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...
bms
by bmsuisseMaster skill for the bmsuisse platform — routes to the relevant skills based on sub-command. Always enables caveman communication style. Use /bms for core guidelines (SQL + Python + TypeScript + glossary), /bms sql for SQL + Databricks optimization, /bms python for Python + autotuner, /bms data for dimensional modeling + Fabricks. Trigger on: "/bms", "/bms sql", "/bms python", "/bms data", "bmsuisse mode", "activate bms".
data-modeling-dimensional
by bmsuisseDimensional data modeling guide for the Fabricks platform — covers the full pipeline from staging through raw, transf, core, and semantic layers; fact and dimension table design; key strategy; SCD types; bridge tables; degenerate dimensions; and config. Use whenever designing or reviewing fact/dimension tables, deciding where logic belongs in the pipeline, choosing SCD1/SCD2, constructing business/surrogate keys, modeling many-to-many relationships, or understanding layer architecture. Trigger on: "design fact table", "design dimension", "SCD type", "slowly changing dimension", "surrogate key", "business key", "bridge table", "layer architecture", "transf vs core", "udf_identity", "udf_key", "__valid_from", "__is_current", "new dim table", "new fact table", "data model", "bronze", "silver", "gold", "semantic layer", "staging".
fabricks-glossary
by bmsuisseUse this skill whenever company-specific jargon, acronyms, or domain terminology is needed to answer correctly.
fabricks-sql-analyzer
by bmsuisseAnalyzes all SQL files in the Fabricks.Runtime repository, builds a dependency DAG, runs performance heuristics, and produces a Markdown report with ranked findings and improvement suggestions. Optionally fetches row counts and EXPLAIN COST plans from Databricks. Pass --fix to automatically create a branch and apply SQL rewrites.
kendo-ui-vue
by bmsuisseUse this skill whenever the user is working with Kendo UI for Vue — including the Data Grid, DropDownList, ComboBox, AutoComplete, or any @progress/kendo-vue-* package. Covers server-side paging/filtering/sorting, inline CRUD editing, row selection, custom cell templates, master-detail rows, grouping, Excel export, and virtualization for large datasets. Trigger on any mention of kendo grid, telerik vue, @progress/kendo-vue-grid, or when the user is building a sortable/filterable/pageable data table in Vue. Also trigger when a user asks about adding editing, export, or selection to an existing Kendo grid.
kendo-ui-angular
by bmsuisseUse this skill whenever the user is working with Kendo UI for Angular — including the Data Grid, TreeList, TreeView, DropDownList, AutoComplete, or any @progress/kendo-angular-* package. Covers server-side paging/filtering/sorting, inline CRUD editing, row selection, custom cell templates, master-detail rows, grouping, Excel export, and virtualization for large datasets. Trigger on any mention of kendo grid, kendo treelist, kendo treeview, telerik angular, @progress/kendo-angular-grid, or when the user is building a sortable/filterable/pageable data table in Angular. Also trigger when a user asks about adding editing, export, tree navigation, or dropdown filtering to an existing Kendo Angular component.
scientific-revision
by bmsuisseUse this skill whenever the user wants to verify, revise, or improve a scientific essay, academic paper, or any written document. It checks citation consistency, verifies bibliography entries via CrossRef and Google Scholar/Semantic Scholar, and detects AI-generated writing patterns (slop). Trigger this skill whenever the user mentions 'check citations', 'verify references', 'scientific revision', 'revise essay', 'clean up writing', 'check for AI slop', 'improve writing quality', 'check google scholar', or 'review my paper', especially in academic or professional writing contexts.
fastapi-azure-auth
by bmsuisseAzure Entra ID SSO for FastAPI using cookie-based sessions (MSAL, /login → /callback → session). Trigger on: Azure AD login, Entra SSO, protect routes, RBAC, DEV_MODE bypass, download links with auth. Covers App Registration, AuthMiddleware, role checks via Postgres, and cookie auth enabling native <a download> links.
nicegui
by bmsuisseBuild Python web UIs with NiceGUI — covering layout, widgets, data binding, routing, and the AgGrid data grid. Use this skill whenever the user mentions NiceGUI, wants to build a Python web app, dashboard, or internal tool, asks about ui.aggrid, ui.page, or any NiceGUI component. Triggers on: "nicegui", "ui.aggrid", "ui.page", "NiceGUI app", "python web ui", "python dashboard", "aggrid python", "build a web interface in python".
duckdb
by bmsuisseGuide for working with DuckDB — CLI usage, SQL execution, reading files (CSV, Parquet, JSON, Excel), extensions (httpfs, spatial, json, excel, postgres, etc.), and the Python duckdb package. Use this skill whenever the user is working with DuckDB, whether via CLI, SQL scripts, or Python. Trigger on: duckdb queries, reading local/remote files with duckdb, installing duckdb extensions, duckdb in Python/pandas, exporting data, attaching or querying PostgreSQL from DuckDB, or any question about DuckDB behavior or syntax.
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.