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...
format-table
by 4IRLFormat markdown tables and ASCII box diagrams so all borders align vertically. Use this skill whenever writing, editing, or reviewing a markdown file with tables or box-drawing diagrams (plans, reviews, architecture docs, etc.) to ensure properly aligned columns and consistent line widths. Also use when asked to fix table or diagram formatting.
run-plan
by 4IRLExecute all remaining steps of a plan autonomously in a loop, without pausing between steps. Delegates each step to a subagent that runs the /next-step-taker workflow (execute, validate, review, update tracking). The main agent is purely an orchestrator — it reads the plan, spawns subagents, commits, and loops. Only stops on blockers (test failures, unresolved review findings, design decisions requiring user input) or when the plan is finished. Use when asked to "run the plan", "execute all steps", "finish the plan", "auto-run", or "keep going until done". Argument is the plan name (e.g., "/run-plan splash-modal-prerender").
run-review
by 4IRLExecute all pending TODO items from a review file autonomously in a loop. Delegates each item to a subagent running /next-step-taker in review mode. The main agent is purely an orchestrator — it reads the review, spawns subagents, and loops. Only stops on blockers (test failures, unresolved findings requiring user input) or when all items are done. Use when asked to "run the review", "fix all review items", "work through the review", or "apply all review feedback". Argument is the review name (e.g., "/run-review push-review-refactor-foo") or omit to auto-detect from current branch.
test-failure-logger
by 4IRLAutomatically log test failures to timestamped files in tmp/ directory. Use this skill EVERY TIME a test failure is encountered during development, testing, or CI/CD workflows. Captures test name, timestamp, likely cause analysis, and stack trace snippets. Critical for tracking test failures across feature development and debugging sessions.
ui-test-runner
by 4IRLWhen asked to run UI tests for URLS4IRL, this skill will be used.
apply-plan-review
by 4IRLApply all pending review changes from a review file to its corresponding plan file, one item at a time, with a staff-engineer quality check after each change. Use when asked to apply a review to a plan, update a plan from its review, or work through review feedback on a plan. The plan name is inferred from the argument (e.g., "/apply-plan-review pydantic-integration"). Plan files live at plans/<topic>/<name>.md; review files live at plans/<topic>/reviews/<name>-review.md.
build-vite
by 4IRLBuild Vite in docker container and verify the build passes.
git-changes-summary
by 4IRLSummarize all git changes on the current branch compared to main, including staged/unstaged changes, committed changes, and commit history. Use when asked to "summarize my changes", "what has been changed", "what are the current changes", "what's on this branch", or when returning to the codebase after a break and needing an overview of all branch work.
git-commit
by 4IRLStage and commit changes to git in one workflow with automatic pre-commit hook handling. Use when the user asks to commit changes, create a commit, save work to git, or similar git commit requests. Automatically generates commit messages and handles pre-commit failures by fixing linting/formatting errors.
git-push
by 4IRLReview all unpushed code on the current branch using 7 parallel subagents (Safety & Security, Correctness, Simplicity & Conciseness, Test Coverage, Completeness & Cleanup, Consistency & Style, Integration Risk). Classifies findings as mechanical (auto-fixed via /run-review) or design_decision (presented via AskUserQuestion). Auto-fixes mechanical issues, presents design decisions for user input, re-reviews, then pushes when clean. Creates or updates a GitHub PR after push. Use when asked to push, push code, git push, review-and-push, or create a PR.
gmas
by 4IRLRun the `gmas` workflow — checkout main, pull, fetch -p, and interactively clean up stale local branches. Use when the user says "run gmas", "/gmas", "update main and clean branches", "clean up stale branches", or similar. Presents the candidate list as a multiSelect AskUserQuestion so the user picks which branches to delete (not all-or-nothing).
login-with-playright
by 4IRLWhen needing to login to URLS4IRL, or go to the homepage, then we need to do these tasks.
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.