All Skills

Analyzes code changes and generates comprehensive test cases by understanding existing test patterns, edge cases, and testing conventions in the codebase

MiniMax TTS API - 文本转语音、声音克隆、声音设计

Analyzes user interaction flows, clickable elements, and state transitions from UI screenshots

Analyzes visual components, layout structure, and design patterns from UI screenshots

Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development

Reviews synthesized task lists for completeness, consistency, and quality

Turn ideas into fully formed designs and specs through natural collaborative dialogue. Use when planning new features, designing architecture, or making significant changes to the codebase.

prompt-creator

Remotion spring physics for motion graphics video production. Bouncy entrances, elastic trails, orchestrated sequences, physics presets, and organic motion patterns that interpolate() alone cannot achieve.

Analyze product screenshots to extract feature lists and generate development task checklists. Use when: (1) Analyzing competitor product screenshots for feature extraction, (2) Generating PRD/task lists from UI designs, (3) Batch analyzing multiple app screens, (4) Conducting competitive analysis from visual references.

ReactBits animations for Remotion - curated for aesthetic excellence in video production

GSAP + Remotion integration for professional motion graphics video production. Timeline orchestration, text splitting, SVG morphing, advanced easing, and reusable effect presets.

Generate article cover images with 5 dimensions (type, palette, rendering, text, mood). Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to 'generate cover image', 'create article cover', or 'make cover'.

Execute implementation tasks from design documents using markdown checkboxes. Use when (1) implementing features from feature-analyzer output, (2) resuming interrupted work, (3) batch executing tasks. Triggers on 'start implementation', 'run tasks', 'resume'.

Three.js 性能优化专家指南，涵盖 WebGPU 渲染器、资源压缩、绘制调用优化、内存管理、着色器优化、光照阴影、React Three Fiber、后处理等100+最佳实践。适用于：(1) 优化 Three.js 项目性能，(2) 迁移到 WebGPU 渲染器，(3) 减少绘制调用和内存泄漏，(4) 实现高效粒子系统和物理模拟，(5) 配置后处理效果，(6) React Three Fiber 性能调优。触发关键词："Three.js 优化"、"WebGPU"、"绘制调用"、"draw calls"、"性能瓶颈"、"内存泄漏"、"TSL 着色器"、"InstancedMesh"、"BatchedMesh"、"R3F 优化"等。

专业的解决方案架构师助手，提供系统架构设计、技术选型、架构评审、性能优化等全方位指导。适用于设计新系统架构、评审现有架构、技术选型决策、架构重构、性能优化、微服务设计等场景。结合网络搜索了解最新技术趋势，提供基于2025年最佳实践的架构建议，涵盖微服务、事件驱动、云原生、AI架构等现代架构模式。

雪峰式AI-Native产品开发方法论。适用于：(1) 用户行为开放、不可穷举的AI-native产品（AI日历、AI助手、AI推荐、对话式产品等），(2) 强模型依赖型场景，AI驱动核心决策而非仅辅助，(3) 多专精Agent架构设计与分工，(4) 上线后快速校准、行为审计与漂移检测，(5) 模型选择和智能路由策略，(6) 概率性输出的质量评估。触发场景包括"AI-native产品怎么做"、"用户行为不可预测怎么办"、"多agent怎么分工"、"模型漂移怎么处理"、"校准到95%太难了"、"唯快不破"、"怎么选模型"、"agent并行分工"、"AI产品上线后怎么迭代"。注意：如果产品是场景明确、边界可定义的+AI类型，请改用 keqian-method skill。即使用户没有明确说"AI-native"，但在讨论AI驱动决策、用户行为不可预测、概率性输出等话题时也应触发。

AI咨询/销售的对话策略助手。当用户需要准备AI方案沟通、跟业务部门聊AI落地、写AI提案、应对客户异议、做AI培训破冰时使用。触发场景："怎么跟老板聊AI"、"客户说AI不靠谱"、"准备一个AI方案汇报"、"帮我想想怎么推AI"、"业务部门不配合"、"AI项目怎么卖"、"demo之后怎么跟进"。也适用于AI咨询师、技术合伙人、CTO做内部AI推广。

专业的微信公众号文章创作助手。当用户提供网站链接、文本素材或图像，需要创作微信公众号文章时使用。支持多种写作风格——企业官号文案、个人技术博客、社区活动回顾、产品评测等。擅长AI/技术话题的深度内容创作，也能产出规范的企业宣传文案。通过搜索工具丰富内容，优化标题和结构。当用户提到"公众号"、"微信文章"、"写一篇推文"、"帮我写篇文章发公众号"等场景时触发。即使用户没有明确说"公众号"，但在要求创作中文长文（技术博客、产品介绍、活动回顾等）时也应考虑触发。

Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.

基于大纲自动研究并生成高质量可视化内容的 Agent Pipeline。 支持两种输出模式：(A) PPTX 演示文稿（PptxGenJS 编程生成，含完整设计系统）； (B) 信息图提示词组图（Notion 手绘风 / 多风格可选，可直接用于 imageGen / DALL·E）。 用户只需提供主题大纲或关键词，skill 自动启动专家子 Agent 并行抓取信息， 主 Agent 负责规划、设计决策和验收，最终输出风格统一的高质量视觉内容。 触发场景："帮我做一组信息图"、"生成 Notion 风格图片"、"做个PPT"、"做个演示文稿"、 "把这个大纲做成图"、"infographic"、"信息图"、"手绘信息图"、"图解"、 "把这篇文章可视化"、"做成社交媒体传播图"、"小红书图文"、"slides"、 "presentation"、"deck"、"pptx"、"演示文稿"、"汇报PPT"。 即使用户没有明确说"信息图"或"PPT"，但在提供大纲/要点并要求可视化传播时也应触发。 当用户上传文章/文稿并要求"做成图"、"可视化"、"做成演示"时，同样触发此 skill。

Save content to GROWI wiki with intelligent path suggestions. Use this skill when the user asks to save, store, or archive content to GROWI. Triggers on: "save to GROWI", "store this in the wiki", "save this page", or any request to persist content in GROWI. Also use when the user uploads a document and wants it stored in GROWI, or after a conversation session the user wants to capture as a wiki page.

资深产品经理助手,提供PRD文档创作与评审、产品策略咨询、留存增长分析、竞品研究、功能优先级排序等全方位产品管理支持。适用于创作或评审PRD/MRD/BRD/用户故事等产品文档；诊断产品问题（留存低、转化差、增长瓶颈）并给出可执行策略；进行竞品分析和市场研究；设计功能方案和用户体验优化。当用户提到"PRD"、"需求文档"、"产品规划"、"用户留存"、"功能设计"、"竞品分析"、"产品指标"、"增长策略"、"用户体验优化"、"功能优先级"等产品管理相关话题时，使用此skill。即使用户没有明确说"产品"，但在讨论App功能设计、用户增长、商业模式、需求分析等话题时也应触发。

Use this skill when the user wants an evidence-based research memo, literature review, market/policy/technical landscape, or a multi-source decision brief with citations, trade-offs, and a clear conclusion. Best for tasks that need synthesis across multiple external sources, iterative follow-up research, or a reusable written artifact. Do not use for quick factual lookups, single-source summaries, simple Q&A, or when the user clearly wants a short answer instead of a report. Chinese trigger examples: "帮我调研", "深度研究", "综述报告", "技术选型分析", "竞品研究", "政策分析". Success = scoped plan, grounded notes, verified citations, explicit limitations, and a final brief/report that clearly separates evidence from analysis.