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...
t3-vx-apps-integration-workflow
by jackpridhamUse when adding, changing, or debugging T3 Code integration with Vortex app wrappers, especially `vx apps list --json`, `vx apps <target> artifacts ...`, app catalog data, app target IDs, app-scoped server RPCs, NativeApi methods, or UI features driven by configured Vortex apps. Triggers on vx apps, Vortex apps, app catalog, target_id, app wrappers, app-scoped artifacts, `server.listVortexApps`, `server.listVortexAppArtifacts`, or adding app data to navigation/artifacts pages.
t3-vortex-error-workflow
by jackpridhamUse when adding, changing, debugging, reviewing, or displaying vxapp/vortex error handling in T3 Code, especially owner-backed `agents-vxapp` authority failures, websocket RPC error payloads, centralized error enums, sanitized error banners, runtime authority failures, or requests to replace raw stack traces and file paths with stable error codes like `Error 69`. Trigger on vortex error, agents-vxapp error, owner data unavailable, sidebar authority error, error code, centralized error handler, websocket error payload, runtime authority unavailable, wrong role workspace, or graceful error handling for vxapp-backed UI.
t3-readonly-file-viewer-workflow
by jackpridhamUse when adding, changing, or debugging read-only file viewing in T3 Code, especially markdown artifact detail views, absolute artifact paths, NativeApi projects.readFile, workspace read helpers, ChatMarkdown rendering, CodeFileViewer reuse, or deciding whether a new read-only server RPC is needed. Trigger on markdown viewer, artifact content, read file, absolute path, file viewer, ChatMarkdown, CodeFileViewer, or read-only RPC.
t3-tanstack-router-workflow
by jackpridhamUse when adding, changing, debugging, or reviewing TanStack Router file routes in T3 Code, especially nested routes, index routes, route params, routeTree.gen.ts regeneration, standalone route matching, or bugs where a child URL renders the parent page. Trigger on TanStack route, file route, routeTree.gen.ts, Outlet, index route, nested route, route params, or /artifacts-style route work.
t3-artifacts-workflow
by jackpridhamUse when building, changing, or debugging the T3 Code `/artifacts` page, artifact routes, app-scoped artifact lists, chat links to `@Scratch` artifacts, artifact preloading, artifact detail markdown rendering, localStorage artifact caches, artifact slug/title routing, or navigation from the Artifacts group in the hamburger nav sidebar.
t3-cache-ttl-workflow
by jackpridhamUse when adding, changing, or debugging caching in T3 Code, especially SQLite TTL cache rows, `runtime_ttl_cache`, React Query stale/refetch intervals, localStorage preload caches, 5 minute refresh policies, cache invalidation, changed-only refreshes, or deciding whether data should live in SQL, React Query, localStorage, or component state.
t3-composer-suggestions-workflow
by jackpridhamUse when adding, changing, debugging, or reviewing T3 Code chat composer suggestions, ChatView input behavior, @ file mentions, // skill mentions, / slash commands, /model selection, ComposerCommandMenu, ComposerPromptEditor, composer trigger detection, prompt replacement, or keyboard navigation in the composer. Trigger on ChatView composer, composer menu, mention picker, file mention, skill mention, double slash, slash command, model command, prompt editor, Lexical composer, inline composer chip, or `detectComposerTrigger`.
t3-deploy-ui
by jackpridhamUse when the user wants to deploy only T3 Code UI or web-client changes, especially phrases like "deploy ui changes", "deploy web changes", "ship frontend", "redeploy the browser UI", or "publish UI-only changes". This skill is specifically for the local `deploy-web.sh` wrapper and the `deploy.sh --ui-only` flow.
t3-dev-orchestration-tools-workflow
by jackpridhamUse this whenever adding, changing, debugging, or reviewing T3 Code developer-only orchestration controls, debug menus, manual command launchers, local test helpers, or UI surfaces that intentionally send real orchestration commands for dev/test flows. Trigger on `DevOrchestrationMenu`, dev orchestration menu, debug command UI, local-only orchestration tools, developer controls, manual wake/program notification actions, or requests to expose orchestration test/debug actions in the web app.
t3-local-dev-server-workflow
by jackpridhamUse when starting, stopping, restarting, inspecting, or documenting the repo-local T3 Code development server, especially `scripts/dev/dev.sh`, localized dev lifecycle commands, JSON status/log payloads, workspace-scoped runtime state, automatic port selection, root `bun run dev*` scripts, or debugging why local dev startup did not come up on the expected port. Trigger on dev server, local dev server, scripts/dev/dev.sh, start dev, stop dev, restart dev, status --json, list --json, logs --json, dev:web, dev:server, or package.json dev scripts.
t3-local-model-provider-workflow
by jackpridhamUse when adding, changing, debugging, or reviewing T3 Code local-model or self-hosted provider support, especially Ollama, host/IP or endpoint settings, provider-backed model lists, local model defaults, adapter HTTP wiring, provider snapshots, provider picker integration, or live integration tests for local inference backends. Trigger on local model, Ollama, self-hosted model, LAN model server, model endpoint, host/IP, port, API path, provider expansion, add provider kind, local inference, or provider-backed `/model` behavior.
t3-nav-sidebar-workflow
by jackpridhamBuild on or modify the T3 Code hamburger navigation sidebar. Use this whenever the user mentions the nav sidebar, hamburger menu, app navigation menu, grouped settings navigation, sidebar logo/header actions, or asks to add, remove, reorder, style, indent, or route items in the new navigation sheet. This skill keeps agents from dumping route links flat, duplicating project/thread sidebar logic, or bypassing the shared sidebar primitives.
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.