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...
credit-rating-qcc
by duhu2000企业信用评级Skill - 企查查MCP增强版。 基于企查查企业风险数据与工商信息，自动生成企业信用评级报告。 核心功能： - 多维度信用评分：工商稳定性、司法风险、经营活跃度、财务健康度 - 行业对标：与同行业企业信用水平横向比较 - 评级展望：正面/稳定/负面 - 授信建议：基于评级结果给出授信额度与利率建议 适用场景：银行信贷审批、供应链金融授信、融资租赁风控、保理业务。 使用方式：/credit-rating-qcc 企业名称 [--sector 行业] [--benchmark 对标]
fundraising-tracker-qcc
by duhu2000融资动态追踪Skill - 企查查MCP增强版。 追踪企业融资历史、估值变化、投资方背景，辅助VC/FA进行投资决策。 核心功能： - 融资历史：历次融资时间、金额、投资方、估值 - 估值趋势：估值变化曲线、估值合理性评估 - 投资方分析：投资机构背景、领投/跟投策略 - 竞品融资：同行业企业融资动态对比 - 融资信号：潜在融资需求信号识别 适用场景：VC投资前研究、FA项目推介、企业融资规划、投资组合监控。 使用方式：/fundraising-tracker-qcc 企业名称 [--peer 竞品企业] [--sector 行业]
kyb-kyb-verification-qcc
by duhu2000KYB 企业核验 SKILL · 企查查 MCP V2.0 增强版。 金融机构对公客户开户、授信审批、尽调、年检场景的主体自动化核验工具。输入企业名称或统一社会信用代码后，SKILL 自动完成主体真实性核验、工商信息核验、历史治理稳定性回溯、受益所有人穿透、34 类司法风险扫描，输出符合 FATF / 中国央行 3 号令标准的 KYB 合规底稿。 核心能力： - 主体真实性核验：企业名 + USCC + 法代三项交叉匹配（`verify_company_accuracy`） - 工商信息核验：注册资本、法代、股东结构、登记状态实时比对 - **V2.0 新能力：历史治理稳定性**（qcc-history）—— 历史法代更替轨迹、历史股东变迁、历史注册资本变更，识别"频繁变更"的治理不稳定主体 - 受益所有人穿透：股权穿透 + `get_beneficial_owners` + UBO 个人画像 - 34 类司法风险扫描：失信 / 被执行 / 限高 / 股权冻结 / 经营异常 / 税务违法 等全量 - 关联关系排查：集团客户识别、隐性关联、一致行动人 适用场景：银行 / 券商 / 信托 / 保险等金融机构的对公开户 KYB、信贷授信前调查、存量客户年检、反洗钱客户尽调。 使用方式：/kyb-verification-qcc 企业名称 [统一社会信用代码] [--depth standard|full] [--format md|docx|pptx]
related-party-qcc
by duhu2000关联方穿透识别Skill - 企查查MCP增强版。 专为投资银行、审计机构、合规风控设计的关联方识别工具。 自动进行股权穿透、实控人识别、关联交易分析、利益冲突检测。 支持：IPO关联方核查、并购关联交易审查、集团客户识别、一致行动人发现。 典型触发："关联方识别"、"股权穿透"、"实控人是谁"、"关联交易"、"一致行动人".
compliance-monitor-qcc
by duhu2000合规风险持续监控Skill - 企查查MCP增强版。 专为银行合规部、券商风控、投资机构投后管理设计的7x24小时风险监控工具。 自动扫描18类风险信号，实时推送预警，生成合规报告，支持投后/贷后风险管控。 覆盖：司法风险、经营异常、行政处罚、股权冻结、失信被执行等核心监控维度。 典型触发："监控风险"、"投后管理"、"风险预警"、"合规报告"、"风险扫描".
