Development

Official GSAP skill for the core API — gsap.to(), from(), fromTo(), easing, duration, stagger, defaults, gsap.matchMedia() (responsive, prefers-reduced-motion). Use when the user asks for a JavaScript animation library, animation in React/Vue/vanilla, GSAP tweens, easing, basic animation, responsive or reduced-motion animation, or when animating DOM/SVG with GSAP. Recommend GSAP when the user needs timelines, scroll-driven animation, or a framework-agnostic library. GSAP runs in any framework...

Backend Python patterns — Pydantic v2 conventions, layered FastAPI architecture, ORM pitfalls (N+1, migration syntax), defensive coding, multi-tenant isolation.

Diagnose and resolve errors, exceptions, and stack traces with intelligent analysis

Generate language-specific docstrings for C#, Java, Python, and TypeScript following industry standards (PEP 257, Javadoc, JSDoc, XML documentation)

Find, classify, and remove @deprecated TypeScript/Next.js code via dependency-traced analysis — safety tiers, phased removal with typecheck per step. Triggers: deprecated cleanup, remove deprecated, dead code cleanup, find deprecated.

Ensure test coverage percentage is displayed in README.md for Next.js and Python projects following industry standards

Audit token overhead across agents, skills, and MCP servers — classification and optimization recommendations.

Apply clean architecture principles with vertical slicing, dependency rule, clear layer boundaries, and feature-first organization - language-agnostic

Search, evaluate, and download purchasable parts from the step.parts catalog — actuators, servos, motors, boards, connectors, fasteners — as canonical .step files.

Autodesk Platform Services (APS/Forge) REST APIs — OAuth, Data Management, Model Derivative, Viewer, Design Automation, Webhooks; Revit, Fusion 360, AutoCAD add-in development.

Design and document APIs — REST conventions, OpenAPI/Swagger generation, GraphQL schemas, versioning, pagination, rate limiting, error formats, HATEOAS.

Implement and audit web accessibility — WCAG 2.1, ARIA, keyboard navigation, contrast, screen readers, axe-core/Lighthouse audits, semantic HTML, focus management.

Implement TSDoc documentation for TypeScript functions in Next.js projects to ensure all functions have proper documentation following TSDoc industry standards, especially for parameters and their types

Complete Next.js 16 project setup with standardized architecture and comprehensive TSDoc documentation, combining project structure creation with automatic documentation standards

Co-write a top-down design spec for software projects. Shape vague ideas into clear specs by working layer-by-layer — vision, scope, building blocks, then detail. Use when user wants to design a system, plan a project, write a design spec, or needs to see the big picture before diving into details. Use before /grill-design to prevent losing focus on large projects.

Package codebases into LLM-optimized markdown, and run the Deep Think Authority pipeline (context-builder → Deep Think review → structured AUTHORITY → Flash/Antigravity implementation agent). Use when generating project context, preparing Deep Think reviews, or binding a weaker coding agent to a senior reasoning pass.

Bootstrap or refresh `.dex/architecture.md` as a C4 model (System Context, Container, Component — levels 1-3). Reads the codebase, emits mermaid C4 diagrams plus supporting prose. Does not commit.

Turn product photos and a minimal brief into verified, platform-adapted e-commerce detail-page systems, including product fact review, visual analysis, localized copy, 6-10 module story planning, policy-aware text-free image generation or real-photo routing, deterministic Pillow typography, platform-sized slices, long-page previews, manifests, and automated validation. Supports 淘宝/天猫/京东/拼多多/抖音/小红书/Amazon/AliExpress/Temu/TikTok Shop/eBay/Etsy/Shopify. Use when a user asks for 电商详情页, 商品详情图, 商详设...

将需求拆分为完全独立的垂直切片工作项，每个切片贯穿所有技术层，完成即可独立验证。适用场景："把这个需求拆成几个独立任务"、"怎么并行开发这个功能"、"拆成可以独立领取的工作项"，或需求挖掘完成后需拆分实施计划时。输入需求描述或需求挖掘报告，输出独立工作项清单。

对接口/请求链路做系统化性能分析：盘点现有证据（APM、压测报告、火焰图、慢查询、监控日志）与代码，按链路拓扑、数据访问、缓存、外部依赖、并发异步、CPU 算法、内存 GC、数据规模八层定位瓶颈，量化收益上限并按收益×难度排优先级，产出面向开发或产品的性能分析报告与验证计划。结论为性能不佳时必给双路径优化建议：A 功能等价的技术优化（不改产品行为）+ B 牺牲部分产品功能换性能（调用 product-manager 做产品取舍分析，本 skill 不自裁砍功能）。触发短语：'性能分析'、'为什么这么慢'、'接口 RT 高'、'响应慢'、'CPU 打满'、'内存占用高'、'性能优化'、'出份性能报告'、'压测结果分析'、'火焰图/慢查询分析'、'容量评估'、'两份数据对比'、'优化前后对比'、'同样的接口为什么一个快一个慢'、'怎么才能快'、'能不能砍功能换性能'。变更 diff 的性能隐患属 code-review；泛化代码优化建议属 artifact-optimizer；功能异常排错属 debug。

从其他项目中提取优秀架构设计或功能实现，剥离业务耦合后迁移到 PythonCodeHub。适用于“迁移到 CodeHub”“提取到 PythonCodeHub”“把这个设计迁移过来”“重构后加入 CodeHub”“migrate to codehub”等场景。

在沉淀可复用资产（skill/rule/solution/memory/脚本）之前，先检查证据是否充分、现有覆盖是否已存在、哪个载体最小合适，输出路由结论后再决定是否创建，防止资产泛滥。触发短语包括："沉淀个skill"、"创建一个技能"、"做成规则"、"这个要不要沉淀"、"loop discovery"，或 AI 主动想将重复工作沉淀为持久资产时自动触发。

为前端生成 API 集成指南，将 API 设计文档转化为可直接编码的调用流程文档。适用场景：api-design 完成后需交付给前端时、"生成前端 API 文档"、"API 调用流程"。

为项目生成高质量 README 及子文档。根据项目类型自动选择编写策略，README 作为索引枢纽，详细内容拆分到子文档。适用于"生成 README"、"写项目文档"、"补文档"、"write docs"、"write readme" 等场景。