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...
cancer-buddy-caregiver
by CancerDAO支持癌症患者的主要照护者（配偶/父母/成年子女）走过照护全程：陪诊清单、化疗当天准备、家庭分工模板、Zarit 照护负担自评、如何向孩子解释病情、坏消息的情绪预备；也为次要家属提供精简支持模式。Use when 用户以照护者或家属身份求助，需要陪护实务、分担照护负担、或处理照护倦怠。Triggers on: 家属, 陪护, 照护者, 照护倦怠, 我照顾得太累, 我在照顾, 我爸/妈/爱人得癌症, 怎么陪诊, 陪诊清单, 化疗当天带什么, 我太累了.
cancer-buddy-education
by CancerDAO从 MTB 报告和患者档案生成患者友好的宣教手册（含 Mermaid 机制图的 Markdown），包含速查卡、大白话健康摘要、带副作用管理的药物单、日常生活指南、复诊安排、费用/医保导航、分阶段 FAQ；吸收了 vmtb-patient-education 的机制图、癌种模块和按阶段组织的 FAQ。Use when 患者有 profile.json + 至少一份 MTB 报告（lite 或 full），需要把临床报告转成患者和家属能日常使用的材料。Triggers on: 宣教手册, 给我爸妈看的版本, 我爸妈看不懂报告, patient handbook, 患者教育.
cancer-buddy-disclosure
by CancerDAONegotiates whether/how/when to tell a Chinese cancer patient their diagnosis, modeling layered (not binary) disclosure. Use when a family is deciding whether to suppress or reveal the diagnosis, a patient is breaking the news to kin, or someone spontaneously asks 我是不是癌症. Triggers on: 要不要告诉, 不想让 Ta 知道, Ta 不知道自己得癌, 瞒着, 知情同意, 他爸妈不让说, 披露, disclosure.
cancer-buddy-vault
by CancerDAO为患者建立 N=1 数据保险箱——结构化目录、分级分享（🔒 私密 → 🔑 授权 → 📊 匿名供 AI → 🌐 公开）、访问日志。不是云存储，而是患者自己拥有、可迁移、可选择性分享的本地文件结构。Use when 患者想长期整理病历、把数据分级分享给医生/研究者、或控制谁能看自己的健康档案。Triggers on: 数据保险箱, N=1, 我的健康档案, 数据分享, 隐私, 谁能看, 匿名, data vault.
cancer-buddy
by CancerDAO抗癌搭子 (cancer-buddy) — 患者和家属的 AI 抗癌伙伴。不做临床决策，不给治疗建议，不替代医生。 做的是：陪你整理病历、陪照护者扛过来、做心理筛查和危机支援、帮你和家人聊聊告不告诉的问题、建你自己的健康档案、生成给家人看的宣教手册、日常饮食陪伴、第二意见 packet 打包。 严肃临床判断（MTB / 试验匹配 / 扩展准入 / 缓和医疗 / 副作用分级 / 换线决策 / 生存期监测 / 服药依从）不在这里做，需要那些去找主诊医生 + cancer-buddy-pro-skill（内部版）。 Triggers on: 抗癌搭子, 搭子, 患者导航, 帮我分析病情, 刚确诊, 病历整理, 数据保险箱, 宣教手册, 家属, 陪护, burnout, 睡不着, 焦虑, 抑郁, 吃什么, 忌口, 第二意见, 跨境会诊, 告不告诉, 不想让对方知道.
cancer-buddy-organize
by CancerDAOTurn a patient's raw medical records (PDF/images/docx) into a canonical, structured patients/<patient_code>/ directory every other sub-skill can consume. Use when the user hands over a folder of medical records, or says 病历整理 / 我有一堆报告 / 帮我整理报告.
