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...
comunicacao-interna
by Marcelo-RosasUm conjunto de recursos para redigir comunicações internas (relatórios de status, atualizações de projeto, relatórios de incidentes, FAQs) usando os formatos e o tom do projeto Cargo Flow Navigator.
skill-evaluator
by Marcelo-RosasUma skill para analisar e avaliar o desempenho de outras skills no Cargo Flow Navigator, usando análise pós-hoc de comparações A/B e resultados de benchmarking para gerar insights e sugestões de melhoria.
develop-web-game
by Marcelo-RosasUse when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.
stakeholder-comms
by Marcelo-RosasElabora atualizações para stakeholders adaptadas à audiência — liderança, engenharia, clientes ou parceiros multifuncionais. Use ao escrever atualizações de status semanais, relatórios mensais, anúncios de lançamento, comunicação de riscos ou documentação de decisões.
cargo-flow-automation
by Marcelo-RosasImplement, plan, modify, review, debug, or test Cargo Flow Navigator automation work related to exactly four workflows: auto-approval, auto-order creation, driver suggestion, and risk evaluation. Use when the user asks for edge functions, SQL migrations or triggers, hooks or pages, Playwright tests, architecture, rollout plans, debugging, audits, or code review for those workflows. Always follow a rigid sequence: analyze request, map repo impact, list files, generate implementation, generate tests, generate migrations or triggers when needed, provide validation checklist, and call out risks and rollback. Support two operating modes: implementation mode for shipping code and audit-debug mode for tracing failures, reviewing existing code, validating rules, and proposing minimal fixes. Prefer the repo's current automation stack and paths, especially workflow-orchestrator, notification-hub, ai-orchestrator-agent, ai-manager, workflow_events, approval_requests, and the current Playwright projects.
convert-form-to-wizard
by Marcelo-RosasConverts long complex forms (e.g. Nova Cotação) into multi-step wizards to improve usability. Use only when explicitly invoked (/convert-form-to-wizard) on a form file such as QuoteForm.tsx.
implement-skeleton-loader
by Marcelo-RosasAdds skeleton loader components to pages and components that load data asynchronously (Kanban, Dashboard, tables). Use when useQuery/useSWR pages lack loading state, or when improving perceived performance during data fetch.
simplify-kanban-card
by Marcelo-RosasSimplifies Kanban card components (QuoteCard, OrderCard) to reduce information density by moving secondary data into tooltips. Use when reducing Kanban card complexity, editing QuoteCard.tsx, OrderCard.tsx, or improving card readability.
document-writer
by Marcelo-RosasUm processo estruturado em 3 estágios para a escrita colaborativa de documentos técnicos (especificações, ADRs, propostas) com um usuário, garantindo clareza, profundidade e alinhamento com o leitor.
eval-result-viewer
by Marcelo-RosasUma skill que fornece um script Python para gerar e servir uma página web interativa para revisar os resultados de avaliações (evals) de skills, com a identidade visual Vectra Cargo.
eval-set-builder
by Marcelo-RosasUma skill para criar, revisar e exportar conjuntos de avaliação (eval sets) para as skills do Cargo Flow Navigator, usando um template HTML interativo com a identidade visual Vectra Cargo.
feature-spec
by Marcelo-RosasEscreve documentos de requisitos de produto (PRDs) estruturados com declaração do problema, histórias de usuário, requisitos e métricas de sucesso. Use ao especificar uma nova funcionalidade, escrever um PRD, definir critérios de aceitação, priorizar requisitos ou documentar decisões de produto no contexto do Cargo Flow Navigator.
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.