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...
c-programming
by WbunkerExpert-level C programming assistance based on modern C standards (C99/C11/C17/C23) and the pedagogical approach of "C Programming: A Modern Approach" by K.N. King. Use when the user is writing C code, debugging C programs, asking about C syntax or semantics, discussing C data types, pointers, arrays, strings, structs, unions, enums, the preprocessor, the C standard library, memory management, file I/O, bitwise operations, or program organization. Also triggers on mentions of gcc, clang, Makefile with C files, segfault debugging, undefined behavior, pointer arithmetic, malloc/free, printf/scanf formatting, header files, linkage, storage duration, translation units, or any C standard library header (stdio.h, stdlib.h, string.h, math.h, etc.). Covers the full language from fundamentals through advanced topics like function pointers, abstract data types, and low-level programming.
m5stickc-plus-expert
by WbunkerExpert for programming and using the M5Stack M5StickC PLUS and M5StickC PLUS2 — the stick-shaped ESP32-PICO mini IoT dev kit with a 1.14" TFT, 6-axis IMU (MPU6886), IR transmitter, microphone, RTC, buzzer, buttons, and Grove port. Use when the user wants to: program/flash the StickC PLUS or PLUS2 (Arduino IDE, PlatformIO, UIFlow2, or MicroPython); find a GPIO/pinout or peripheral address; read the IMU/buttons/mic, drive the display, send IR, play tones, use the RTC, or read battery/power; connect HATs or Grove Units; get the PLUS-vs-PLUS2 differences (AXP192 vs GPIO4 HOLD pin, pin remaps); wear it as a watch; or pick and build a project. Triggers: "M5StickC", "StickC Plus", "M5StickC PLUS2", "M5Stack stick", "ESP32-PICO", "M5Unified", "UIFlow", "MPU6886", "flash my stick", "stick pinout", "IR remote with the stick", "M5 watch".
klydoclock-expert
by WbunkerSetup, configuration, troubleshooting, and daily use guidance for the Klydoclock — an animated analog clock display device. Use when the user needs help connecting Klydoclock to WiFi (especially Orbi or other mesh networks), getting it on a 2.4GHz network, configuring display settings, using the remote control, managing Klydo content, or diagnosing any Klydoclock problem.
flow-architect
by WbunkerExpert in Flow Architectures and event-driven integration based on "Flow Architectures: The Future of Streaming and Event-Driven Integration" by James Urquhart (O'Reilly, 2021). Covers the full spectrum of flow concepts: what flow is and why it matters, the business value of real-time integration, event taxonomies and producer/consumer patterns, flow-oriented architecture design principles, event streaming platforms (Kafka, Kinesis, Pulsar), event brokers and messaging protocols (AMQP, MQTT, RabbitMQ), standards and protocols (CloudEvents, AsyncAPI), event discovery and federation, security and trust in event streams, flow design patterns (event sourcing, CQRS, saga, outbox), operational concerns (observability, schema evolution, backpressure), and the future of flow including serverless, edge computing, and the World-Wide Flow vision. Use this skill for questions about designing event-driven systems, choosing between streaming platforms and brokers, implementing integration patterns, scaling flow architectur
istio-expert
by WbunkerExpert-level Istio service mesh assistance covering architecture, traffic management, security, observability, production deployment, and extensibility. Use when the user is working with Istio, Envoy proxies, service mesh configuration, or Kubernetes networking via Istio. Triggers on mentions of Istio, Envoy sidecar, VirtualService, DestinationRule, Gateway, ServiceEntry, PeerAuthentication, RequestAuthentication, AuthorizationPolicy, mTLS, traffic shifting, canary deployments, circuit breaking, fault injection, rate limiting, Kiali, Jaeger, Zipkin, istioctl, istiod, Istio ambient mesh, sidecar injection, Istio ingress/egress gateway, Wasm plugins, telemetry API, or any Istio CRD. Also covers service mesh concepts like sidecar proxy pattern, data plane vs control plane, zero-trust networking, and observability in microservices architectures.
