技術寫作

Evidence-based UI design system from Practical UI by Adham Dannaway (283 pages, 14 chapters). Use when designing interfaces, reviewing UI, creating mockups, building components, or applying design principles. Covers visual hierarchy, spacing systems, color palettes, typography scales, form design, button patterns, accessibility (WCAG 2.1 AA), copywriting, and reducing cognitive load. Triggers on UI design, interface design, component design, design system, accessibility, WCAG, visual hierarchy, spacing, typography, color palette, forms, buttons, layout, grid, or copywriting questions.

プロジェクト内のドキュメント（README.md、CHANGELOG.md、docs/ など）を監査し、コード変更に基づいて更新が必要な箇所を特定・提案します。作業完了後のドキュメント更新確認に使用。

Structured workflow for co-authoring documentation, specs, proposals, and decision docs. Use when user wants to write docs, create specs, draft proposals, or similar structured content.

Pattern for verifying your output matches required schema before completing. Use before writing final output to ensure validity.

Expert in Lighthouse Journey Timeline backend architecture, service patterns, testing, and API development using Express.js, TypeScript, and Drizzle ORM. Use when implementing backend services, APIs, controllers, database queries, authentication, permissions, error handling, testing server code, or writing migrations.

Execute the RED phase of TDD by writing a failing test for the next unmarked item in PLAN.md. Writes tests with Korean descriptions and confirms test failure.

Write clean, readable code with consistent naming, formatting, and structure. Use this skill when writing any code that should follow team conventions. When naming variables, functions, classes, or files. When structuring functions to be small and focused. When removing dead code, avoiding duplication, or applying DRY principles. When configuring formatters or enforcing indentation standards.

Examines git diffs between commits or branches with intelligent analysis. Provides unified diff format with comprehensive summaries including file statistics, rename detection, and merge commit handling. Outputs formatted diffs to /claudedocs for documentation and review purposes.

TDD for process documentation - test with subagents before writing, iterate until bulletproof

Manage Confluence documentation with downloads, uploads, conversions, and diagrams. Use when asked to "download Confluence pages", "upload to Confluence", "convert Wiki Markup", "sync markdown to Confluence", "create Confluence page", or "handle Confluence images".

Guides BDD example-writing: intent-based steps, observable outcomes, and mapping steps to services.

Write strategic, behavior-focused tests for critical paths without over-testing during development. Use this skill when writing unit tests, integration tests, or end-to-end tests. When working on files in tests/, __tests__/, spec/, or any test files. When deciding what to test, naming test cases, or mocking external dependencies. When focusing on core user flows rather than edge cases during feature development.

ARCHIVE REFERENCE ONLY. Superseded by active `campaign-page-copy` skill. Use this as inspiration, not for invocation in the orchestrated flow.

End-to-end testing for Blazor applications using Playwright for .NET. Use when writing E2E tests, creating test infrastructure, testing MudBlazor components, handling Blazor WebAssembly loading, debugging test failures, or setting up CI/CD test pipelines.

Use when unsure about command syntax, options, or behavior, or when the user asks to "check the man page", "look up the manual", or "what does [command] do". Consult system man pages for accurate, version-specific documentation.

Structured investigation with a persistent markdown log and evidence-first execution. Use when: investigating a user question, auditing behavior, verifying dependencies, or using MCP tools. Triggers: inspect, investigate, analyze, audit, verify, deepwiki. Default mode: MANIFEST_IO.

Use when implementing features or refactoring with TDD - enforces writing ONE test at a time, implementing minimal code to pass, then repeating, preventing batch test writing that defeats incremental design discovery

Expert prompt engineering for LLMs and AI agents. Use when users request help writing, reviewing, or improving prompts for chatbots, AI agents, system prompts, instruction sets, or any LLM-based application. Applies research-backed techniques to minimize hallucinations and maximize reliability.

Manage and maintain VRP Toolkit skills through compliance checking, audit tracking, and documentation synchronization. Use when (1) adding or modifying skills, (2) checking skill compliance with project standards, (3) auditing SKILLS.md vs skills directory consistency, (4) recording skill changes to SKILLS_LOG.md, or (5) performing periodic skill health checks. Ensures skills stay independent, under 500 lines, properly structured, and well-documented.

Read and extract content from PDF files using multiple methods.LOAD THIS SKILL WHEN: User says "讀取 PDF", "read PDF", "打開論文", "看這篇" | has PDF file path | needs to extract text from PDF.CAPABILITIES: PDF to markdown conversion, text extraction, figure detection, citation extraction.