Claude Skills by whyzsm

Service Widget-style HarmonyOS service widget and meta-service card builder. Use when creating, modifying, explaining, or debugging HarmonyOS service widgets/cards, widget layouts, card resources, widget configuration, form_config.json, widget names, card abilities, static resources, logic insertion, preview/save flows, or when the user mentions Service Widget, serviceWidget, ServiceWidget, meta service, 元服务卡片, 服务卡片, 万能卡片, or CodeGenie Service Widget.

Controls session resume/fork(branch) for /work based on --resume/--fork flags. Updates session.json and session.events.jsonl. Internal workflow use only. Do NOT load for: user session management, login state, app state handling.

Internal sub-skill for session startup checks, Plans.md status, git state, and harness-mem resume pack. Invoked by session/startup workflows only. Do NOT load for: implementation, reviews, or mid-session tasks.

Internal sub-skill for cross-session handoff, durable learning, and memory persistence. Invoked by session/memory workflows only. Do NOT load for: implementation, review, ad-hoc notes, or SSOT editing.

Manages session state transitions per SESSION_ORCHESTRATION.md. Controls state updates at /work phase boundaries, escalated transitions on error, and initialized restoration on session resume. Internal workflow use only. Do NOT load for: user session management, login state, app state handling.

Unified session management window. Handles initialization, memory, state all-in-one. Explicit /session invocation only — sub-skills handle auto-delegation. Use when managing Claude Code sessions, /session command. Do NOT load for: app user sessions, login state, authentication features.

Expert guidance for integrating and building applications with shadcn/ui components, including component discovery, installation, customization, and best practices.

Behavior-preserving code simplification workflow for clarity, consistency, directness, and maintainability. Use when the user asks to simplify code, run /simplify, reduce unnecessary complexity, flatten conditionals, improve naming, or make recently changed code easier to read without changing behavior.

Analyze Codex Skills and agent manifests. Use when the user wants to拆解 a Skill, explain how a Skill or agent is written, or learn how to write one with bilingual Chinese/English guidance, reusable Skill formulas, and templates, especially when the target is an existing SKILL.md or agents/openai.yaml.

设计、生成和验证 Codex Skill 包。用于用户提出创建 Skill、开发 Skill、把流程或专家能力封装成 Skill、把外部专家卡片或提示词转换为 Skill，或需要升级已有 Skill 时；写入前先用 find-skills 再查 SkillHub，核对可复用能力，然后澄清触发场景、输入输出、边界和副作用，最后生成符合约定的 SKILL.md、agents/openai.yaml、引用文件和可选脚本。

Use to optimize/improve an existing agent skill against scored tasks. Ports Microsoft SkillOpt: treats the target SKILL.md as a trainable document and improves it via a rollout→reflect→edit→gate→memory loop with a held-out gate, while keeping the model frozen. Trigger when the user wants to tune, harden, or measurably improve a skill.

Intelligent chart generation and data analysis skill. Reads user-supplied

周报生成器 · Weekly Report Generator skill. Smart Weekly Report skill from

软件产品经理/软件开发经理知识技能。当用户需要产品经理级别的专业支持时触发，包括： 需求分析、PRD撰写、产品设计、产品路线图规划、竞品分析、数据分析； 或用户询问产品经理职责、如何成为产品经理、产品经理技能要求； 或需要产品架构图、流程图、时序图、甘特图等 Mermaid 图表； 或需要从0到1输出PRD文档并自动生成可交互H5原型图； 或需要将PRD文档导出为Markdown(.md)或Word(.docx)格式。 注意：本 skill 采用主动式产品咨询流程。流程：确认需求 → 提问澄清 → 网络搜索 + RAG搜索 → 产品规划 → 方案对比 → 技术选型 → 需求确认 → PRD文档 + Mermaid图表 → 导出格式 → H5原型图（可选）。

Auto-generates comprehensive API docs from code. REST, GraphQL, WebSocket with examples and schemas.

Use when medium-to-large changes need explicit requirements, technical design, and task planning before implementation, especially for multi-module work, unclear acceptance criteria, or architecture-heavy requests.

Comprehensive statistical testing library with 37+ methods for normality tests, location tests, correlation tests, time series tests, and model diagnostics. Use when performing hypothesis testing, A/B testing, data quality checks, time series analysis, or regression model validation. All methods return unified TestResult objects with consistent interface including p-value, statistic, confidence interval, and effect size.

Backtest stock trading strategies on historical OHLCV data and report

记录少儿英语学习情况与家长反馈（本地档案）。适用于学情记录、家长沟通、学员建档、咨询留档等场景。

Use when encountering any bug, test failure, or unexpected behavior. Enforces systematic four-phase debugging: root cause investigation, pattern analysis, hypothesis testing, and evidence-based fix verification.

Use when implementing any feature or bugfix, before writing implementation code - enforces RED-GREEN-REFACTOR cycle: write failing test first, verify it fails, write minimal code, verify it passes, then refactor

Spec-first, TDD, subagent-driven software development workflow. Use when: (1) building any new feature or app — triggers brainstorm → plan → subagent execution loop, (2) debugging a bug or test failure — triggers systematic root-cause process, (3) user says "let's build", "help me plan", "I want to add X", or "this is broken", (4) completing a feature branch — triggers test verification + merge/PR options. NOT for: one-liner fixes (just edit), reading code, or non-code tasks. Requires exec to...

