skills

Incubate, validate, and refine a raw product idea into an evidence-backed, decision-ready requirement through one durable 12-phase workflow. Use when starting or resuming idea discovery, executing or revising a named incubation phase, answering a pending phase question, or deciding whether an idea should become a formal requirement.

Plan and drive safe old-to-new project or repository migrations with phase-based outputs, risk controls, and migration artifacts. Use when a user needs to: (1) audit an inherited or undocumented project before migration, (2) compare old and new repositories across tooling, architecture, routing, state, request, styling, CI/CD, or release flow, (3) produce migration deliverables such as audits, maps, diff matrices, plans, pilot scopes, adapter plans, risk lists, or verification checklists, (4) execute or update a specific migration phase such as intake, audit, map, diff, plan, pilot, execute, verify, or cleanup.

Clean Code 规范总览与路由，覆盖命名、函数、注释、格式、对象与数据结构、错误处理、边界、测试、类、系统、并发、简单设计、渐进式重构及各类代码坏味道。当用户进行代码审查、重构、写新代码或询问 Clean Code / 整洁代码 / 代码坏味道相关规范时使用，并按主题加载 references 中的对应规则文件。Use for code review, refactor, writing new code, or any clean code / code smell / readability question; routes to the matching rule file under references.

当用户要求将会话中的代码规范、工程约定、架构约束、命名规则、目录结构、测试要求、提交流程、协作规则或 AI 协作规则沉淀为长期可复用的项目规则，或在对话中持续出现这类稳定约束时，调用此 skill。用于识别规则、判断新增/更新/合并/冲突、过滤临时指令，并按职责同步到 .cursor/rules、AGENTS.md、CLAUDE.md。

Use this skill when the user wants to convert one or more existing documents into a dedicated skill, including analyzing suitability, extracting capabilities, designing the skill structure, and drafting SKILL.md and references.

Spec-driven development workflow skill for product requirement intake, engineering research, technical planning, task breakdown, implementation, testing, bugfix loop, and engineering review. Use when a user wants to run or continue a structured software delivery workflow with explicit specs, durable artifacts, and iterative implementation/testing loops.

Use this skill when the user wants to generate, update, or improve usage documentation for a project, file, component, SDK, module, or function based on source code.

Systematically learn and explain the principles of a library, framework, module, function, or code path. Use when a user wants to understand overall architecture, module responsibilities, execution flow, call chains, core data structures, design tradeoffs, implementation details, or interview-ready explanations from source code.

Generate a practical project handover document from the current codebase and project artifacts. Use when a user needs to: (1) prepare resignation or transition handover docs, (2) summarize project architecture and responsibilities, (3) explain deployment, configuration, risks, and pending work for successors, (4) produce a structured, editable handover document grounded in the actual repository.

Minimal Context Sentinel Installer (All-Layers Broadcast). Installs a hard Context Sentinel rule into EVERY detected rule file to force assistant to append a sentinel token to every response. Use when (1) Installing context monitoring via /context-probe, (2) Checking installation status via /context-probe status, (3) Uninstalling via /context-probe off.

Minify verbose prompts into semantically equivalent minimal prompts while preserving behavior. Supports configurable output modes (prompt-only or prompt + compression report).

Create a new dedicated workflow skill by reusing the existing skills-workflow (to collect/normalize a pipeline) and the existing skill-creator (to materialize the new skill). Use when you want a reusable workflow skill without re-entering skill order/templates each time.

Interactive skills workflow for chaining multiple skills where the output of step i becomes the input of step i-1. Use when you need to: (1) Chain multiple skills together in a specific order, (2) Pass outputs between skills as inputs, (3) Execute complex multi-step workflows with traceability, (4) Run skills in dry-run mode before execution, (5) Debug or audit multi-skill workflows

Senior Prompt Engineer and Prompt Interviewer that interviews users to refine and complete their prompts through structured analysis and iterative questioning. Use when a user has an initial prompt but needs help refining it for better LLM performance: (1) When a prompt lacks clarity or context, (2) When constraints or boundaries are missing, (3) When output formats or quality criteria are undefined, (4) When there are ambiguities or conflicting requirements

Autonomous Frontend Code Generation Agent specialized in project-aware API integration. Use when user provides backend API specs needing frontend request code, mock data to convert to request types and handlers, API endpoints to add with types mocks and tests, or new API integration following existing project conventions. Automatically detects TypeScript, request patterns, mock infrastructure, and test frameworks to generate artifact-gated code.

Release workflow for baoyu-skills plugin. Use when user says "release", "发布", "push", "推送", "new version", "新版本", "bump version", "更新版本", or wants to publish changes to remote. Analyzes changes since last tag, updates CHANGELOG (EN/CN), bumps marketplace.json version, commits, and creates version tag. MUST be used before any git push with uncommitted skill changes.

Engineering PRD gatekeeper that validates PRDs against 5 hard quality gates and ensures production-readiness for engineers. Use when reviewing, critiquing, or validating PRDs to ensure: (1) No implicit product decisions are pushed into implementation, (2) Success criteria are testable and verifiable, (3) Failure scenarios and dependencies are explicitly defined, (4) Scope is bounded with enforceable non-goals, (5) Engineering risk is assessable with clear responsibility boundaries.

Comprehensive frontend architecture analyzer that identifies technology stacks, build tools, and architectural patterns. Use when you need to quickly understand a project's structure, dependencies, and technical configuration. Provides analysis for Vue/React/Angular frameworks, Node.js environments, package managers, TypeScript usage, linters, and architecture patterns with multiple output formats including executive summaries and visualizations.

Enhanced dependency analyzer with comprehensive markdown reporting and actionable recommendations. Use when you need to optimize frontend project dependencies, detect security vulnerabilities, identify unused packages, find duplicate functionality, analyze dependency impact, generate cleanup scripts, or produce detailed Markdown reports. Supports JavaScript, TypeScript, Vue, React, Angular, and modern build tools with parallel processing and incremental analysis capabilities.

Intelligent unit test generator for frontend projects that detects existing test frameworks and generates comprehensive tests for functions, components, and modules. Use when you need to: (1) Add unit tests to existing codebases, (2) Set up testing infrastructure for new projects, (3) Generate test cases for specific functions or components, (4) Ensure architectural consistency in testing approach across projects. Supports Jest, Vitest, Mocha with React, Vue, Angular frameworks.

Transform codebases into authentic, interview-defensible resume project experience. Use when analyzing a codebase for: (1) Extracting resume-ready project descriptions, (2) Preparing for technical interview questions about past projects, (3) Understanding the engineering depth and value of a codebase, (4) Identifying defensible technical achievements. Prioritizes correctness and interview credibility over exaggeration.