Skills
开放的 AI 智能体 Skills 注册表,收录结构化提示词和工作流,并提供推荐模型、示例提示词与兼容工具。
部分描述为试点机器翻译内容,尚未经过人工审核。
Skills
11
类别
9
兼容工具
5
贡献者
1
Diagnoses failing browser and end-to-end tests by correlating assertions, traces, screenshots, network activity, timing, and application state into reproducible fixes.
Converts a design specification or screenshot into accessible, responsive production UI while preserving component boundaries, design tokens, semantic structure, and states.
Creates comprehensive design system documentation and component specifications from existing UI patterns or requirements. Generates design tokens, component APIs, usage guidelines, and accessibility specifications. Supports Figma-to-code workflows and produces consistent theming across platforms.
Plans and generates migration strategies for framework upgrades, language versions, database changes, and architecture shifts. Produces step-by-step migration guides with rollback plans, risk assessment, and automated codemods where possible.
Performs comprehensive security analysis of code and configurations. Identifies OWASP Top 10 vulnerabilities, insecure patterns, missing input validation, authentication flaws, and secrets exposure. Provides remediation steps with secure code examples.
按契约优先原则设计 RESTful 和 GraphQL API。涵盖端点结构、请求与响应模式、错误处理、版本控制、分页、身份验证和速率限制,并生成 OpenAPI/Swagger 规范及实现脚手架。
Identifies and resolves performance bottlenecks in code and systems. Covers algorithmic complexity analysis, memory optimization, caching strategies, database query tuning, and frontend performance (Core Web Vitals). Follows a measure-first approach.
Designs normalized database schemas from business requirements. Covers entity relationships, indexing strategies, migration planning, and performance considerations. Supports PostgreSQL, MySQL, MongoDB, and other databases with dialect-specific optimizations.
Designs, optimizes, and iterates on prompts for LLM applications. Covers system prompt design, few-shot examples, chain-of-thought reasoning, output formatting, and prompt testing strategies. Helps build reliable AI-powered features.
Guides systematic code refactoring while preserving exact behavior. Identifies code smells, suggests appropriate refactoring patterns, and executes transformations incrementally with verification at each step. Follows Chesterton's Fence principle — understands why code exists before changing it.
Translates code between programming languages while preserving logic, idioms, and best practices of the target language. Handles differences in type systems, error handling, concurrency models, and standard library APIs. Produces idiomatic target code, not line-by-line transliteration.
Skills 与 MCP 服务器
有什么区别?Skills定义“做什么”
Skill 将说明、示例提示词和推荐模型组织在一起,让智能体稳定地完成任务。Skills 增加的是知识,而不是新的连接。
MCP 服务器定义“如何连接”
MCP 服务器通过连接数据库、API 和文件等真实系统,为智能体增加新能力。MCP 提供连接和操作,而不是任务说明。
简单来说:当模型需要把某项任务做好时选择 Skill;当模型需要访问工具或系统时选择 MCP 服务器。两者可以组合使用,Skill 可以依赖 MCP 服务器提供的工具。
创建了实用的 Skill?
提交 SKILL.md,加入由社区维护的开源注册表。