Skills 导航
浏览和发现最好用的 AI Agent Skills,按 GitHub 仓库分类展示
找到 220 个 Skills
浏览和发现最好用的 AI Agent Skills,按 GitHub 仓库分类展示
找到 220 个 Skills
by anderskev
LLM-as-judge methodology for comparing code implementations across repositories. Scores implementations on functionality, security, test quality, overengineering, and dead code using weighted rubrics. Used by /beagle:llm-judge command.
by anderskev
Reviews ExUnit test code for proper patterns, boundary mocking with Mox, and test adapter usage. Use when reviewing _test.exs files or test helper configurations.
by bwbernardweston18
>
by anastasiavanzato299-maker
小红书图文创作技能。触发条件:用户说"生成图文"、"创作内容"、"做图文矩阵"、"生成XX的图文"时使用。功能:读取素材库 → 生成7张竖屏小红书图文 → AI专家两轮review迭代 → 用户最终确认交付。
by anderskev
Reviews FastAPI code for routing patterns, dependency injection, validation, and async handlers. Use when reviewing FastAPI apps, checking APIRouter setup, Depends() usage, or response models.
by andyli-gh
博查搜索 (Bocha Search) 的 Python 实现技能,提供增强的网页搜索能力。当用户需要通过博查 AI 搜索 API 进行网页搜索、获取联网信息、查找最新资讯或中文内容时使用此技能。与现有的 JavaScript 版本相比,本技能提供更稳定的连接、更灵活的输出格式(原始 JSON/Brave 兼容格式/Markdown)、更好的错误处理和重试机制。适用于 AI Agent 需要联网搜索、RAG 应用获取网页摘要、中文内容检索等场景。
by amitb-quantum
Read-only triage for a local git working tree that summarizes uncommitted changes and applies conservative risk flags. Use when a user asks what changed in a repo, what is dirty, what is staged versus unstaged, or which risk flags apply before a commit. Do not use for commit writing, branch management, history analysis, merge conflict resolution, PR review, or general git assistance.
by belivar
副业/独立开发项目验证工具。当用户有了一个副业想法、产品 idea、或者想验证某个方向能不能做时使用。帮助分析需求真伪、竞品情况、市场规模、变现可能和实施难度。适用于副业规划、独立开发、产品验证等场景。附带真实案例库、数据调研脚本。
by BytesAgain
Visualize file diffs side-by-side with syntax-highlighted change views. Use when reviewing changes, comparing versions, inspecting merge results.
by anderskev
Automatic graph layout using dagre with React Flow (@xyflow/react). Use when implementing auto-layout, hierarchical layouts, tree structures, or arranging nodes programmatically. Triggers on dagre, auto-layout, automatic layout, getLayoutedElements, rankdir, hierarchical graph.
by anderskev
Reviews Go code for idiomatic patterns, error handling, concurrency safety, and common mistakes. Use when reviewing .go files, checking error handling, goroutine usage, or interface design. Covers generics (Go 1.18+), errors.Join and slog (Go 1.21+), and Go 1.22 loop variable semantics.
by anderskev
Advanced React Flow patterns for complex use cases. Use when implementing sub-flows, custom connection lines, programmatic layouts, drag-and-drop, undo/redo, or complex state synchronization.
by anderskev
Architectural guidance for building node-based UIs with React Flow. Use when designing flow-based applications, making decisions about state management, integration patterns, or evaluating whether React Flow fits a use case.
by anderskev
Test PydanticAI agents using TestModel, FunctionModel, VCR cassettes, and inline snapshots. Use when writing unit tests, mocking LLM responses, or recording API interactions.
by anderskev
Implements React Flow node-based UIs correctly using @xyflow/react. Use when building flow charts, diagrams, visual editors, or node-based applications with React. Covers nodes, edges, handles, custom components, state management, and viewport control.
by asimons81
Validates side hustle ideas against real market demand. Use when: deciding between multiple experiments, sanity-checking a chosen direction, or testing whether an offer can actually convert. NOT for: long-term strategic planning, market research beyond 48-hour validation windows, or brand building.
by 杨卫薪律师(微信ywxlaw)
智能 Git 批量提交工具。当用户说 "git 提交"、"git commit"、"批量提交"、"拆分提交"、"整理提交" 时使用,或者当用户暂存了多个不同类型的文件需要分开提交时使用。自动将混合的文件修改按类型分类(依赖管理、文档更新、license 文件、配置、源代码等),并创建多个清晰聚焦的提交,使用标准化的提交信息格式。帮助保持清晰的 Git 历史,确保每个提交都有单一、明确的目的。使用英文前缀(docs:、feat:、fix: 等)加中文内容,支持 GitHub 彩色标签显示。
by daymade
面向 iOS/macOS 应用开发与排障,覆盖 XcodeGen、SwiftUI、SPM、签名公证、真机部署和 CI/CD,快速解决 Xcode 构建失败、依赖异常及证书配置问题
✎ 做 iOS/macOS 应用时,签名、公证、真机部署和 CI/CD 最容易卡壳,它把 XcodeGen、SwiftUI 到证书配置的问题一并理顺,特别适合排查顽固构建错误。
by daymade
聚焦 GitHub 开源贡献实战,教你筛选值得投入的项目、发现适合切入的 issue、写出高质量 PR,并持续积累贡献者口碑与公开影响力。
✎ 想高效参与 GitHub 开源项目时,它能帮你从选项目、找机会到写出高质量 PR 一路理顺,尤其适合想系统积累贡献口碑的人。
by daymade
用于 React、Next.js、Vue 等前端项目的 i18n 搭建与审计:配置框架、替换硬编码文案、校验 en-US/zh-CN 词条一致性,并处理复数、格式化和错误信息本地化。
✎ 帮你把 React/TS 项目的国际化从配置到审计一次理顺,既能清硬编码、补齐中英文覆盖,还会校验键一致性和复数格式,省心又可靠。
by daymade
针对文档里的技术规格、统计数据、AI 模型参数等事实陈述做核查,优先检索官网和权威来源,标出错误或过时内容,并在你确认后生成修正建议。
✎ 技术文档、AI 规格或数据说明里怕有错漏,用它能快速核验事实和过期信息;结合网页搜索与官方信源给出修正建议,还会等你确认后再改,靠谱省心。
by daymade
拆包 repomix 生成的 XML、Markdown、JSON 仓库文件,按原路径批量还原目录和代码,适合反向提取打包结果、审查内容,或把单文件仓库恢复成可直接使用的项目。
✎ 碰到repomix打包仓库时,它能从XML/Markdown/JSON中一键还原原始目录结构,反向解包尤其省事。
by daymade
搭建完整QA流程:按Google Testing Standards写用例、执行测试计划与OWASP安全测试,跟踪P0-P4缺陷,统计覆盖率和进度,并产出第三方团队交接模板。
✎ 测试专家把测试策略、标准化用例、缺陷分级和质量报告一条龙打通,还带 OWASP 安全测试与第三方交接模板,帮团队更快把 QA 做扎实。
by daymade
按官方最佳实践审查并优化 Claude Code Skill,支持自检、评审他人 Skill 仓库,以及 fork 后自动改进并提交 PR,适合发布前验收和开源贡献。
✎ 对照官方最佳实践快速体检并优化 Claude Code 技能,既能自查代审,也能自动提 PR,特别适合高效维护开源技能库。