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...
longbridge-securities-toolkit
by findscripter当需要查港股/美股/A股/新加坡市场实时行情、K线、基本面、自选组合、持仓盈亏、期权与板块资金流时使用；通过 longbridge CLI（无则回退 MCP）以 JSON 输出按子命令拉数并用用户语言解读；不适用于自动下单、加密非 .HAS 标的或无凭证/无 CLI/MCP 环境。触发词：港股美股行情、自选股、持仓盈亏、期权分析、板块资金流、longbridge、长桥
andreessen-vc-lens
by findscripter当需要用市场优先的犀利风投视角压力测试创业点子/功能/押注，或判断是否已达 PMF 时使用；产出先反驳后立论、带置信度的 BUILD/DERISK/KILL 裁决与 PMF 信号评分；不适用于温和头脑风暴、求安慰背书或纯执行落地。触发词：该不该做、有没有市场、市场优先、PMF、产品市场契合、product market fit、压力测试点子、风投视角、andreessen、pmarca、为什么现在
diligence-issue-extractor
by findscripter当对并购数据室（VDR）做尽调、需按门类与重要性门槛从海量文件中提取关键问题并产出备忘录格式发现时使用；做的是：清点 VDR、按重要性过滤、逐门类抽取问题（控制权变更/转让限制/IP 权属/劳动/诉讼等）、按严重度分级（红/黄/绿）并标注来源；不适用于做重要性临界判断、谈判陈述与保证、或高量条款批量抽取（移交 Luminance/Kira）。触发词：尽职调查、尽调、数据室、VDR、data room、diligence review、提取问题、issue extraction、控制权变更、change of control。
network-interface-health
by findscripter当怀疑丢包、时延抖动、间歇不可达由物理链路/交换端口/线缆光模块/双工或拥塞引起时使用；做接口计数器取基线-等间隔-复测对比、CRC/runts/giants/drops/resets 归因、双工速率失配排查，产出方向定位与处置清单；不适用于纯路由/防火墙策略、应用层与 BGP/OSPF 控制面、DNS 解析故障；触发词：接口错误、丢包、CRC、双工失配、链路抖动、ifInErrors
agentmail-email-infra
by findscripter当 AI 智能体需要真实邮箱完成注册/验证码/事务通信时使用；通过 AgentMail REST API 开通账号、收发邮件、注册 Webhook、查询 karma 余额并产出可执行调用；不适用于自建/企业 SMTP/IMAP 或个人邮箱代收。触发词：AgentMail、智能体邮箱、theagentmail.net
makepad-rust-ui
by findscripter当用 Rust + Makepad 框架搭建跨平台 GUI（桌面/移动/Web）时使用；做工程脚手架、live_design! DSL 布局、事件处理、MPSL 着色器与 cargo-makepad 多端打包的实现产物；不适用于 egui/Tauri/Slint 等非 Makepad 栈、纯后端逻辑或无 GUI 的 Rust 项目。触发词：Makepad、live_design、MPSL、cargo makepad
bond-relative-value-analysis
by findscripter当判断债券贵/便宜、做利差分解（无风险+信用+残差）、对比同类券或跑利率冲击情景时使用；做基于 MCP 行情/曲线工具链的相对价值评估并产出利差分解表、情景损益表与贵/便宜建议；不适用于权益估值、纯发行定价、组合层级配置或无可比券与曲线数据的场景；触发词：相对价值、贵便宜、利差分解、Z-spread、G-spread、债券情景分析
pyopenms-mass-spectrometry
by findscripter当需要用 PyOpenMS（OpenMS 的 Python 绑定）处理 LC-MS/MS 蛋白质组学或代谢组学原始质谱数据时使用；做 mzML/mzXML 等格式读写、信号处理（平滑/峰检测/质心化）、特征检测与跨样本连接、肽段/蛋白鉴定及 FDR 控制、非靶向代谢组学流程，产出特征表/鉴定表（pandas/CSV）；不适用于简单谱库匹配与代谢物注释（用 matchms）、纯蛋白序列分析（用 biopython）、不读质谱数据的任务；触发词：PyOpenMS、OpenMS、质谱、mass spectrometry、mzML、LC-MS/MS、蛋白质组学、proteomics、代谢组学、metabolomics、峰检测、peak picking、特征检测、FDR。
polars-bio-genomic-intervals
by findscripter当在 Polars DataFrame 上做基因组区间运算（overlap/nearest/merge/coverage/complement/subtract）或读写 BED/VCF/BAM/GFF 等生信格式、且数据量大需流式/云端处理时使用；做区间算术、生信文件 I/O、DataFusion SQL 查询、BAM 测序深度计算，产出 LazyFrame/DataFrame 结果。不适用于纯序列比对、变异注释或非区间型分析。触发词：基因组区间、overlap、bioframe 替代、BED/VCF/BAM、测序深度 depth
arm-cortex-firmware-expert
by findscripter当为 ARM Cortex-M 系列单片机（Teensy 4.x、STM32 F4/F7/H7、nRF52、SAMD）编写固件、外设驱动或排查时序/内存一致性问题时使用；产出可编译的完整驱动模块（init/ISR/示例）、并发与 DMA 缓存方案、NVIC/临界区/HardFault 处理；不适用于纯应用层、桌面/服务器或非 Cortex-M 平台。触发词：Cortex-M、STM32、Teensy、DMA、HardFault
macro-regime-detector
by findscripter当判断当前宏观市场处于何种结构性体制、是否正在发生1-2年级别的体制切换、或需要据此做战略性资产配置时使用；做用月频跨资产比价(RSP/SPY、10Y-2Y、HYG/LQD、IWM/SPY、SPY/TLT、XLY/XLP)的三层信号检测，加权打分并按决策树分类为集中/扩散/收缩/通胀/过渡五种体制，产出切换概率与配置建议的JSON+Markdown报告；不适用于2-8周战术择时、日内信号、个股选股或实盘下单；触发词：宏观体制、市场体制切换、结构性轮动、长期配置、RSP SPY、收益率曲线、信用利差、macro regime
pipecat-voice-assistant
by findscripter当需要用 Pipecat 搭建实时对话式语音 Agent、把多家服务商（OpenAI STT/TTS、Google Gemini LLM）串成一条低延迟语音流水线时使用；做基于 Mic→VAD→STT→LLM→TTS→Speaker 的本地语音助手并产出可运行 Python 脚本与配置；不适用于端到端 speech-to-speech 一体模型、电话/WebRTC 远程接入或非 Pipecat 框架。触发词：Pipecat、语音助手、低延迟语音流水线
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.