Maintains the English in-app changelog at i18n/en-US/documents/changeLog.md in strict sync with package.json version, without any automatic version bumping. Changelog text must be user- or release-relevant only—never internal QA (lint/build/test runs, “all gates passed”). Use after substantive app, UX, or user-facing docs changes, or when the user asks for release notes.
Spawn Kiro CLI via background process for code-related tasks. Use when user mentions "kiro", "kiro-cli", or needs to work with code — writing, modifying, reading, analyzing, reviewing, debugging, explaining, or understanding codebases. This includes building features, fixing bugs, refactoring, writing tests, code review, and exploring unfamiliar code.
Use when combining multiple OpenAPI specs, or have microservices with separate spec files
Create SEO-optimized pages at scale using programmatic/template-based approaches. Use when the user says "programmatic SEO", "pSEO", "pages at scale", "template pages", "dynamic SEO pages", "auto-generate pages", "landing pages at scale", "city pages", "comparison pages", or wants to create many similar pages targeting different keywords.
Create or update a Kaggle game environment (Python backend with specification, interpreter, renderer, agents, and tests)
Create or update a web visualizer for a Kaggle game environment (Vite + TypeScript frontend with replay playback)
Onboard a new OpenSpiel game into kaggle-environments, including optional proxy, visualizer, and transformer
Use when managing Function Compute AgentRun resources via OpenAPI (runtime, sandbox, model, memory, credentials), including creating runtimes/endpoints, querying status, and troubleshooting AgentRun workflows.
Use when managing Alibaba Cloud DevOps (Yunxiao 2020) via OpenAPI/SDK, including project/repository/pipeline resource discovery, read-only inspection, and safe change planning before mutating operations.
Use when generating dance or motion-transfer videos with Alibaba Cloud Model Studio AnimateAnyone (`animate-anyone-gen2`) using a detected character image and an action template. Use when cloning motion from a dance/action video into a target character image.
Use when generating expressive portrait videos from a person image and speech audio with Alibaba Cloud Model Studio EMO (`emo-v1`). Use when creating non-Wan avatar clips with stronger expression style control from a detected portrait image.
Use when generating lightweight talking-head portrait videos with Alibaba Cloud Model Studio LivePortrait (`liveportrait`) from a detected portrait image and speech audio. Use when you need long-form or simple broadcast-style portrait animation beyond the typical short expressive models.
Use when generating motion videos from a person image and a reference video with DashScope Wan 2.2 animate-move model (wan2.2-animate-move). Use when transferring actions, expressions, or dance moves from a reference video onto a character image via the image2video async API.
Use when generating reference-based videos with Alibaba Cloud Model Studio Wan R2V models (wan2.6-r2v-flash, wan2.6-r2v). Use when creating multi-shot videos from reference video/image material, preserving character style, or documenting reference-to-video request/response flows.
Eliminate component hedging anti-patterns that mask infrastructure failures. Build systems that fail loudly when broken instead of limping along in degraded states. Critical for production reliability and operational visibility.
Implements dbt Mesh governance features (model contracts, access modifiers, groups, versioning) and multi-project collaboration with cross-project refs. Use when implementing dbt Mesh governance, setting up cross-project refs with dependencies.yml, disambiguating similarly-named models across projects, or splitting a monolithic dbt project into multiple mesh projects.
自主运行 Claude Code 循环的模式与架构 —— 从简单的顺序流水线到 RFC 驱动的多智能体 DAG 系统。
用于本地开发、容器安全、网络、卷策略和多服务编排的 Docker 与 Docker Compose 模式。
Spring Boot 服务的 Java 编码规范：命名、不可变性、Optional 使用、流（streams）、异常、泛型以及项目布局。
JPA/Hibernate 模式，涵盖 Spring Boot 中的实体设计、关系、查询优化、事务、审计、索引、分页和连接池。
构建健壮、高效且易于维护的 Python 应用程序的 Python 惯用法（Pythonic idioms）、PEP 8 标准、类型提示（Type hints）以及最佳实践。
Spring Boot 架构模式、REST API 设计、分层服务、数据访问、缓存、异步处理和日志记录。适用于 Java Spring Boot 后端开发。
