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...
hm-qa
by rodrigohighermindQuality assurance que declara baseline-ready (Dev Team), não product-ready (Owner). Use antes do Dev Team entregar pro Owner avaliar. Valida 5 checks obrigatórios (typecheck, lint, smoke test, zero console.error em código novo, zero TODO crítico em código novo) + security quick scan + functional tests + edge cases (forms, streaming, erros, mobile, LLM, concorrência, dados sagrados). Para projetos que persistem dados, complementa com /hm-data-integrity.
hm-validate-all
by rodrigohighermindOrquestrador pré-ship que dispara as 5 skills de validação (security, engineer, qa, designer, deploy) em ordem otimizada, consolida findings priorizados em UM único report e declara baseline-ready (Dev Team) ou BLOQUEADO. Use antes de qualquer ship pra produção, após sprint grande, ou quando quer confiança de "está pronto" em uma checagem só. Product-ready continua sendo prerrogativa do Owner.
hm-cli
by rodrigohighermindConstrução de CLI no padrão Higher Mind. Use quando criar um CLI novo, refatorar visual de CLI existente, ou quando quiser que o agente entre no mindset de "terminal como produto cinematográfico" — densidade, intenção visual, agentic-first, custo-consciente, dados sagrados.
hm-data-integrity
by rodrigohighermindDados sagrados — backup, migration safety, operações destrutivas, runtime integrity, schema validation, DR plan, compliance, integridade de arquivos. Use antes de shippar projeto que persiste qualquer coisa (DB, files, blob), após mudança em schema/migration, ao definir política de backup, após incidente envolvendo perda de dados, periodicamente em projetos com dados pessoais/financeiros. Cobre nível "produção pessoal" (Electron/Tauri com DB em userData) explicitamente.
hm-deploy
by rodrigohighermindValidação de deploy por distribution model. Use antes de subir pra produção pela primeira vez, quando o ambiente local parou de funcionar, quando mudou infra, ou para validar que qualquer pessoa consegue subir o projeto do zero. Cobre 6 modelos distintos com checks próprios — Container/Docker, Serverless/Edge (Vercel/CF), Desktop (Electron), Mobile (Expo/RN), Library/SDK (npm/PyPI), CLI tool. Security Gate primeiro: se falha, não continua.
hm-designer
by rodrigohighermindValidação visual de interface no padrão Higher Mind (Linear, Stripe, Apple, A24). Use antes de shippar qualquer visual novo ou refactor de UI. Avalia sofisticação, diferenciação, experiência, encantamento, usabilidade, beleza, pixel-perfect. Dark-first, editorial, cinematográfico, agent-first quando aplicável. Para validar fluxo cognitivo (ordem de decisão, microcopy), use /hm-ux-flow.
hm-engineer
by rodrigohighermindValidação de código senior-level pré-ship. Use quando precisa auditar um bloco grande de código — baseline inegociável (zero bare except, zero any, zero fire-and-forget, zero secrets hardcoded), OWASP quick, container & infraestrutura, performance, LLM patterns, custo, resiliência, dados sagrados. Para deep security audit use /hm-security; para profiling profundo use /hm-performance; para projetos que persistem dados, complementa com /hm-data-integrity.
hm-init
by rodrigohighermindInício de projeto novo no padrão Higher Mind. Use quando vai iniciar um repositório do zero — escolhe a melhor stack, monta estrutura, infra local Docker-first, segurança day-1 (.dockerignore, multi-stage, non-root), Memory + CLAUDE.md cravados, configs obrigatórias por stack (Next.js, Supabase, Tailwind v4, Tauri/Electron). Para CLI especificamente, complementa com /hm-cli.
hm-llm-guardrails
by rodrigohighermindCatálogo de 14 patterns obrigatórios para app que integra LLM (Claude/GPT/Gemini) em produção. Use antes de shippar feature LLM pra produção, quando custo da API explode sem explicação, quando user reclama de "respostas demoram demais" ou "trava no meio", ao adicionar tool calling, agentes ou chat persistente. Cobre sliding window, lazy client factory, in-flight dedupe, rate limit por endpoint, streaming abort/retry, schema validation no response, token budget explícito, cross-channel safety, cost tracking, multi-provider failover, custo×performance como restrição de design, identidade não-mesclável, tool calling guardrails.
hm-performance
by rodrigohighermindProfiling com metas concretas e fix por gargalo. Use antes de shippar feature performance-critical (chat, lista grande, dashboard), quando user reclama "tá lento", após refactor em data flow, periodicamente em projetos com escala, quando custo de LLM/API explode. Cobre 8 domínios — bundle size, Web Vitals (LCP/INP/CLS), API latency (p50/p95/p99), database queries, LLM tokens+cost, network, memory, build performance. Numbers concretos, não especulação.
hm-security
by rodrigohighermindAuditoria de segurança profunda (L1/L2/L3). Use antes de deploy externo, após adicionar auth/dados sensíveis/fluxo financeiro, ou periodicamente como manutenção. Cobre 14 domínios — CIS Docker, OWASP Top 10, OWASP API Top 10, ASVS AuthN/Session, dados/compliance (LGPD/GDPR/PCI), supply chain, AI/LLM (prompt injection, tool calling, multi-tenant LLM), file upload, business logic, secrets scan com 20+ patterns, Supabase/PostgREST RLS regime absoluto. Barra Tempest / Trail of Bits / Cure53.
hm-ux-flow
by rodrigohighermindValidação de fluxo cognitivo end-to-end. Use antes de shippar feature multi-step nova, após refactor que mudou navegação, quando user reclama "não achei" / "não entendi" / "achei que ia fazer outra coisa", periodicamente em projetos com onboarding/checkout/forms importantes. Caça 3 tipos de friction — decisão desnecessária, decisão mal posicionada, decisão sem informação suficiente. Para validar visual (pixel-perfect, dark-mode), use /hm-designer.
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.