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...
backend-development-expert
by 1SkipProvides professional backend development and system architecture consultation with 10+ years of experience across Java, Go, Python, Node.js, and distributed systems. Use this skill when the user asks about API design, database optimization, microservices, performance tuning, security, DevOps, or system architecture. Trigger keywords: backend, API, database, microservice, distributed, Docker, Kubernetes, SQL, Redis, message queue, gRPC, REST, authentication, performance, scalability, architecture, 后端, 接口, 数据库, 微服务, 分布式, 性能, 架构.
devops-sre-expert
by 1SkipProvides professional DevOps and Site Reliability Engineering consultation with 10+ years of experience in large-scale production systems across e-commerce, fintech, and cloud services. Covers CI/CD, infrastructure as code, observability, SLO/SLI, incident management, progressive delivery, DevSecOps, FinOps, and database/middleware reliability. Use this skill when the user asks about deployment, Docker, Kubernetes, monitoring, alerting, incident response, automation, or any operations/reliability topic. Trigger keywords: DevOps, SRE, CI/CD, Docker, Kubernetes, Terraform, Jenkins, GitHub Actions, monitoring, Prometheus, Grafana, alerting, incident, SLO, deployment, IaC, observability, FinOps, 部署, 监控, 告警, 容器, 运维.
financial-data-ai-analysis-expert
by 1SkipProvides professional financial data science, quantitative analysis, and AI/ML consulting with 10+ years of experience in banking, securities, funds, insurance, and fintech. Covers market microstructure, asset pricing, risk management, alpha factor research, NLP for finance, model risk governance, and high-performance time-series architecture. Use this skill when the user asks about stock analysis, quantitative strategy, risk modeling, financial data processing, FinBERT, credit scoring, or any AI+finance topic. Trigger keywords: stock, trading, quant, alpha, risk, option, derivative, time series, backtest, Sharpe, VaR, factor, portfolio, NLP, sentiment, credit, compliance, 股票, 量化, 因子, 风控, 期权, 回测, 舆情, 金融.
streamlit-frontend-expert
by 1SkipProvides professional Streamlit development consultation with deep expertise in Python web UI, data apps, and interactive dashboards. Covers Streamlit architecture, caching, session state, layout, performance optimization, and integration with pandas/plotly/matplotlib. Also includes general frontend knowledge for React/Vue/Next.js when needed. Use this skill when the user asks about Streamlit UI, data app development, dashboard design, or Python-based web interfaces. Trigger keywords: Streamlit, st., session_state, cache_data, dashboard, UI, 界面, 图表, 交互, plotly, matplotlib, frontend, component, layout, 前端, 组件, 布局.
security-expert
by 1SkipProvides professional information security and security architecture consultation with 10+ years of experience in offensive and defensive security, application security, cloud security, data protection, and security operations. Covers threat modeling, code security, network defense, IAM, data privacy, cloud native security, incident response, penetration testing, and security governance. Use this skill when the user asks about security review, vulnerability, authentication, encryption, compliance, or any security topic. Trigger keywords: security, vulnerability, threat, authentication, encryption, OWASP, compliance, penetration test, GDPR, IAM, firewall, WAF, incident, zero trust, CSPM, 安全, 漏洞, 渗透, 加密, 合规, 认证.
software-testing-expert
by 1SkipProvides professional software testing and quality assurance consultation with 10+ years of full-stack testing experience. Covers test strategy, automation, performance testing, security testing, CI/CD quality gates, and defect management. Use this skill when the user asks about writing tests, test strategy, test automation, performance testing, QA processes, or any quality-related task. Trigger keywords: test, testing, QA, quality, automation, unit test, integration test, e2e, performance test, coverage, pytest, Jest, Playwright, Cypress, JMeter, CI/CD, defect, bug, 测试, 自动化, 质量, 覆盖率.
ui-ux-design-expert
by 1SkipProvides professional UI/UX design consultation with 10+ years of experience across mobile, web, and cross-platform digital products. Use this skill when the user asks for design feedback, UI review, UX improvement, layout advice, accessibility guidance, design system questions, or any interface-related task. Trigger keywords: UI, UX, interface, design, layout, style, color, typography, spacing, component, accessibility, WCAG, design system, CSS, visual, interaction, user experience, usability, 界面, 设计, 样式, 布局, 配色, 字体, 组件, 可用性.
stock-analyzer
by 1SkipUse for work in this stock_analyzer repository: project red lines, recommendation/T+1 boundaries, Feishu/GitHub Actions workflows, cache/scheduler checks, real-data validation, memory/README updates, commits, and push requests such as 更新推送.
python-data-engineering-expert
by 1SkipProvides professional Python data engineering consultation with deep expertise in pandas, numpy, data pipelines, caching strategies, and performance optimization for data-intensive applications. Covers financial time-series processing, multi-source data fetching with fallback chains, health check patterns, and offline caching. Use this skill when the user asks about pandas operations, DataFrame manipulation, data fetching, caching, data pipeline design, or numerical computation. Trigger keywords: pandas, DataFrame, numpy, 数据获取, 缓存, cache, 数据管道, data pipeline, time series, 时间序列, rolling, ewm, 取数据, fetch, fallback, 回退, 健康检查, health check, AKShare, yfinance, 离线, offline, 性能优化.
system-architect-expert
by 1SkipProvides professional system architecture and technical strategy consultation with 10+ years of experience in large-scale distributed systems across e-commerce, fintech, and SaaS. Covers architecture modeling, technology selection, distributed systems, performance engineering, cloud-native design, security architecture, and technical debt governance. Use this skill when the user asks about system design, architecture review, technology selection, scalability, microservices, or any architecture-level decision. Trigger keywords: architecture, architect, system design, microservice, distributed, scalable, C4 model, DDD, clean architecture, event-driven, Kubernetes, cloud native, ADR, trade-off, refactoring, monolith, 架构, 系统设计, 微服务, 分布式, 技术选型.
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.