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...
market-status
by dadachundanGoldman-Sachs-Weekly-Kickstart-style market-exuberance dashboard. Scores how much of a late-cycle euphoria the equity market is currently expressing — using the same 9 indicators GS uses to "evaluate exuberance" (Momentum factor returns, S&P 500 52-week market breadth, GS Speculative Trading Indicator, CBOE Put/Call ratio, median short interest, Yale Stock Market Confidence Indices, AAII Investor Sentiment, US IPO count, Net US equity issuance) plus the broader Kickstart dashboard pages (Sentiment Indicator, Financial Conditions Index, fund flows, GDP nowcast, VIX, realized correlation, SPX vs equal-weight, factor & sector returns, top movers, P/E and ERP, top-10 concentration). Each indicator gets a percentile rank vs its own ~30-year history; a single composite Exuberance Score (0–100) maps to a 5-tier verdict (Frothy / Stretched / Elevated / Neutral / Subdued). Produces a 3,000–5,000 word English markdown report mirroring the GS US Weekly Kickstart layout — Verdict box up top, 9-indicator calibration table
zsxq-analyze
by dadachundanAnalyze a PDF stored in db/zsxq.db (the zsxq report library) and answer the user's question about it. Use whenever the user references a zsxq PDF by file_id, filename, or topic keyword — e.g. "what stocks does file_id 184124282514242 recommend?", "summarize the Deloitte report from zsxq", "/zsxq-analyze what does <name> say about robotics". **Also persists any sell-side price-target (PT) calls found in the deep PDF read into `db/stock_price_target.db`** (with `--replace` semantics so the full-text extraction overwrites any prior summary-only row from `/zsxq-recommend`), surfaced in the `/pt` viewer. Pair: `/zsxq-recommend` finds candidate file_ids to feed into this skill.
zsxq-ideas
by dadachundanGenerate investment ideas from the zsxq report library (db/zsxq.db) by combining zsxq-recommend (theme/PDF surfacing) + zsxq-analyze (parallel per-PDF deep reads) + idea-generation (Step-4 presentation). Supports three modes — **themed** ("ideas on AI infra from zsxq", "long humanoid plays from my reports"), **fishing** ("what should I buy", "scan my zsxq feed", "any ideas", "pitch me something from zsxq"), and **theme-build** ("build themes from my zsxq feed", "turn my feed into tracked baskets", "build a theme on X from zsxq") which clusters the feed and seeds/refreshes durable `theme-research` baskets from the actual broker content. Use whenever the user wants stock ideas or tracked thematic baskets sourced from their zsxq library rather than generic quantitative screens. Triggers: "ideas from zsxq", "zsxq ideas", "what stocks does my zsxq feed suggest", "scan zsxq for ideas", "build themes from zsxq", "turn my zsxq feed into baskets", "/zsxq-ideas".
zsxq-recommend
by dadachundanRecommend zsxq reports to read by scanning the most-recent rows of db/zsxq.db (titles + summaries — no PDF parsing). Default: latest 50 reports, focus on AI / robotics. User may override with a count ("latest 100") and/or a subject ("focus on semiconductors", "anything on EVs"). When the user has no clue, group the recent feed into themes and surface a handful of standout reads. **Also persists any sell-side price-target (PT) calls found in the same summaries into `db/stock_price_target.db`** (idempotent via UNIQUE(ticker, broker, file_id)), surfaced in the `/pt` viewer. Pair: hand a returned `file_id` to `/zsxq-analyze` for a deep read.
catalyst-calendar
by dadachundanOne unified catalyst & event lens with three modes. (A) **Day-of brief** — "what's big today/tomorrow" tight 500–1,500 word note covering macro releases (NFP, CPI, PCE, FOMC, ISM, jobless claims, retail sales), earnings (pre/post-market), Fed speakers, M&A milestones (votes, expected closes), index rebalances, options expiry / OPEX, government data releases. Opinionated, actionable, no fluff — written for a 7am desk read. (B) **Week-ahead / horizon calendar** — multi-day catalyst calendar over a coverage universe + weekly preview note (earnings dates, conferences, product launches, regulatory decisions, macro events). (C) **Single-deal M&A monitor** — 3,000–6,000 word English markdown report on one active or proposed M&A transaction (target / acquirer / consideration / spread / milestones / break-risk / probability range), pulling SEC EDGAR (S-4, DEFM14A, 425, 8-K Item 1.01 / 2.01) + jurisdiction antitrust portals; **always confirms target / acquirer direction before writing**. Day-of triggers — "what's big t
earnings-preview
by dadachundanBuild pre-earnings analysis with estimate models, scenario frameworks, and key metrics to watch. Use before a company reports quarterly earnings to prepare positioning notes, set up bull/bear scenarios, and identify what will move the stock. Triggers on "earnings preview", "what to watch for [company] earnings", "pre-earnings", "earnings setup", or "preview Q[X] for [company]".
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.