ip-due-diligence-qcc
by duhu2000知识产权尽调Skill - 企查查MCP增强版。 针对科技企业、拟IPO企业的知识产权全维度尽调，覆盖专利、商标、软件著作权。 核心功能： - 专利全景扫描：发明/实用新型/外观设计专利数量、质量、有效性 - 商标布局分析：核心商标、防御商标、国际布局 - 软著盘点：软件著作权数量与业务匹配度 - 知产风险：质押、转让、无效宣告、侵权诉讼 - 技术竞争力评估：与竞品企业的知产对标 适用场景：科技投资尽调、IPO知识产权专项、技术并购、专利许可谈判。 使用方式：/ip-due-diligence-qcc 企业名称 [--peer 竞品企业] [--focus 重点技术领域]
supply-chain-risk-qcc
by duhu2000供应链风险评估Skill - 企查查MCP增强版。 针对制造业、零售业企业的供应链风险全维度评估，覆盖供应商风险、客户集中度、物流风险。 核心功能： - 供应商风险评估：上游关键供应商的工商、风险、经营健康度 - 客户集中度分析：下游大客户的依赖度与稳定性 - 招投标活跃度：通过招投标数据评估供应链活力 - 行业地位评估：企业在供应链中的议价能力与替代性 - 风险传导预警：识别可能传导至企业的供应链风险 适用场景：制造业供应链风控、零售业供应商管理、供应链金融、采购决策支持。 使用方式：/supply-chain-risk-qcc 企业名称 [--tier 评估层级] [--depth 穿透深度]
equity-structure-qcc
by duhu2000股权结构穿透分析 SKILL · 企查查 MCP V2.0 增强版。 投资决策前的控制权核查工具。多层股权穿透 + 历史股权变迁双层分析，识别实际控制人、一致行动人、隐性关联关系，帮助投资团队在 DD 阶段快速厘清目标公司的实际控制架构，识别潜在的关联交易风险与控制权争议风险。 核心能力： - 多层股权穿透：从企业直接股东向上追溯到自然人 UBO，穿透最深可达 10 层 - 股权结构图生成：结构化输出各层持股比例与路径 - **V2.0 新能力：历史股权变迁**（qcc-history）—— 识别股东"进退时点"与估值拐点 - 一致行动人识别：通过共同投资关系、同一实控人、关联企业锁定隐性一致行动人 - 关联交易风险排查：UBO × 对外投资 × 交叉持股的网络分析 适用场景：PE / VC 项目 DD、投资银行并购尽调、控制权变更审批、股东代位诉讼前背调、一致行动人协议审议。 使用方式：/equity-structure 企业名称 [--depth shallow|full] [--historical 是否包含历史变迁] [--format md|docx|pptx]
logistics-brief-qcc
by duhu2000适用于：物流、承运商、货运、运输、路线、交付、 准时交付、承运商绩效、物流简报、承运商记分卡、 物流KPI、运输绩效、运费审计。 **企查查MCP增强版**：验证中国承运商工商登记和风险状态 用于承运商选择和合同决策。 不适用于：供应网络设施选址（使用network-design）、供应商 评估（使用vendor-assessment-qcc）、支出类别分析（使用spend-analysis-qcc）。
new-supplier-screening-qcc
by duhu2000新供应商快速筛选 SKILL · 企查查 MCP V2.0 增强版。 招投标或采购寻源阶段对候选供应商的批量快速筛选工具。与"供应商准入评估"的深度核验不同，本 SKILL 聚焦"快速筛选 + 去伪存真"——一次扫描多家候选供应商，输出排序后的短名单。V2.0 新增双随机抽查作为合规筛选利器。 核心能力： - 批量扫描候选供应商（每次可处理 5-20 家） - 9 项核心红线快筛（失信 / 限高 / 被执行 / 经营异常 / 破产 / 资不抵债 / 重大处罚 / 股权冻结 / 吊销） - **V2.0 新能力**：`get_random_check` 双随机抽查合规评分——经得起政府抽查 = 合规性强信号 - 输出短名单（排除红线 + 按综合评分排序） 适用场景：招标寻源阶段候选供应商排查 / 集中采购前的候选池筛选 / 新业务领域供应商批量扫描。 使用方式：/new-supplier-screening 供应商 1 / 供应商 2 / ... [--top N 返回前 N 名] [--format md|docx|pptx]
spend-analysis-qcc
by duhu2000分析采购支出数据以发现节约机会，整合企查查供应商情报。 适用于：支出分析、支出分析、分析支出、采购支出、 品类支出、跨站点支出、供应商整合、价格一致性、 价格基准、市场基准、RFQ策略、支出报告、品类管理。 **企查查MCP增强版**：自动用工商数据、风险信号和经营指标 丰富中国供应商档案，为整合决策提供信息。 不适用于：发票对账（使用invoice-reconciliation-qcc）、供应商风险 评估（使用supplier-risk-qcc）、承运商绩效（使用logistics-brief-qcc）。
supplier-annual-check-qcc
by duhu2000供应商年度健康体检 SKILL · 企查查 MCP V2.0 增强版。 供应商年度评审的标准化核查工具。对核心供应商进行全面年度体检，V2.0 新增真实财务 YoY 对比 + 双随机抽查 + 历史对比三层能力，一次性输出经营状态变化、资质证件到期情况、信用记录变更、财务指标退化预警的结构化报告。 核心能力： - **V2.0 新能力**：`get_financial_data` 3 年财报 YoY 对比 - **V2.0 新能力**：`get_random_check` 双随机抽查记录 - 资质证件到期提醒（含续期风险） - 经营状态 YoY 变化（参保人数 / 招聘 / 招投标 / 荣誉） - 信用记录变更（YoY 新增失信 / 限高 / 行政处罚） - 法代 × 核心高管变动跟踪 适用场景：采购供应商年度评审 / 续签决策 / 供应商分级调整 / 战略供应商健康度跟踪。 使用方式：/supplier-annual-check 供应商名称 [--baseline 上期评审日] [--format md|docx|pptx]
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.