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...
doc-gen
by IsaiaScopeGenerate and maintain project documentation — README files, CLAUDE.md guides, docs/ architecture guides, Playwright screenshots, and ASCII/Mermaid diagrams for the AllOnFire monorepo. Use when asked to "generate docs", "create README", "update documentation", "refresh screenshots", "audit docs", "document this feature", "add docs", or "doc-gen".
doc-update
by IsaiaScopeRun a documentation audit for MonorepoOnFire. Verifies all READMEs and doc/ guides against the actual codebase — scripts, routes, schemas, exports, env vars, middleware, CI workflows. Use after code changes or when running /doc-update.
iso-ai-init
by IsaiaScopeInitialize AI defaults. Global steps run anywhere — install/verify caveman (ultra + shrink + statusline) and shrink any allowlisted MCP server that is present and stdio-launchable. Repo-scoped steps (graphify CLI install + /graphify wiring) run only inside a git repo. A gate decides which steps apply. Use when the user runs /iso-ai-init or asks to set up AI tooling.
iso-init-repo
by IsaiaScopeSet up a repo with IsaiaScope governance defaults — GitHub repo creation, prod/test/dev branch structure with protection, prod-gate CI, commitlint, version-bump hook, and /deploy-cascade command. Use when the user runs /iso-init-repo or asks to set up repo governance.
iso-plan
by IsaiaScopePlanning-only chain. Runs brainstorming → grill-with-docs → (prototype, only when needed) → writing-plans in order, then renders a visual summary of the finished plan file. No state, no implementation. Use when the user runs /iso-plan, optionally with a seed idea as the argument.
iso-readme
by IsaiaScopeWrite or refine README files in the IsaiaScope house style — curated shieldcn (shadcn-styled) badges, context-aware layout (repo root/app · skill · lib/pkg), scannable prose — then commit only the README changes and push. Global, stack-agnostic (node, python, rust, go, docs-only, monorepo). Use when invoked as /iso-readme [path], or asked to write/refine/beautify a README in my style.
iso-review
by IsaiaScopeReview the uncommitted working tree. By default spawns codex /review and claude /code-review in two visible herdr tabs; with --codex-only, spawns only codex. Merges and de-duplicates findings in the main session, applies every fix except the net-negative ones via a fix tab (codex by default, claude via --fix-agent, or an existing tab via --fix-term) that then runs the project's tests and type-check — leaving all changes uncommitted. Use when invoked as /iso-review [--codex-only] [--claude-review-effort high|max] [--fix-agent codex|claude] [--fix-term TERM] [--kill-tabs], or asked to review-and-fix the current uncommitted changes.
iso-spawn
by IsaiaScopeSpawn a codex or claude agent in its own herdr tab inside the SAME workspace where the skill runs, with full permissions and an optional auto-running prompt. Use when the user wants to spawn/open/launch a codex or claude tab/agent/panel in the current herdr workspace, dispatch a task to a sub-agent beside the current session, or says "spawn codex", "open a claude tab", "/iso-spawn", "launch an agent here".
iso-todo
by IsaiaScopeRun a full development cycle — plan, then implement, then review — as one hands-off chain. Invoked as /iso-todo [--codex-only] [seed]. The parent session plans with iso-plan, spawns a codex implementation tab to run iso-write on a fresh feat/<slug> branch, keeps that tab alive, runs iso-review over the resulting uncommitted diff with reviewer tabs killed after recovery, and reuses the implementation tab for accepted fixes. With --codex-only, review skips Claude. Commits nothing. Use when the user runs /iso-todo, or asks to take an idea all the way from plan to implemented-and-reviewed without committing.
iso-write
by IsaiaScopeImplement a written plan using TDD, without committing. Use when invoked as /iso-write <plan_path> [--no-branch | --branch=<name> | --worktree] or handed an implementation plan to build. Default creates a fresh branch from the plan filename; --no-branch implements on the current branch; --branch=<name> uses a named branch; --worktree runs in an isolated worktree. Delegates execution to superpowers executing-plans (red-green-refactor per task), stamps the plan done, and stops so the user reviews all changes before any commit. Agent-independent (Claude Code or Codex).
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.