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...
viewport-zero-scroll
by JoyJoin-Tech-LimitedZero-scroll viewport policy for web and WeChat mini-program (launch priority): 100dvh shell, no document/page scroll, no-scroll containers, ResponsiveSpacer (web + Taro), ScrollSentinel (web dev), FormStepper (max 4 inputs per step). Trigger phrases: "zero scroll", "viewport lock", "mini-program layout", "Taro ScrollView", "100dvh", "ResponsiveSpacer", "collapseBelow".
frontend-performance-and-loading
by JoyJoin-Tech-LimitedFrontend loading and runtime performance guidance for route splitting, Suspense, asset loading, list-size heuristics, and platform-appropriate loading strategies. Use when improving page load speed, route transitions, bundle behavior, or long-list rendering in web or mini-program clients. Trigger phrases: "React.lazy", "bundle size", "LCP", "prefetchQuery", "VirtualList", "loading strategy".
matching-domain
by JoyJoin-Tech-LimitedDeterministic server-owned matching — default 6D pair weights; optional 7D when ENABLE_SEMANTIC_SIMILARITY. Signal boundary: user_interest_signals never in scoring path. Use for pool matching, pair/group formation, match explanation. Triggers: scoring factor, match weights, groups not forming, low scores, match explanation, semantic similarity dimension.
semantic-matching-embeddings
by JoyJoin-Tech-LimitedSemantic matching and embedding pipeline: feature-flagged 7th pair-scoring dimension (ENABLE_SEMANTIC_SIMILARITY), deterministic 64-dim feature-hash vectors, neural embedding generation via DeepSeek, async user semantic profile cache, and dialogue insight storage. Use when modifying semantic similarity scoring, embedding clients, profile vector pipelines, or dialogue embeddings. Triggers: semantic similarity, embedding, vector, cosine similarity, user_semantic_profiles, dialogue_embeddings, DeepSeek embedding, matchingSemantic.
admin-client-frontend
by JoyJoin-Tech-LimitedBuild and maintain the JoyJoin admin portal UI in apps/admin-client. Covers Recharts dashboards, shadcn/ui tables and forms, RBAC UI gating (super_admin / operator / viewer), pool admin surfaces, auth/session patterns, and wouter routing. Use when adding admin pages, charts, admin-specific components, or modifying the admin sidebar/login. Trigger phrases: "admin dashboard", "add an admin page", "Recharts chart", "admin sidebar", "pool management UI", "admin login", "RBAC admin", "super_admin only UI", "event pool admin", "admin table", "admin guard".
frontend-hook-engine
by JoyJoin-Tech-LimitedAudit screens, components, and frontend flows with a normalized Seven Deadly Sins heuristic, then route the response into Brainstorm, Execute, or Debug mode with concrete UI deliverables. Use when evaluating CTA hierarchy, component states, interaction clarity, or a screen-level product problem. Trigger phrases: @sin-fe, /7sins-fe, Frontend Hook Engine, screen sin mapping, audit this interface, CTA hierarchy, this page feels confusing, what should people click first.
pm-sin-mapper
by JoyJoin-Tech-LimitedDiagnose product ideas, funnels, and feature directions with a normalized Seven Deadly Sins product-design heuristic, then route the response into Brainstorm, Execute, or Debug mode with concrete PM deliverables. Use when auditing onboarding, monetization, activation, retention, or a new feature concept through a sin-mapping lens. Trigger phrases: /7sins-pm, PM Sin Mapper, why are users dropping off, which idea is better for users, what should we change first.
mini-program-frontend-excellence
by JoyJoin-Tech-LimitedDeliver premium, JoyJoin-native UI in apps/mini-program using Taro-native primitives, brand-aligned hierarchy, complete state design, and mini-program-safe performance discipline. Enforces pixel-precision when specs exist (match exactly; ≤1px effective deviation only with documented exception) and strict 8rpx spacing rhythm when they do not. Two-tier: Routine changes use a 5-point quick check; Full changes require WeChat DevTools inspection before merge. Use when implementing or refining Taro pages/components, raising a screen above generic "cheap mini-program" quality, or reviewing whether a mini-program UI feels native-quality and unmistakably JoyJoin. Trigger phrases: "mini-program UI", "Taro page", "make this feel premium", "native-quality mini-program", "cheap mini-program feel", "improve mini-program empty state", "pixel perfect", "match Figma", "rpx spacing", "WeChat DevTools".
omo-orchestration-bridge
by JoyJoin-Tech-LimitedBridge Oh My OpenAgent (OMO) discipline-agent workflows into Kimi Code CLI. Maps OMO commands (ultrawork, /start-work, resume boulder) to Kimi-native Agent tool orchestration using existing .github/agents/ definitions and .sisyphus/ boulder state. Triggers: ultrawork, /start-work, resume boulder, omo, atlas, prometheus, sisyphus, oracle, team mode, parallel agents, boulder workflow, plan execution.
caching-strategy
by JoyJoin-Tech-LimitedCaching and rate-limiting strategy: backend selection, TTL design, key naming, invalidation contracts, and horizontal-scaling guardrails. Use when adding caches, modifying rate limits, or debugging stale data. Triggers: cache, Redis, rate limit, matchingCache, node-cache, TTL, eviction, invalidate cache, stale data, thundering herd, connect-pg-simple, session store.
wechat-ecosystem-integration
by JoyJoin-Tech-LimitedWeChat auth, Mini Program APIs, Taro patterns, WeChat Pay v3, and cross-platform coordination for the JoyJoin WeChat ecosystem. Use when working with wx.login, Taro.login, jscode2session, OAuth2 web flows, JSAPI/H5 payments, webhook verification, or mini-program-specific transport and auth session wiring. Trigger phrases: "wechat auth", "wx.login", "Taro.login", "jscode2session", "WeChat Pay", "Taro.requestPayment", "mini-program payment", "wechat oauth", "openid", "session_key", "WECHAT_APPID", "WECHAT_PAY".
performance-audit
by JoyJoin-Tech-LimitedPost-implementation performance audit covering smoothness (流畅度), rendering speed (速度), device adaptability (设备适配), memory safety (内存安全), network resilience (网络韧性), and package size (包体积) for WeChat mini-program. Uses Gen Z phone model baselines (8GB+ primary tier, not low-end). Incorporates grill-me interview methodology to stress-test performance assumptions after every implementation. Produces gated report: PASS / WARN / BLOCK. Trigger phrases: "performance audit", "流畅度", "speed check", "device adaptability", "perf audit after implementation", "run perf check", "performance gate", "perf grill".
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.