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...
contract-cli-shared
by qfeiuscontract-cli 开放平台共享约定技能：在 `contract` 和 `mdm` 模块间做选择，并遵守 `contract/v1/mcp` user-only 限制、`--input-file` 请求体输入、输出格式和 profile 选择规则。当用户要操作开放平台 CLI 但尚未明确命令模块时触发。
contract-cli-mdm-vendor
by qfeiuscontract-cli 交易方查询技能：列出交易方候选列表或按 ID 获取交易方详情。当用户要使用 `contract-cli mdm vendor list|get` 查询合同域交易方数据时触发。
contract-cli-mdm-legal
by qfeiuscontract-cli 法人实体查询技能：列出法人实体候选列表或按 ID 获取法人实体详情。当用户要使用 `contract-cli mdm legal list|get` 查询合同域法人实体数据时触发。
auth
by qfeiuscontract-cli 登录与身份切换技能：初始化 dev profile、执行 user OAuth 登录、录入 bot 的 app_id/app_secret 并立即兑换 tenant_access_token、查看状态、切换默认身份、排查本地 config/secrets 持久化问题。当用户需要 `contract-cli config add`、`contract-cli auth login --as user|bot`、`contract-cli auth status/logout/use` 或排查登录异常时触发。
contract-cli-contract
by qfeiuscontract-cli 合同命令技能：支持 user/bot 双身份下的合同详情、合同搜索、合同创建、同步用户组、读取合同文本、查询合同分类、列出模板、查看模板详情、创建模板实例，bot 身份下的文件上传，以及 user 身份下的枚举查询。当用户要使用 `contract-cli contract ...` 操作合同能力时触发。
contract-cli-mdm-fields
by qfeiuscontract-cli 字段配置查询技能：查询 vendor、legal_entity、vendor_risk 的字段配置定义。当用户要使用 `contract-cli mdm fields list` 确认主数据字段结构时触发。bot 身份当前只支持 vendor/legalEntity。
canvas-table-integration
by qfeiusUse when integrating `@qfei-design/canvas-table` into an existing app or page. Covers consumer-side local or virtual tables, public props/methods/events, row-head suffix actions, selection, drag, fixed columns, summary rows, empty states, lightweight `render + TextShape + shape click` interactions, host-side cell-edit architecture, schema-driven Make field editors, `customEdit`, `commit/cancel`, object `autoClose`, `relatedElements`, `overlayOptions`, `editApplyMode: controlled`, attachment editors, and Make field-display columns with value normalization, ExpensePoc-derived field renderers, and overflow-only tooltip behavior. Only supports `@qfei-design/canvas-table`, never UI-library tables. Read package AI docs first, choose Track A, B, or C, use documented public APIs, and do not modify the table library itself.
make-app-auth
by qfeiusUse when generating, modifying, reviewing, or debugging Make App unified login and authenticated /api/make requests with @qfeius/make-app-auth. Covers unified login, OAuth/ngrok mode, 401/403 handling, logout, current-user menu logout wiring, cookies, sessions, redirect callbacks, and Make App auth troubleshooting. Does not cover UI layout, account menu placement, page structure, build output, Service API contracts, DSL modeling, or canvas-table internals; use makeui for the current-user header menu surface.
make-app-filter
by qfeiusUse when integrating, generating, refactoring, or reviewing Make App filtering with `@qfei-design/make-filter` and CanvasTable header linkage. Covers natural-language requests such as 筛选, 高级筛选, 条件筛选, 表格筛选, 表头筛选, 列头筛选, or 按字段筛选; package pre-flight; advanced filter IR; field-type operators; toolbar filter popovers; `AdvancedFilterPanel`; `useAdvancedFilterController`; AntD adapter; host-owned CanvasTable header filter UI linkage; Service `filter.expression` payloads; URL/deep-link filter echo; candidate values; and tests. Requires Make filtering to be delivered as one integrated feature: package-backed advanced filter plus host-owned CanvasTable header filter linkage. Does not cover general page layout, table rendering internals, CanvasTable header menu API details, Service route implementation, auth, runtime packaging, DSL modeling, or Make CLI deployment.
make-app-runtime
by qfeiusUse when generating, refactoring, reviewing, or debugging Make App project runtime structure, workspace manifests, Service runtime, local/dev scripts, build outputs, Docker/K8s image entrypoints, publish readiness, or packaging errors such as missing `apps/service/dist/server.js`. Covers `apps/` workspace contracts, `apps/ui/dist`, `apps/service` port/build/start contracts, runtime config file location, runtime artifact tests, and forwarded host/proto header preservation. Does not cover UI layout, authentication implementation, Make adapter env semantics, DSL modeling, Make CLI resource deployment, or canvas-table internals.
make-app-service
by qfeiusUse when generating, refactoring, reviewing, or debugging Make App `apps/service` API code and UI-Service contracts. Covers Service route design, `apps/docs/api.md`, componentized/layered Service source structure, `make-client` adapters, `services` orchestration modules, `utils` helpers, schema normalization APIs, record CRUD APIs through Make gateway `/make/data/v1/record`, user/department/lookup/file proxy APIs, Make Meta/Data API adapters, Make adapter runtime config such as `MAKE_APP_KEY` and `MAKE_API_BASE_URL`, strict gateway-origin config with fixed Make service scope `/make`, request login-context forwarding to gateway, Service error envelopes, request validation, logging, and Service API tests. Does not cover UI layout, authentication implementation, build output, Docker/K8s runtime, DSL modeling, Make CLI deployment, or canvas-table internals.
makedsl
by qfeiusUse when designing or generating Make platform DSL YAML — defining apps, entities, fields, relations, views, or record schemas. Also triggered by requests like "建模", "建表", "加字段", "定义关联", or "生成 DSL".
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.