zhipuai-glm-coding
by WbunkerExpert knowledge for maximizing a Z.ai GLM Coding Plan subscription (Lite/Pro/Max) and the broader Z.ai platform. Covers Claude Code/Cline/Roo Code/Kilo Code/Cursor/n8n/TRAE/Eigent setup, model selection (GLM-5.1, GLM-5-Turbo, GLM-4.7, GLM-4.5-Air), quota management, MCP server configuration (Web Search, Web Reader, Vision, Zread), structured output, context caching, thinking modes, CLI/agent invocation, PAYG APIs (vision/image/audio/video/agents), and workflow best practices. Use when configuring the Coding Plan, troubleshooting quota or setup issues, choosing models, calling Z.ai APIs directly, or building agentic coding pipelines.
kimi-code-expert
by WbunkerExpert guide for Kimi (Moonshot AI) models, APIs, CLI, and agentic capabilities. Use when: building apps with the Kimi Chat Completions API (OpenAI-compatible); choosing between kimi-k2.6 / kimi-k2.5 / moonshot-v1 models; enabling thinking/reasoning mode; function calling and tool use; using official built-in tools (web-search, code_runner, memory, fetch, excel, rethink); setting up the Kimi CLI for agentic terminal coding; building agents with the agentic loop pattern; uploading files for document QA; streaming, JSON mode, partial mode, vision (image/video) input; batch API for async jobs; migrating from OpenAI to Kimi; integrating Kimi with Claude Code / Cline / RooCode / OpenClaw; rate limits and pricing; Kimi K2.6 benchmarks vs GPT-5.4 / Claude Opus 4.6 / Gemini 3.1 Pro.
gemma-expert
by WbunkerExpert guidance for working with Google's Gemma open-weight model family (Gemma 1, 2, 3, 4). Covers model selection, local inference, Google AI Studio API, Vertex AI, fine-tuning, multimodal capabilities, tool/function calling, and agentic deployment. Use when the user asks about: running Gemma locally (Ollama, llama.cpp, LM Studio), using Gemma via API, choosing between Gemma variants, fine-tuning Gemma with LoRA/Unsloth, Gemma vision/audio tasks, configuring quantization, debugging tool-calling issues, or building on-device/edge AI applications with Gemma.
booking-com-host-hostaway
by WbunkerExpert guide for vacation rental hosts using Hostaway who want to connect, manage, and optimize their listings on Booking.com. Use when a host asks about: connecting Booking.com to Hostaway, setting up or mapping listings, syncing rates/availability/content/reviews, understanding Booking.com's payment models (Channel Collect vs Property Collect), virtual credit cards (VCC), commissions and monthly invoices, cancellation policies, Genius program, Preferred Partner program, improving content score or search ranking, handling overbookings, troubleshooting extranet/channel manager sync issues, or any Booking.com question from the host's perspective within Hostaway.
expedia-vrbo-expert
by WbunkerExpert guide for managing cabin/vacation rental inventory on Expedia Group platforms (Vrbo host dashboard and Expedia Partner Central). Use when the user asks about listing cabins, managing rates and availability, handling reservations, updating property content, setting promotions, viewing performance reports, communicating with guests, or configuring cancellation policies on Expedia or Vrbo.
mempalace
by WbunkerMemPalace setup, ingestion, search, and knowledge graph expertise. Use when the user wants to install or configure MemPalace, mine conversation history into a palace, query memories via CLI or MCP, understand the palace hierarchy (wings/rooms/drawers), work with the knowledge graph, use the 19 MCP tools with Claude, or understand retrieval accuracy and pipeline stages. MemPalace is a local AI memory system that stores raw verbatim conversation text and retrieves it via ChromaDB embeddings — achieving 96.6% R@5 on LongMemEval with zero API calls.
minimax-expert
by WbunkerMiniMax AI expertise covering their API (OpenAI-compatible and Anthropic-compatible endpoints), model lineup (M2.7, M2.5, M2.1, M2-her), flat-rate Token Plan subscriptions ($10–$150/mo), pay-as-you-go pricing, tool use/function calling, streaming, reasoning/chain-of-thought, prompt caching, and multimodal APIs (speech, video, music, image). Use when integrating MiniMax models via API, configuring Claude Code or other CLI tools to use MiniMax, understanding the Token Plan vs pay-as-you-go billing, selecting the right MiniMax model, enabling thinking/reasoning mode, or working with MiniMax's speech/video/music generation APIs.
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.