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:
adamtpang
Showing 12 of 18 skills
adamtpang

on-the-shortness-of-life

by adamtpang
star 0

Apply Seneca's audit from On the Shortness of Life — life is long enough if well invested; we make it short by selling our hours cheaply to projects we did not choose. Use when the user is stuck in a routine they did not pick, postponing real work until "later," or unable to say what they spent the last year on. Sourced from De Brevitate Vitae (On the Shortness of Life) by Seneca, §§ 1–3 and 7–10.

navigation main article SKILL.md
schedule Updated 19 days ago
adamtpang

techno-optimism

by adamtpang
star 0

Apply Marc Andreessen's techno-optimist operating philosophy. Evaluate any decision by whether it raises or lowers capability. Distrust framings that lower capability under the pretense of safety. Treat pessimism as a strategy that almost always loses on a 10-year horizon. Use when the user is being pulled into doom narratives, institutional caution that's eating ambition, or a "safety" framing that's actually a capability tax. Sourced from "The Techno-Optimist Manifesto" by Marc Andreessen, a16z.com, October 16, 2023.

navigation main article SKILL.md
schedule Updated 1 month ago
adamtpang

s1-reality-check

by adamtpang
star 0

Apply the S-1 reality check — stress-test whether your company's story survives being read by a hostile stranger looking at the unit economics. Use pre-IPO, on any late-stage startup raising on private narrative, or whenever growth has outrun the company's ability to explain itself to skeptics. The diagnostic that, applied to WeWork in 2017 instead of 2019, would have saved the company. Sourced from The Cult of We by Brown & Farrell, Chapters 12–15, and the actual WeWork S-1 filed August 14, 2019.

navigation main article SKILL.md
schedule Updated 1 month ago
adamtpang

narrative-arbitrage

by adamtpang
star 0

Apply Adam Neumann's narrative arbitrage technique to compress a capital raise — a great story can do the work of a hundred meetings. Use when raising a story-led round (early-stage, category-defining, unit economics still nascent) or evaluating a competitor's pitch that you suspect is narrative-only. Includes the cautionary anti-pattern — every dollar raised on narrative is an IOU to the next round; if economics don't catch up, the lever turns on you. Sourced from The Cult of We by Brown & Farrell, Chapters 8–11.

navigation main article SKILL.md
schedule Updated 1 month ago
adamtpang

franklin

by adamtpang
star 0

Summon Benjamin Franklin's full operating mindset into the current chat. Use whenever the user is working on self-improvement, building a habit-tracking system, starting a mastermind or peer group, designing a routine of moral practice, drafting a public letter, or working through any decision where charm and persuasion matter more than force.

navigation main article SKILL.md
schedule Updated 1 month ago
adamtpang

junto

by adamtpang
star 0

Design a Junto — Benjamin Franklin's structured peer-improvement society from 1727 that produced the first lending library, the first volunteer fire company, the University of Pennsylvania, and a lifetime of compounding relationships. Use when the user wants to start a mastermind, peer group, weekly dinner, founders circle, study group, or any structured network of mutual improvement. Sourced from "The Autobiography of Benjamin Franklin" Part 2 and "Benjamin Franklin: An American Life" by Walter Isaacson, Chapter 5.

navigation main article SKILL.md
schedule Updated 1 month ago
adamtpang

thirteen-virtues

by adamtpang
star 0

Set up Benjamin Franklin's 13 Virtues system — a structured habit-tracking method for moral and behavioral self-improvement. Use when the user wants to build self-discipline, fix a recurring personal flaw, design a habit tracker, run a 13-week improvement program, or operationalize "becoming a better person." Sourced from "The Autobiography of Benjamin Franklin" Part 2.

navigation main article SKILL.md
schedule Updated 1 month ago
adamtpang

dichotomy-of-control

by adamtpang
star 0

Apply Marcus Aurelius's dichotomy of control — separate what is up to you (judgments, intentions, chosen responses) from what is not (outcomes, other people, the past, your body, reputation), and stop staking your peace on the second category. Use when the user is anxious, resentful, spiraling about an outcome they can't move, or distressed by someone else's behavior. Sourced from Meditations, Books 9.6 and 12.26 (the dichotomy, inherited from Epictetus).

navigation main article SKILL.md
schedule Updated 1 month ago
adamtpang

marcus-aurelius

by adamtpang
star 0

Summon Marcus Aurelius's full operating mindset into the current chat. Use whenever the user is anxious, stuck in resentment, wrestling with mortality or vanity, ruminating about what others think, troubled by the body, or asking what they should actually do today. Channels the Stoic operating manual — dichotomy of control, view from above, memento mori, the body as a thing not you.

navigation main article SKILL.md
schedule Updated 1 month ago
adamtpang

memento-mori

by adamtpang
star 0

Apply Marcus Aurelius's memento mori as a priority filter, not as gloom — run the test "if I might be dead by evening, does this still deserve this much of me?" Most grievances do not survive the question; what survives is what matters. Use when the user is procrastinating, nursing a trivial grievance, over-investing in things that won't matter, or has lost the thread of what's important. Sourced from Meditations, Books 2.11 and 4.17.

navigation main article SKILL.md
schedule Updated 1 month ago
adamtpang

view-from-above

by adamtpang
star 0

Apply Marcus Aurelius's "view from above" — deliberately zoom out to the scale of a whole life, the species, and geological time until the emergency is one dot in a vast, ordered thing. The dot still has duties; it loses the right to terror. Use when the user is catastrophizing, in status panic, stung by an offense that feels enormous, or making a decision distorted by being too close to it. Sourced from Meditations, Books 7.48 and 9.30.

navigation main article SKILL.md
schedule Updated 1 month ago
adamtpang

idiot-index

by adamtpang
star 0

Compute Elon Musk's "Idiot Index" — the ratio of a finished item's cost to the cost of its raw materials. A high ratio means you are paying for inefficiency, not value. Use when the user is auditing supplier prices, vendor contracts, build-vs-buy decisions, or any "why does this cost so much" question. Sourced from "Elon Musk" by Walter Isaacson, Chapter 47.

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

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.