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...
generate-pdf
by RonanCodesRender a shareable PDF from a single wiki page or a folder of pages. Minimal print stylesheet — no title page, no TOC unless --toc passed. Renders mermaid diagrams inline. Closes the loop via verify-quick.sh. Used by /generate pdf. Not user-invocable directly — go through /generate.
wiki-templates
by RonanCodesPage type templates and frontmatter conventions for LLM Wiki pages. Reference skill loaded by ingest, query, and lint skills to ensure consistent wiki structure.
generate-podcast
by RonanCodesRender a spoken-word MP3 podcast from wiki pages — single-host by default or two-voice dialogue. Piper TTS default (local, free); falls back to ElevenLabs / OpenAI TTS when their API keys are present. Used by /generate podcast. Not user-invocable directly — go through /generate.
generate-flashcards
by RonanCodesRender an Anki .apkg deck from wiki pages for spaced-repetition study. LLM writes card pairs; genanki packages them. CSV sidecar is the re-ingestable source. Used by /generate flashcards. Not user-invocable directly — go through /generate.
reflect
by RonanCodesCross-cutting synthesis over personal-journal entries. Reads structured frontmatter (mood, energy, weight, sleep, themes, people, wins, drains) plus body content across a date range, surfaces trends and patterns the user can't see day-to-day, and writes a review-YYYY-Qn.md (or weekly/monthly/yearly) page back to the journal vault. Use when the user wants a weekly/monthly/quarterly/yearly reflection, says "what patterns am I seeing", "look at the last month", "give me a year-in-review", or invokes /reflect.
query
by RonanCodesFind pages, look up sources, recall what was ingested, or ask synthesized questions across an LLM Wiki vault. PREFER over bash grep for ANY wiki-content question. Triggers include "find the article on X", "can you find it", "did we ingest Y", "what do we know about Z", "where is W", "show me the page on V", "search the wiki for U".
about-page
by RonanCodesAdd a standard About page to any web app, what it is, the tech stack, and an FAQ, wired into a footer link with a sticky footer. Built with Spartan + Tailwind (the canonical component layer) and falls back to semantic HTML so it ships reliably. Use whenever building, polishing, or shipping an app, every app should have one. Triggers on "add an about page", "about page", "footer about link", or as a standard step in app build/polish.
grill-with-docs
by RonanCodesPREFERRED default grill mode. Grill-mode plus lazy documentation. Runs the grill-me interrogation and, as decisions are reached, writes them into CONTEXT.md (domain language) and docs/adr/000N-*.md (hard-to-reverse decisions) so a fresh agent can pick up cold without re-grilling the user. Use this by default any time a grill is needed; fall back to /ro:grill-me only when the user explicitly wants ephemeral grilling with no durable artefacts. Triggers on "grill me", "let's grill", "/grill" in agent-native repos, "grill with docs", "grill and document", "interview me", "pressure-test this", "before we code", "let's build / make / design / plan / spec", or when the user wants the grill output captured persistently rather than living in the chat transcript.
grill-me
by RonanCodesEphemeral grill mode (no durable artefacts). PREFER /ro:grill-with-docs as the default for ANY grill since it captures CONTEXT.md + ADRs alongside the interrogation. Use /ro:grill-me only when (a) the user explicitly asks for a no-docs grill, or (b) the repo has nowhere sensible to write durable docs (e.g. a throwaway scratch directory). Both skills walk the same decision tree the same way; the only difference is whether decisions get written down. Triggers on "grill me ephemeral", "quick grill no docs". For everyday "grill me / let's build / before we code / pressure-test this / interview me about", grill-with-docs is the default.
new-tanstack-app
by RonanCodesOrchestrate scaffolding a new TanStack Start app on the canonical stack (TanStack Start + Drizzle + Neon Postgres + Cloudflare Workers + shadcn/ui). Dispatches to sub-skills for DB (Neon default; D1 via --db sqlite), auth (Better Auth by default: identity in your own DB, agent-readable, default sign-in = email OTP via Resend (iOS one-tap autofill, no OAuth-app setup), Google + passkeys opt-in; Clerk as the hosted-UI consideration; WorkOS AuthKit at B2B 100K+ MAU; Cloudflare Access for single-user), observability (PostHog, Sentry, UptimeRobot), DNS, ship; plus optional agentic runtime (XState + Vercel AI SDK, LangGraph Phase-2 POA) and Knock notifications. Use when user wants to start, create, scaffold, bootstrap, or kick off a new TanStack Start project / small app / side project.
better-auth
by RonanCodesWire Better Auth into a TanStack Start app. The DEFAULT auth pick (since the Settle build, 2026-06-07) for small SaaS and personal apps: identity tables in your own Postgres so an agent or API can join user to app data (agent-readable), self-issued access tokens / API keys (PAT) for app-to-app and agent access plus OAuth/OIDC for MCP clients later, passwordless email OTP via Resend as the DEFAULT sign-in method (iOS one-tap autofill via autocomplete="one-time-code", no Google Cloud Console / OAuth-app setup), with Google OAuth + passkeys as opt-in add-ons, $0 self-hosted, no vendor lock-in. Clerk (/ro:clerk) is the hosted-UI consideration; WorkOS (/ro:workos) is alt-at-scale for B2B 100K+ MAU. Use when wiring auth, login, or sign-in for a new app, the default auth, email-code or magic-link, Google sign-in, passkeys, owns-the-table, agent-readable identity, personal access tokens, custom auth flows, or EU data residency.
vercel-ai-sdk
by RonanCodesBuild, debug, and tune Vercel AI SDK (v6) code — Core primitives (streamText, generateText, generateObject, streamObject, embed, embedMany, tool() agentic loops, wrapLanguageModel middleware), UI hooks (useChat, useCompletion, useObject), and provider-specific features for Anthropic (prompt caching, extended thinking), OpenAI (reasoning effort, structured outputs), and Google (grounding, thinking budget). Covers the v6 UIMessage parts[] wire protocol, DefaultChatTransport, message persistence, abort/retry, edge-runtime gotchas (Cloudflare Workers process.env), and v5 → v6 migration. Use when the user mentions Vercel AI SDK, `ai` package, useChat, streamText, generateObject, structured output with Zod, agentic tools, prompt caching, AI SDK v6, AI SDK migration, or wires Anthropic/OpenAI/Google through the unified provider interface.
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.