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...
stm32-developer-skill
by jrjohnSTM32 embedded development guide based on Arcana Embedded STM32 architecture. Provides comprehensive support for Observable Pattern on STM32F051C8 (8KB RAM, 64KB Flash) with FreeRTOS, zero-copy model passing, dual-priority queuing, static allocation, and ISR-safe publishing. Suitable for embedded C++14 development, architecture design, code review, memory optimization, and real-time debugging.
vue-developer-skill
by jrjohnVue 3 development guide based on Arcana Vue enterprise architecture. Provides comprehensive support for Clean Architecture, Offline-First design with 4-layer progressive caching, Vue 3 Composition API with script setup, MVVM Input/Output/Effect pattern, InversifyJS DI, type-safe NavGraph navigation, and enterprise security. Suitable for Vue project development, architecture design, code review, and debugging.
windows-developer-skill
by jrjohnWindows desktop development guide based on Arcana Windows enterprise architecture. Provides comprehensive support for Clean Architecture, WinUI 3, MVVM UDF pattern, Plugin System with 18 plugin types, CRDT-based offline sync, and enterprise security. Suitable for Windows desktop project development, architecture design, code review, and debugging.
android-developer-skill
by jrjohnAndroid development guide based on Arcana Android enterprise architecture. Provides comprehensive support for Clean Architecture, Offline-First design, Jetpack Compose, Hilt DI, and MVVM Input/Output pattern. Suitable for Android project development, architecture design, code review, and debugging.
angular-developer-skill
by jrjohnAngular development guide based on Arcana Angular enterprise architecture. Provides comprehensive support for Clean Architecture, Offline-First design with 4-layer caching, Angular Signals, MVVM Input/Output/Effect pattern, and enterprise security. Suitable for Angular project development, architecture design, code review, and debugging.
arcana-ai-agent-flow-skill
by jrjohnBuild & operate an autonomous CI workflow platform on a SINGLE Kogito BPMN engine (SonataFlow retired 2026-06-09) running three processes — ci-flow (red-build remediation with human handoff — park at humanFixTask, resume the agent's Claude session via `claude --resume <sid>`), merge-flow (verified-green PR automerge + automatic release-please releases), ci-maintenance (hourly read-only health governance) — all feeding one Kogito Data Index, driven by a Rust task-worker dispatching to a Claude agent-task-node, monitored live on an Angular bpmn-js dashboard behind Authelia. Use when the user wants a workflow engine + real-time monitoring dashboard, autonomous CI remediation/merge/release as visible BPMN flows, or AI-to-human handoff with session continuity. Triggers "arcana-ai-agent-flow", "workflow monitor", "工作流監控", "BPMN dashboard", "Kogito Data Index", "green PR automerge", "human handoff", "流程引擎 + dashboard".
esp32-developer-skill
by jrjohnESP32-S3 IoT development guide based on Arcana Embedded ESP32 production-ready IoT command platform. Provides comprehensive support for BLE dual-role (GATT Server/Client via Bluedroid), AES-256-CCM encryption with ECDH P-256 key exchange, Observable sensor pattern, nanopb protobuf, Arcana Frame Protocol, MQTT5, and WiFi+BLE coexistence on FreeRTOS. Suitable for ESP32-S3 firmware development, architecture design, security review, and debugging.
go-developer-skill
by jrjohnGo development guide based on Arcana Cloud Go enterprise architecture. Provides comprehensive support for Clean Architecture, fx (Uber) DI, gRPC-first communication (1.80x faster), dual-protocol support (gRPC/REST via Gin), multi-database DAO layer (MySQL/PostgreSQL/MongoDB via GORM), Viper config, zap logging, Plugin System, SSR Engine, Background Jobs, and 5 deployment modes. Suitable for Go microservices development, architecture design, code review, and debugging.
harmonyos-developer-skill
by jrjohnHarmonyOS 5 (NEXT) development guide based on Arcana HarmonyOS enterprise architecture. Provides comprehensive support for Clean Architecture (four-layer), Offline-First design, ArkTS strict mode, ArkUI declarative UI, InversifyJS-style DI, MVVM Input/Output/Effect pattern, HUKS security, and WorkScheduler background sync. Suitable for HarmonyOS project development, architecture design, code review, and debugging.
ios-developer-skill
by jrjohniOS development guide based on Arcana iOS enterprise architecture. Provides comprehensive support for Clean Architecture, Offline-First design, SwiftUI, SwiftData, and MVVM Input/Output/Effect pattern. Suitable for iOS project development, architecture design, code review, and debugging.
nodejs-developer-skill
by jrjohnNode.js/Express development guide based on Arcana Cloud Node.js enterprise architecture. Provides comprehensive support for Clean Architecture, InversifyJS DI, gRPC-first communication (1.80x faster), dual-protocol support, Prisma ORM, and multiple deployment modes. Suitable for Node.js microservices development, architecture design, code review, and debugging.
python-developer-skill
by jrjohnPython/Flask development guide based on Arcana Cloud Python enterprise architecture. Provides comprehensive support for Clean Architecture, gRPC-first communication (2.78x faster), dual-protocol support, and multiple deployment modes. Suitable for Python microservices development, architecture design, code review, and debugging.
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.