381,784 Collected SKILL.md files

Explore AI Agent Skills & Claude Prompts

Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.

search
expand_more
Active:
ben-mad-jlp
Showing 11 of 11 skills
ben-mad-jlp

vibe-read

by ben-mad-jlp
star 0

Read and display the vibe instructions for the current session

navigation main article SKILL.md
schedule Updated 2 months ago
ben-mad-jlp

worker

by ben-mad-jlp
star 0

Ephemeral per-todo worker — executes one claimed work-graph todo, runs the mechanical acceptance gate, and reports completion. Spawned by the Coordinator daemon; not normally invoked by hand.

navigation main article SKILL.md
schedule Updated 22 days ago
ben-mad-jlp

consult-grok

by ben-mad-jlp
star 0

Consult Grok (xAI) for a second opinion, cross-check reasoning, or explore an idea with a different AI model

navigation main article SKILL.md
schedule Updated 1 month ago
ben-mad-jlp

design-exploration

by ben-mad-jlp
star 0

Explore an open design question from multiple independent creative angles, then synthesize one recommended design. Spawns a diverge→judge→synthesize multi-agent workflow (ground the reality → N distinct concepts in parallel → adversarial judge → one synthesized design doc). Use for UI/UX, architecture, or product design questions where several approaches are viable and you want a creative-yet-buildable recommendation with the reasoning preserved — NOT for a quick decision with an obvious default.

navigation main article SKILL.md
schedule Updated 22 days ago
ben-mad-jlp

executing-plans-bugreview

by ben-mad-jlp
star 0

Systematic bug review of all implementation changes before declaring completion

navigation main article SKILL.md
schedule Updated 2 months ago
ben-mad-jlp

pair-mode

by ben-mad-jlp
star 0

Toggle pair mode on/off for the current vibe session. When on, every behavioral code change requires a before/after diagram approved by the human before writing any code.

navigation main article SKILL.md
schedule Updated 2 months ago
ben-mad-jlp

planner

by ben-mad-jlp
star 0

Per-project Planner — plans the roadmap (as work-graph todos with deps) WITH the human, records decisions/constraints, and on plan-level approval marks todos ready for the Coordinator to execute. The Planner is the only role that promotes todos to ready; the Coordinator daemon never self-promotes.

navigation main article SKILL.md
schedule Updated 21 days ago
ben-mad-jlp

supervisor

by ben-mad-jlp
star 0

A single foreground Claude session that plans per-project roadmaps with the user, spawns approved work as collab sessions, and on a self-scheduling loop reconciles supervised sessions — nudging idle ones with open todos and escalating ones that need a human decision.

navigation main article SKILL.md
schedule Updated 22 days ago
ben-mad-jlp

systematic-debugging

by ben-mad-jlp
star 0

Investigate bugfix items to identify root cause and document findings

navigation main article SKILL.md
schedule Updated 1 month ago
ben-mad-jlp

vibe-review

by ben-mad-jlp
star 0

Run parallel bug and completeness review after vibe-go execution

navigation main article SKILL.md
schedule Updated 1 month ago
ben-mad-jlp

writing-plans

by ben-mad-jlp
star 0

Use when you have a spec or requirements for a multi-step task, before touching code

navigation main article SKILL.md
schedule Updated 2 months ago
Page 1 of 1

Browse Agent Skills by Occupation

23 major groups · 867 SOC occupations

Browse by Category

Explore agent skills organized by their primary use case

SKILLMD / CREATORS AND OCCUPATION CATEGORIES

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.

SEO KNOWLEDGE HUB & TECHNICAL OVERVIEW

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.

8 QUESTIONS

Frequently Asked Questions

A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.