System architecture and modular design workflow for robust, scalable, maintainable software structures. Use when the user asks to design a system, refactor architecture, split modules, define interfaces, choose a stack, create architecture diagrams, or improve project structure with security and scalability in mind.

Taobao Listing skill. Taobao Listing skill from the ecommerce-product-copywriting-team

淘宝产品调研和数据采集工具。用于采集淘宝商品信息，包括主图、标题、价格、销量、评价数、店铺等，并生成包含图片的Excel报告。使用场景：(1)

教师助手全集Skill。覆盖教师日常教学全流程：教案生成、智能出题、成绩分析、家校沟通、教学总结、作业设计、学生档案、班级管理、教学知识卡片生成（可打印PDF）、论文/作业智能批阅（生成批阅报告）。内置8个交互式工具、12个实用模板、5份教学参考。全部功能支持

教师备课助手，用于小学语文教学备课。支持古诗、现代文、寓言、童话等各类课文。当用户提出备课需求时，自动执行：(1)搜索课文相关资料（原文、作者、背景、生字词、段落分析等），生成markdown备课资料；(2)生成教案PPT；(3)生成Word格式课后练习题及参考答案。适用于小学各年级语文备课场景。

专业教案写作助手，基于教学评一致性原则生成符合《义务教育课程标准（2022年版）》的个性化教案。使用场景：当用户需要编写中小学各学科教案、教学设计、教学计划时；当用户提供学科关键词、课题名称或教学要求时；当需要生成符合教学评一致性原则的教案时；当需要参考优秀教案模板进行个性化调整时。

AI编程方法论与中文开发规范专家。用于覆盖头脑风暴、测试驱动开发、系统化调试、代码审查、适配中文文档与国产AI规范。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

AICoding 架构专家团。用于复杂系统架构设计、资料摄入、调研、业务建模、系统设计、部署安全和用户故事交付。来源于 WorkBuddy 技术工程卡片，并转换为 Codex 可安装的专家团入口格式。

API接口开发测试专家。用于专注接口全生命周期，覆盖端点搭建、自动化测试、OpenAPI 文档生成、Mock 和联调。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

End-to-end API documentation workflow. Use when the user wants a complete API documentation expert workflow covering REST/GraphQL API design, OpenAPI/Swagger specs, code-to-doc extraction, API development validation, curl/mock testing, endpoint reference docs, SDK quickstarts, authentication, pagination, error formats, and developer-facing API docs. Coordinates ah-api-designer, sovereign-api-docs-generator, api-dev, api-doc-writer, qa-api-tester, and afrexai-api-docs.

后端架构师。用于深耕分布式系统和高并发架构，擅长将复杂业务转化为优雅技术方案。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

Use this orchestrator skill for end-to-end technical bug troubleshooting in Codex, especially when the user asks for bug 排查, 多 agent debugging, root-cause analysis, log analysis, stack trace diagnosis, runtime error repair, regression-safe fixes, or a complete bug report. It coordinates log-analyzer, debug-pro, code-error-fixer, superpowers-systematic-debugging, bug-fixing-openclaw, and nexus-error-explain when those specialized skills are useful.

End-to-end code refactoring workflow. Use when the user wants a complete refactoring package covering code structure analysis, git-history technical debt signals, Clean Code/SOLID/Clean Architecture review, refactoring pattern selection, target architecture design, behavior-preserving simplification, migration planning, and verification. Coordinates code-analyzer, agent-git-oracle, uncle-bob, code-refactoring, system-architect, and simplify.

End-to-end code review workflow. Use when the user wants a complete code review package covering GitHub PR or git diff intake, strict bug/security/performance review, project coding standards, security auditing, clean-code maintainability checks, and structured Chinese review reports. Coordinates pr-reviewer, critical-code-reviewer, project-code-standard, security-audit, clean-code-review, and code-review-assistant.

开发流水线编排专家。用于编排开发流水线，拆解为测试驱动的细粒度任务，子代理逐任务实现并双重评审。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

DevOps自动化工程师。用于将手动运维自动化，从 CI/CD 到基础设施即代码，部署一键搞定。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

Dockerfile生成专家。用于Dockerfile 自动生成专家，遵循容器化最佳实践。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

嵌入式固件工程师。用于精通微控制器编程，在资源受限硬件上编写高效可靠的固件代码。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

工程保障团队。用于工程总监视角的代码审查、架构评审、ADR、SRE 准备、发布质量闸口和交付风险控制。来源于 WorkBuddy 技术工程卡片，并转换为 Codex 可安装的专家团入口格式。

工程实践专家。用于基于 Google 工程师的 Agent Skills，覆盖规范驱动开发、代码评审、CI/CD 发布。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

前端架构分析专家。用于深度分析前端架构、技术栈、组件设计与构建配置，输出评级和优化建议。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

前端开发工程师。用于精通现代 Web 技术和主流框架，构建响应式高性能 Web 应用。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

Git工作流专家。用于精通 Git 高级工作流和分支策略，让团队协作像行云流水般顺畅。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

事故响应指挥官。用于系统故障时冷静指挥团队快速定位处理和恢复。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

基础设施运维专家。用于确保 IT 基础设施持续稳定运行，一切尽在掌控。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

LSP索引工程师。用于精通语言服务器协议和代码索引技术。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

MCP构建专家。用于精通 Model Context Protocol 设计实现。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

移动应用开发工程师。用于精通 iOS 和 Android 原生及跨平台开发，打造流畅美观的移动应用。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。