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...
umb-bump-version
by umbracoBump the Umbraco CMS version across all required files. Use when the user asks to bump, update, or set the version number — e.g., "bump version to 17.3.4", "set version to 18.0.0-rc", "update version". Accepts the target version as an argument.
umb-review
by umbracoAutomated PR code review for Umbraco CMS. Analyzes changed files for intent, impact on consumers, breaking changes, architecture compliance, and code quality. Non-interactive — outputs a full structured review. Use this skill whenever the user asks to review a branch, review a PR, check their changes for issues, analyze a diff, or validate breaking change patterns — even if they don't say "review" explicitly. Does NOT apply to writing new code, fixing bugs, refactoring, explaining architecture, writing tests, or reviewing documentation content.
umb-release-notes
by umbracoImprove a set of auto-generated GitHub release notes for an Umbraco CMS release. Cross-checks the notes against every PR carrying the release label, adds any that are missing, re-files every PR under the most appropriate category, and strips purely-internal entries. Use whenever the user asks to tidy up, improve, complete, or recategorize release notes for a given version, or mentions a release-notes text file plus a version number.
general-create-workspace
by umbracoCreate a new workspace for an entity in the Umbraco backoffice. Supports two workspace types — default (simple, manifest-only, for root/listing pages) and routable (entity detail editing with create/edit flows). Use when the user says "create a workspace", "add a workspace for X", or "scaffold a workspace". For routable workspaces, the entity must already have a package, entity type, repository, and data source.
general-deprecate-api
by umbracoDeprecate a public API (class, method, property, type, constant, or context token) following the 2-major-version rule. Use when removing or replacing any publicly exported symbol that external consumers may depend on — includes exports from package index.ts files, global components, extension type aliases, and manifest schemas.
general-create-repository
by umbracoCreate or extend a repository in the Umbraco backoffice. Covers detail (CRUD), item (batch lookup), collection (paginated list), and action-specific (publish, duplicate, move, etc.) repositories. Use when the user says "create a repository", "add a data source", or when a feature needs to fetch or post data. Each repository type has its own template — pick the right one based on the operation.
general-create-package
by umbracoCreate a new package in the Umbraco backoffice client with its first module. Use when adding a new domain feature area that needs its own package under src/packages/ — e.g., a new CMS feature like data types, tags, or relations. Packages are self-contained domain modules that can theoretically be uninstalled independently. Also use when the user says things like "scaffold a new package", "add a new feature package", or "create a new domain module".
general-create-kind
by umbracoCreate a new extension kind — a reusable default implementation for an extension type. Use when multiple extensions of the same type share the same element/API implementation and only differ in configuration. Kinds reduce boilerplate by providing pre-built defaults that extensions customize via meta.
general-create-extension-type
by umbracoCreate a new extension type for the Umbraco backoffice extension registry. Use when adding a new type of extension that can be registered via manifests (e.g., a new dashboard type, a new sidebar app type, a new toolbar extension type). Any package can define extension types.
general-create-condition
by umbracoCreate a new extension condition that controls when extensions are active. Use when you need to conditionally show or hide extensions based on application state (e.g., current section, user permissions, entity state, workspace context). Conditions are registered as extensions and referenced in manifest condition arrays.
general-add-value-type
by umbracoAdd a new value type — a named, typed string constant that extends UmbValueTypeMap. Use when a feature needs to declare what type of value it holds so it can be referenced in collection columns or value summary manifests. Also use when a property editor needs to expose its value type for use in collection views.
general-add-value-summary
by umbracoAdd a value summary extension so a feature's typed value can be displayed compactly in collection views (e.g., table columns). Use when a feature or property editor already has a value type and needs a renderer for collection table cells. Two variants — simple (element only, no API call) and resolver (batch API resolution needed). Prerequisite: a value type constant must already exist — use the general-add-value-type skill first if it doesn't.
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.