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...
nvidia-developer-firehose
by ssurmicReal-time AI-ECOSYSTEM firehose (v3 multi-source, May 2026). Polls 12 Atom/RSS feeds every 30 min: NVIDIA (developer-blog + main-blog + newsroom), hyperscalers (Azure, AWS, AWS-ML, Meta-Engineering), AI labs (OpenAI, DeepMind, Hugging Face), and neoclouds (CoreWeave, Together AI). For each new post, uses HEURISTIC EXTRACTION + yfinance.Search to auto-resolve every mentioned company → US ticker (no hand-maintained name→ticker dict), with a persistent ticker cache that learns over time. Surfaces names via Telegram tagged by source, separated into 🎯 portfolio-tracked tickers vs 🔍 newly discovered tickers. Why it matters: hyperscalers + NVIDIA + AI labs publicly name 800V HVDC, CPO, optical, power, and custom-silicon partners — the forward-looking design ecosystem that re-rates weeks later when sell-side picks it up. (AMD has no public RSS — covered separately by SEC 8-K strategic-partner-firehose.) Triggers in English ("nvidia developer firehose", "ai ecosystem firehose", "ai partner monitor", "hyperscaler blog
narrative-reversal-screen
by ssurmicScreens for "narrative reversal" candidates — stocks down 30%+ from 52W high with concrete catalyst still intact, worst-case priced in, early reversal signal (first higher low, 50DMA cross, insider buying after capitulation). Returns top 3 with entry plan. Triggers in English ("beaten-down stocks with thesis", "find reversal plays", "stocks at bottom that can recover", "fallen angel screen", "comeback candidates") or Chinese ("找暴跌反转股", "找回归类股票", "ORCL 那种反转", "已经跌透的好股", "底部反弹候选").
strategic-partner-firehose
by ssurmicReal-time SEC 8-K + SC 13D strategic-partner monitor. Detects PIPE deals, joint ventures, and strategic investments from Tier-1 corporate names (NVIDIA, Microsoft, SK Telecom, Samsung, TSMC, Oracle) and sovereign wealth funds (MGX, Saudi PIF, Mubadala, Temasek) BEFORE Substack/Twitter covers them. Filters: US-listed only, market cap ≥ $50M, deal size ≥ $50M. Auto-scores 0-10 ("Strategic Partner Score") via the same enrichment pipeline as insider-firehose. Triggers in English ("strategic investor", "8-K partnership", "find next PENG", "PIPE deal", "13D filing") or Chinese ("战略投资人", "8-K 合作公告", "找下一个 PENG", "PIPE 增发", "13D 申报").
13f-firehose
by ssurmicDaily monitor for new 13F-HR filings from famous funds. Telegram alerts with NEW/ADDED/CLOSED diff vs. prior quarter.
macro-warning
by ssurmicDaily batch-mode macro pullback / warning radar. Checks valuation extremes (NDX/QQQ Forward PE), volatility (VIX/MOVE), sentiment (CNN F&G, AAII), credit spreads (HY OAS), market internals (% above 200DMA, breadth), yen carry (USD/JPY), yield curve, and 11-sector rotation. Outputs Red/Yellow/Green regime + specific positioning advice. Designed for daily 5pm ET (post-close) or 8am ET (pre-open) batch runs via /schedule. Triggers in English ("macro warning", "regime check", "is the market at peak", "should I take profits", "is it time to buy") or Chinese ("宏观警报", "市场是不是顶了", "该不该减仓", "regime 怎么样", "该入场吗").
find-untapped-thesis
by ssurmicScreens for "未爆发 / undiscovered" stocks within a theme — low Forward P/E, lagging 1Y returns vs leaders, real catalyst (concrete contracts not just narrative), low institutional ownership room for re-rating. Returns top 3 candidates with entry plan. Triggers in English ("find undervalued in X", "find next big winner in Y", "what's underrated in Z", "screen for theme X", "show me cheap names in Y") or Chinese ("找未爆发的 X 股", "X 板块还有什么便宜的", "未涨过的 Y", "下一个 NOK", "X 主题筛选").
portfolio-audit
by ssurmicComprehensive portfolio risk audit. Computes single-name concentration, factor cluster exposure, leverage ETF decay risk, options Greeks aggregation, stress test scenarios (-10% SPX, yen carry, single-name miss), hedge effectiveness. Outputs explicit trim list with $ amounts and reasons + cash target. Triggers in English ("review my portfolio", "audit my book", "am I too concentrated", "what should I trim", "portfolio risk check") or Chinese ("审一下我的组合", "我组合风险大吗", "该减什么仓", "组合审计", "我哪里太集中").
tax-optimize
by ssurmicCalculate optimal trim strategy with tax math. Compares Sell-Now (STCG/LTCG depending on holding period) vs Wait-for-LTCG vs Hedge-with-Puts (no taxable event). Computes lot identification (FIFO/HIFO/Specific Lot), tax loss harvesting opportunities. Asks for shares + buy date + income bracket + state. Triggers in English ("should I sell X for tax", "tax on selling X", "LTCG vs STCG on X", "trim X tax efficient") or Chinese ("X 减仓税务", "X 卖出税多少", "现在卖还是等长期", "X 减仓最省税").
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.