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...
debug-performance
by QuantConnectDiagnoses slow QuantConnect Python (.py) and C# (.cs) backtests using the Performance Chart first and Python cProfile only when the chart does not pinpoint the hot function. Trigger phrases: "slow backtest", "high CPU", "algorithm slow", "CPU usage", "RAM usage", "memory usage", "performance chart", "profiling", "bottleneck", "debug performance", "taking too long", "optimize algorithm".
alternative-data
by QuantConnectUse when subscribing to a QuantConnect/LEAN alternative-data class via `AddData<AltClass>(symbol)` and reading the result from `slice` in `OnData`. Triggers — "is this dataset a list or single point per bar", "why does iterating slice[dataset_symbol] fail", "why does .property error on a Quiver/RegAlytics/EODHDEconomicEvents value", missing-attribute errors after `slice[_datasetSymbol]`. Skip when — the dataset is a universe (use alternative-data-universes), Morningstar fundamentals, ETF constituents, or the price feed comes through `AddEquity` / `AddOption` instead of `AddData`.
alternative-data-universes
by QuantConnectUse when selecting a dynamic Equity universe from QuantConnect/LEAN alternative-data classes with `AddUniverse<AltClass>(selector)`. Covers Brain, CoinGecko, EODHD, Quiver Quantitative, and Smart Insider universes. Skip for Morningstar fundamentals, ETF constituents, or pure indicator-driven universes.
debug-algorithm
by QuantConnectDiagnoses QuantConnect Python (.py) and C# (.cs) algorithm failures: runtime exceptions and zero-trade backtests. Invoked by other agents the moment an algorithm throws a runtime error or completes a backtest with 0 orders. Walks an ordered checklist to the root cause without hiding it. Trigger phrases: "runtime error", "stack trace", "0 orders", "no trades", "flat equity curve", "unknown property", "AttributeError", "KeyNotFoundException", "wasn't found in the DataDictionary", "insufficient buying power", "indicator not ready", "debug the algorithm".
debug-performance
by QuantConnectDiagnoses slow QuantConnect Python (.py) and C# (.cs) backtests using the Performance Chart first and Python cProfile only when the chart does not pinpoint the hot function. Trigger phrases: "slow backtest", "high CPU", "algorithm slow", "CPU usage", "RAM usage", "memory usage", "performance chart", "profiling", "bottleneck", "debug performance", "taking too long", "optimize algorithm".
indicator-universes
by QuantConnectUse when selecting a QuantConnect/LEAN universe based on per-symbol indicators. Triggers — code uses `AddUniverse(...)` with a selection callback that builds per-symbol `SimpleMovingAverage`/`ExponentialMovingAverage`/`BollingerBands`/`RSI`/`ATR` etc., often via a `SelectionData` class kept in a per-symbol dict; questions like "rank stocks by 21-day SMA", "top N most volatile crypto pairs", "fundamentals universe with momentum filter", "why does my SMA spike around splits/dividends", "why does my universe shrink during warm-up", "how do I avoid history calls in universe selection". Skip when — universe doesn't need per-symbol indicators (use plain fundamentals/ETF/CryptoUniverse selection).
notifications
by QuantConnectUse when a QuantConnect/LEAN live algorithm sends data out or receives external instructions. Triggers — code uses `Notify.Email`/`Notify.Sms`/`Notify.Telegram`/`Notify.Web`/`Notify.Ftp`/`Notify.Sftp`, `SignalExport.*`, `OnCommand`, `AddCommand`, `BroadcastCommand`, `Link()`, or a class implementing `ISignalExportTarget` / `Command`; phrases like "Discord/Slack alert on fills", "email on drawdown", "push portfolio targets to our endpoint", "custom signal export to my broker", "manual liquidate from outside", "parent algo signals child", "multi-algorithm arbitrage". Skip when — purely in-algo log/debug (use `logging` skill).
logging
by QuantConnectUse when adding or reviewing logging in a QuantConnect/LEAN algorithm. Triggers — code uses `Log`, `Debug`, `Error`, `Quit`; questions like "why are my logs missing", "log quota exceeded", "too many log lines per bar", "how do I log every fill", "where do my prints go", "save backtest data for Research analysis", "log spam in `OnData` / inside loops". Skip when — goal is sending alerts out of the algo (email/SMS/webhook → `notifications` skill).
scheduled-events
by QuantConnectUse when adding or reviewing Scheduled Events in a QuantConnect/LEAN algorithm. Triggers — code uses `Schedule.On(...)`, `DateRules.*`, `TimeRules.*`; questions like "rebalance weekly/monthly", "fire at 8am ET", "why is my rebalance using yesterday's universe", "schedule 15 min before close", "daily Crypto rebalance at midnight UTC", "why does my hourly schedule fire at the wrong time", "multi-asset rebalance across time zones". Skip when — scheduling indicator updates (those route through universe selection or `PlotIndicator`, not `Schedule.On`).
chained-universes-options
by QuantConnectUse when chaining a dynamic Equity universe (Fundamental or ETF constituents) with an Equity Option universe in a QuantConnect/LEAN algorithm. Triggers — code that wants Option contracts on top of a moving equity universe via `AddUniverseOptions(universe, filter)`; questions like "how do I add options on top of my fundamental universe", "options on the top-N PE-ratio stocks", "QQQ constituents with their front-month calls", "why are my option strikes wrong after a stock split", "where do I react to option contracts joining/leaving the chain". Skip when — single static Option universe (call `AddOption` once in `Initialize`) or a non-Options chain (use the alternative-data chain pattern).
fundamental-universes
by QuantConnectUse when selecting or screening a QuantConnect/LEAN Equity universe on Morningstar fundamentals — the `AddUniverse(...)` pattern, the `Fundamental` object and how its data is organized, period accessors for `MultiPeriodField` values, and year-over-year deltas. Covers the Piotroski F-Score, Altman Z-score, Magic Formula, Graham filters, and custom screens. For the exact path of any field, it points to the equity-fundamental-data skill. Skip when — the universe is index/ETF-constituent only (`Universe.ETF(...)`).
alternative-data
by QuantConnectUse when subscribing to a QuantConnect/LEAN alternative-data class via `add_data(<AltClass>, symbol)` and reading the result from `slice` in `on_data`. Triggers — "is this dataset a list or single point per bar", "why does iterating slice[dataset_symbol] fail", "why does .property error on a Quiver/RegAlytics/EODHDEconomicEvents value", missing-attribute errors after `slice[dataset_symbol]`. Skip when — the dataset is a universe (use alternative-data-universes), Morningstar fundamentals, ETF constituents, or the price feed comes through `add_equity` / `add_option` instead of `add_data`.
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.