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...
add-synonym
by owidAdd search synonyms to the Algolia synonym list. Use when someone wants to add, update, or extend synonym groups for site search.
create-migration
by owidCreate a new database migration file for the OWID MySQL database. Use when the user needs to create a database schema change or migration.
faust-metadata-audit
by owidGenerate a compact Markdown audit of user-facing chart text (Title, Subtitle, Footnote, description_short, description_key — i.e. FAUST) for an MDim, a grapher/garden dataset, or a hand-picked list of indicators. Each field is tagged by source (override / inherited / missing) so the reader can tell what Grapher renders vs. what comes from the ETL metadata. Trigger when the user wants to review, audit, or spot-check the user-facing text of one or many charts/indicators at once — e.g. "audit the FAUST for dataset X", "dump the FAUST for dataset X", "I want to review the text of all views in this MDim", "show me the chart text for these indicators".
etl-profiling
by owidProfile and optimize ETL step performance — CPU time, memory usage, and I/O bottlenecks. Use when an ETL step is slow, uses too much memory, or when the user asks to profile, optimize, or speed up a step. Covers profiling commands, categorical dtype optimization, vectorization, SUBSET filtering for fast dev runs, and iterative diagnose→fix→reprofile workflow.
streamlit-app
by owidCreate or modify Streamlit apps in the Wizard. Use when building new wizard apps, adding Streamlit pages, or working with apps/wizard/ code.
check-metadata-typos
by owidCheck .meta.yml and snapshot .dvc files for spelling typos using codespell. Use when user mentions typos, spelling errors, metadata quality, or wants to check metadata files for mistakes.
fix-dependabot
by owidResolve Dependabot security alerts on owid/etl by upgrading vulnerable dependencies. Use when the user mentions "dependabot", "security alerts", "vulnerability", "CVE", "security fixes", "dependabot alerts", or wants to fix vulnerable packages. Also trigger when the user pastes a GitHub Dependabot URL or asks about outdated/insecure dependencies.
map-explorer-to-mdim
by owidSuggest a redirect mapping from a (soon-to-sunset) OWID explorer's views to the views of one or more replacement MDIMs. Pulls explorer views and MDIM views from the grapher DB, writes a CSV per source/target plus a wide joint proposal that routes each explorer view to a target MDIM view, and flags when several explorer views land on the same MDIM view. Trigger when the user says "map explorer <slug> to mdim(s) <...>", "suggest explorer->MDIM redirects", "we're sunsetting the <slug> explorer, map its views to the new multidims", or similar.
migrate-dataset
by owidMigrate a legacy OWID dataset (no catalogPath) into the ETL pipeline. Use when user wants to migrate, backport, or convert a legacy dataset by ID, or mentions datasets without catalogPath.
migrate-explorer-csv
by owidMigrate a non-ETL CSV-based explorer (data lives in a static CSV hosted in `owid-grapher/public/explorers/` or on GitHub; explorer config has `tableSlug`/`table` blocks) into ETL by adding a snapshot → meadow → garden → grapher chain, then handing off to `/create-explorer` for the export step. Trigger when the user says "bring CSV explorer <slug> into ETL", or refers to fish-stocks (the only remaining target).
migrate-explorer-grapher
by owidTranslate a non-ETL explorer (lives in MySQL `explorers` table; TSV mirrored in `owid-grapher/explorers/`) whose `graphers` block references variable IDs or chart IDs into the inputs `/create-explorer` needs. Resolves IDs to catalog paths, pulls per-chart config when needed, and produces the dimension + view layout. Trigger when the user says "bring <slug> explorer into ETL", "migrate grapher explorer <slug>", or refers to one of: energy, co2, democracy, global-health, food-prices, fertilizers, natural-disasters, food-footprints, plastic-pollution, conflict-data, conflict-data-source, countries-in-conflict-data.
migrate-explorer-indicator-legacy
by owidModernize an explorer step that already exists in this repo but doesn't use the YAML-driven `paths.create_collection(explorer=True)` API yet. Covers two legacy shapes: (A) `data://explorers/<ns>/<v>/<short>` steps that write wide CSV tables for the legacy explorer infra (e.g. poverty_inequality, lis, wid, wb, emdat, monkeypox); (B) `export://explorers/<ns>/latest/<short>` steps that already exist but build the TSV programmatically via `paths.create_explorer_legacy(df_graphers, df_columns)` (minerals, air_pollution, migration/2024-08-05, minerals_supply_and_demand_prospects). This skill extracts the dimensions/views/config from the legacy shape and hands them to `/create-explorer` to write the modern step. Trigger when the user says "migrate indicator-legacy explorer <short>", "convert create_explorer_legacy to create_collection", or "move data://explorers/... to export://explorers/...".
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.