands, services, or tools (Stripe, GitHub, Vercel, AWS, etc.). Also use when the user mentions SVG logos, brand icons, or asks for professional iconography for known products. This skill replaces emoji and text placeholders with real SVG brand assets. Trigger broadly — if you see a brand name in UI context, this skill applies.
cc-tooling
by leonardoacostaClaude Code tooling standards — MCP server inventory and selection criteria, mermaid diagram rendering (mmdc), skill integration patterns with agent-skill mapping table, and shared config architecture. Use when working with MCP servers, rendering diagrams, managing skills, or configuring shared project settings.
dithering
by leonardoacostaDithering, halftone, and ASCII art rendering patterns for React — retro monochrome effects, Bayer matrices, Floyd-Steinberg error diffusion, ordered dithering, and image-to-ASCII conversion. Use this skill whenever the user wants a retro/CRT/terminal aesthetic, asks to "dither an image", mentions halftone, pixel art, ASCII cards, monochrome photography styling, or wants decorative text-art hero elements and cards. Triggers on: dither, dithered, Bayer, halftone, ASCII art, pixelated, CRT effect, retro terminal, 1-bit aesthetic, black-and-white stippling, `react-ascii-ui`, React Bits Dither, Efecto shaders, Three.js shader art. Also covers the design decision of which approach to pick — drop-in library vs. WebGL shader vs. Canvas 2D — based on whether content is static, interactive, or full-motion. Pull this skill any time the brief mentions retro aesthetic, brutalist design, or decorative art effects.
t3-code-patterns
by leonardoacostaProject-specific code patterns for T3 Turbo monorepo development. Covers DB import patterns, raw SQL column naming (camelCase→snake_case), env vars (POSTGRES_URL not DATABASE_URL), schema path conventions per project, migration workflow (drizzle-kit generate), script placement (package-local vs root, env wiring, turbo task), null narrowing guards, type ownership (db→entities, api→DTOs, app→UI types), Stripe API type checking, Terraform path conventions, and ESLint agent guidance with whitelist decorators.
t3-monorepo-patterns
by leonardoacostaT3 Turbo monorepo patterns for pnpm workspaces, Turborepo task configuration, package extraction, and cross-package type sharing. Use when structuring monorepo packages, configuring Turbo tasks, or managing workspace dependencies.
t3-testing-patterns
by leonardoacostaProject-specific test patterns for T3 Turbo monorepos (vitest unit + playwright e2e). Covers real-DB integration (NEVER vi.mock Drizzle), tRPC createCaller pattern, Stripe SDK fixture strategy, test data builders in testing/ modules, e2e fixture import enforcement (@fixtures/base not @playwright/test), wait strategy hierarchy with concrete timeout table, tag-coverage CI gate, and data isolation by mutation vector. Use when writing vitest tests, playwright specs, or reviewing test PRs in T3 Turbo projects. Triggers: unit test, vitest, vi.mock, createCaller, playwright, e2e, @fixtures, waitFor, test fixture, mock context, coverage threshold.
ai-media-gen
by leonardoacostaGenerate raster images and video from prompts via the ai-cli (Vercel AI Gateway). Use when you need a real raster image or video — hero banners, conceptual illustrations, social cards, mockup imagery, or any pixel/motion asset that mermaid, visual-explainer HTML, excalidraw, or ascii-wireframe (all vector) cannot produce. Also use to generate or compare images across models from the terminal. Triggers on "generate an image", "make a hero image", "render a picture/photo", "create a video", "illustration for the doc".
ascii-wireframe
by leonardoacostaAuthor UI wireframes as Unicode box-drawing TEXT (┌─┐│└┘) that embeds directly into proposal.md, tasks.md, beads issues, and PR/issue bodies — cc's native text medium. Use this skill whenever the request is for a "wireframe", "mockup", "ASCII layout", "box-drawing UI sketch", "text wireframe", "low-fi mockup", "lay out a screen", or any low-fidelity sketch of a UI/page/screen/form/dashboard that should live inside a markdown doc rather than a browser. Trigger broadly — even when the user says "sketch the settings page" or "show me roughly how the checkout flow lays out" without the word "wireframe". Ships a glyph canon (4 border families, 30 component recipes, composition rules) for hand-authoring, plus an optional `scripts/bin/wireframe-render` for spec-driven generation. Do NOT use for rich explanatory HTML diagrams (use `visual-explainer`) or production UI (use `frontend-design`).
autoresearch-loop
by leonardoacostaRun the Karpathy autoresearch ratchet loop on an L2 prose atom (skill, agent, or reference fragment) — synthetic prompts score the candidate, edits KEEP on score gain or REVERT on regression. Use when iteratively optimizing a single .md file behind a frozen eval suite. NOT for L3 orchestrator commands (`/apply:all`, `/p2p`) — see "Out of scope" below.
awesome-design-md
by leonardoacostaCurated DESIGN.md reference files for matching specific brand aesthetics — 66 production brands including Linear, Stripe, Vercel, Apple, Claude, Cursor, Notion, Figma, Tesla, Spotify, OpenAI, Cal.com, Supabase, Framer, Warp, Raycast, and more. Each DESIGN.md is a plain-text design system document describing colors, typography, spacing, motion, and UI conventions in a format AI agents can read and replicate. Use this skill whenever the user asks for UI that should "look like X", "feel like Y", match a specific product's aesthetic, clone a brand's style, or when building an inspired-by design. Triggers on: "make it look like Linear", "Stripe-style checkout", "Vercel vibes", "Apple-style landing", "like Claude's site", brand clone, brand-match, design reference, DESIGN.md, aesthetic target. Pull the relevant DESIGN.md into the workspace and let it guide color/type/spacing decisions rather than improvising.
better-stack
by leonardoacostaBetter Stack MCP triage for production errors, logs, traces, and uptime. Use when (1) a Better Stack alert fires, (2) investigating production errors, slow traces, or log anomalies, (3) checking monitor / incident / heartbeat state, (4) correlating Vercel deploys with telemetry. Triggers on "better stack", "betterstack", "telemetry", "check errors", "check logs", "investigate error", "uptime check", "incident", "heartbeat", or any phrase pointing at production observability after the cutover from Sentry.
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.