android-agent-skills
Production-ready Agent Skills framework for Android Kotlin development. Provides Clean Architecture patterns, Jetpack Compose best practices, validation DSL, MVI state management, error handling, and …
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Production-ready Agent Skills framework for Android Kotlin development. Provides Clean Architecture patterns, Jetpack Compose best practices, validation DSL, MVI state management, error handling, and …
Build full-paper Chinese-English side-by-side, figure/table-aware, source-grounded Markdown readers for journal or conference papers from PDF, DOI, arXiv, publisher HTML, or pasted text. Use whenever …
项目可行性论证与研究报告写作框架 —— 任何「这事能不能做、怎么做、值不值得做」的商业决策场景:可行性研究/立项论证/新项目评估/创业方向验证。10大论证模块 + 强制联网尽调 + 多源交叉验证 + 读者视角写作 + 结构化报告输出。(v1.4 升级:从「引导客户把项目情况讲清楚」到「按问题类型与项目类型选论证方法」再到「用假设台账逐条验证」的六步教练流程;附可行性门槛评分器与假设台账两个零依赖脚…
Use Tavily Search API for optimized, real-time web search results for RAG. A pre-configured, cost-effective search tool.
当用户搜索或需要降级切换,模型Fallback,主备模型,容灾时使用。帮助开发者、AI产品经理、技术负责人、模型采购和成本管理团队完成在主模型不可用或预算超限时选择可接受替代方案,通过AI-HIVE MCP实时核验模型并交付主备模型、触发条件、质量底线、切换日志和恢复规则。不适用于超出以下边界的请求:不得静默切换到更贵模型。
Deploy Alibaba Cloud official tech solutions. Trigger when the user mentions an Alibaba Cloud solution, pastes a solution URL (aliyun.com/solution/tech-solution/...), or wants to deploy an official so…
USE THIS for Gemini models, Google AI. Access Gemini 3 Pro, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.5 Flash Lite. 1 million token context window. No Googl...
USE THIS for web scraping, data extraction, crawling websites. Scrape LinkedIn (profiles, companies, jobs), Twitter/X, Instagram, TikTok, Amazon (products, r...
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, tes…
Optimize and quality control the novel text, check for consistency in writing style, logical consistency, pacing, grammar, and detect sensitive content
生成高质量产品需求文档(PRD),覆盖 B2B SaaS、内部管理系统、数据平台、API 平台、2C 移动端、2C Web 产品等场景。通过结构化访谈、多模板选择、质量校验,产出实施级规格文档。支持国内企业级合规要求(等保/数据安全法/多租户/私有化)及 2C 合规要求(个人信息保护法/内容审核/未成年人保护)。
Mobile app UI design expert for iOS and Android. Use when designing app interfaces, creating design systems, ensuring accessibility, or following platform guidelines. Covers Material Design 3, Human I…
当用户搜索或需要MoE,稀疏模型,Mixture of Experts,模型路由时使用。帮助开发者、AI产品经理、技术负责人、模型采购和成本管理团队完成理解MoE模型的有效参数、速度和成本差异并设计路由,通过AI-HIVE MCP实时核验模型并交付概念说明、任务评测、模型候选、成本表和路由规则。不适用于超出以下边界的请求:不得仅按总参数量判断质量与费用。
Decode - command-line tool for everyday use
Submit and operate PyFlink jobs on Alibaba Cloud Realtime Compute for Apache Flink. Use for storage-routed artifact upload, Python deployment creation or configuration updates, cross-session deploymen…
用 Windows DPAPI 把密钥/口令加密存到本机、仅当前用户可解、明文不落盘、带权限锁与泄漏标注的可复用凭据保管 skill。适合"当前 Windows 账号即信任边界"的本地保管场景。
聘才猫 - 简历诊断 使用时需要调用聘才猫简历诊断助手API来解析和诊断求职者的简历是否符合职位描述。首先需要上传简历文件以获取cos_key。需要设置PCM_RESUME_DIAGNOSIS_KEY环境变量。
>
shadcn/ui for Next.js App Router with TanStack Form. Use when building UI components, forms, dialogs, tables, toasts, or accessible components.
Algebra - command-line tool for everyday use
浏览器自动化技能,通过 browser_action 工具控制 Chrome 浏览器执行多步骤网页操作任务。支持页面导航、元素点击与输入、页面状态提取、截图分析、控制台错误与网络请求监控查询等。适用于网页数据采集、表单自动填写、网页信息查询、多步骤网页交互等场景。
Puzzle - command-line tool for everyday use
Designs and builds Axiom dashboards via API. Covers chart types, APL patterns, SmartFilters, layout, and configuration options. Use when creating dashboards, migrating from Splunk, or configuring char…
Generate UI components, full pages, documents, emails, and assets that strictly follow the EDIC design system (Editorial × Olive Green, OKLch tokens, dark-mode ready, CJK-optimized). Use this skill wh…