cancer-buddy-find-care
by CancerDAO查找能做特定治疗资源的医院、专科医生和临床试验。**只做资源发现，不做临床判断**。典型问题：哪家医院能做 MTB（分子肿瘤委员会）？我这个癌种谁是国内做得最好的医生？我能去的城市里有没有 X 靶点的临床试验？这个免疫治疗副作用问题哪里看更专业？输入：profile.json（癌种/分期/分子分型/所在城市/能否跨城/经济条件）+ 一个具体诉求。输出：排序后的资源短名单（含挂号路径、地址、联系方式、匹配理由）。Triggers on: 找医院, 哪家医院能做 MTB, 哪个医生擅长, 临床试验在哪招, 异地就医, 推荐医生, 找专家, 哪儿能做 NGS, 找肿瘤多学科会诊, MDT 哪里有, 找试验中心.
cancer-buddy-nutrition
by CancerDAO按癌种与治疗阶段（术前/化疗/放疗/免疫/康复）生成个体化饮食方案，并核查药物-食物相互作用（人参↔抗凝、西柚↔TKI 等）。Use when 患者或照护者问吃什么、忌口、补剂能不能吃、某药配某食物有没有冲突，或在新化疗周期/术后/免疫治疗起始等阶段切换时。Triggers on: 吃什么, 忌口, 化疗期饮食, 术后营养, 补剂, 保健品, 中药冲突, 中医饮食, 灵芝, 孢子粉, 人参, 蛋白粉.
cancer-buddy-mind
by CancerDAO用经过验证的量表（PHQ-9 抑郁、GAD-7 焦虑、NCCN 苦难温度计、C-SSRS Lite 自杀风险）为肿瘤患者及照护者做心理筛查与分级支持，输出自助 / 就医 / 危机升级三级响应。Use when 患者或照护者出现情绪困扰、需要心理评估、或其他子技能检测到自杀意念需转入临床筛查。危机拦截（crisis INTERCEPTION）由 meta 层的 crisis path 负责；mind 负责跑 C-SSRS Lite 与 PHQ-9 随访，并独占临床筛查与倦怠（clinical-screening burnout）。Triggers on: 睡不着, 焦虑, 抑郁, 崩溃, 没力气, 不想活, 想哭, 心理, mental health, screening, burnout.
cancer-buddy-second-opinion
by CancerDAO为跨境或国内第二意见生成审阅者可直接使用的英文病例资料包。产出简洁英文病例摘要（1-2 页可转 PDF 的 markdown）、病历索引、医生对医生的转诊信、DHL/FedEx 病历寄送指南，以及「如何把第二意见带回主治医生处沟通」的脚本。覆盖国内三甲与国际中心（如 MSK、MD Anderson 等，更多见正文 top-centers）。按角色处理：仅限患者或照护者，其他家属路由会被拒绝。Use when 患者或照护者想去国内别家医院或跨境寻求第二意见、需要把病例打包成审阅者可用的英文资料包时。Triggers on: 第二意见, 去别的医院看看, 跨境会诊, MSK, MD Anderson, 日本癌研, 梅奥, 香港养和。
firefly-disclosure
by CancerDAO罕见病遗传风险家庭告知。不是癌症的'要不要告诉患者'禁忌，而是罕见病特有的'如何告诉孩子诊断'、'如何告诉有生育风险的兄弟姐妹'、'如何告诉配偶携带者状态'。按年龄/关系分层告知脚本、家庭会议协议、拒绝回应预案. Use when: 家长纠结要不要告诉孩子诊断、已确诊患者犹豫要不要告诉亲属遗传风险、备孕夫妻发现携带者状态后如何沟通. Triggers on: 告诉孩子诊断, 告诉亲属, 遗传风险告知, 家族告知, 携带者告知, 基因诊断披露.
firefly-mind
by CancerDAO罕见病患者与照护者心理筛查与支持。使用 PHQ-9（抑郁）+ GAD-7（焦虑）+ IES-R（诊断奥德赛创伤应激）三套标准化量表；按分数分级建议（自助/热线/就医）；提供罕见病专属心理支持资源（热线、互助群、照护者支持小组）. Use when: 患者说'情绪不好'、'睡不着'、'撑不住了'、'不知道怎么办'、'感觉绝望'；照护者说'好累'、'不想做了'；诊断奥德赛后出现创伤应激症状. Triggers on: 情绪不好, 抑郁, 焦虑, 睡不好, 撑不住, 崩溃, 想不开, PHQ-9, GAD-7, 创伤应激, 心理支持, 心理筛查.
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.