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...
astro-starlight-best-practices
by allenlin90Best-practice guardrails for Astro + Starlight docs apps in this repo. Use when building or changing eridu_docs routes, rendering mode, middleware/auth flows, search behavior, content structure, component overrides, or asset/env handling.
spreadsheet
by allenlin90Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (.xlsx, .csv, .tsv) with formula-aware workflows, cached recalculation, and visual review.
backend-large-file-refactor
by allenlin90Use when developing, auditing, or refactoring apps/erify_api NestJS files that are over roughly 600 lines, mix several backend concerns, hide duplicated logic, or invite Rails-style mixins/concerns.
backend-testing-patterns
by allenlin90Testing patterns for erify_api NestJS backend. Use when writing service unit tests, controller tests, guard tests, or orchestration service tests. Covers NestJS TestingModule setup, project-specific test helpers, mocking strategies, and what to assert at each layer. The erify_api test runner is Jest (not Vitest).
design-patterns
by allenlin90Provides comprehensive architectural patterns for building scalable systems. This skill focuses on high-level architecture, layer boundaries, and package organization. Use when making architecture decisions, defining layer boundaries, or organizing packages.
doc-hygiene
by allenlin90Keep any doc that can be updated and reasoned about — ideation drafts, feature docs, PRDs, architecture references, skills, workflows, canonical docs, READMEs — clean of reasoning artifacts so each revision reads as the current state, not the path that produced it. Trigger any time a doc is being refined, refactored, reorganized, or amended, regardless of whether it is committed. Trigger especially when about to write phrases like "after auditing", "verified on <date>", "previously listed as a blocker", "now resolved", "originally framed as", or numbered gap/decision lists whose items are already addressed. The doc body is for the current truth; reasoning trails belong in commits, PRs, or explicitly-named decision logs.
domain-refactor-cutover-strategy
by allenlin90Multi-phase domain renaming and cutover strategy. Use when planning or executing a large-scale rename (models, routes, contracts, UI) across the monorepo, or when reviewing a cutover scope branch for completeness and safety.
package-extraction-strategy
by allenlin90Guidance for deciding when to extract shared monorepo packages and how to structure code for future extraction. Use when evaluating whether logic should move to a shared package or when designing new features that may have multiple consumers.
soft-delete-restore
by allenlin90Patterns for implementing restore workflows on soft-deleted records in erify_api. Use when adding restore capability to any model (task templates, show creators, shifts, etc.), designing restore permission rules, handling optimistic version conflicts on restore, or building restore endpoints and audit trails.
solid-principles
by allenlin90Provides SOLID design principles guidance for both frontend (React) and backend (NestJS) code. This skill should be used when generating, reviewing, or refactoring code to ensure adherence to Single Responsibility, Open/Closed, Liskov Substitution, Interface Segregation, and Dependency Inversion principles.
user-facing-docs
by allenlin90Convert PRDs and feature docs into non-technical user documentation for eridu_docs. In this repo, organize output by workflow and function first, with guide, SOP, and FAQ pages grouped inside the same area rather than separate top-level buckets. Use when writing help articles, user guides, or onboarding docs for eridu_docs.
frontend-error-handling
by allenlin90Provides error handling patterns for React applications. This skill should be used when implementing error boundaries, API error interceptors, error tracking, or user-friendly error messages.
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.