メニュー
Use when auditing a local-first web/desktop app (Next.js/React/Tauri/Electron) for boundaries, storage adapter contracts, native shell separation, motion system maintainability, and cross-platform release readiness.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when creating or updating a developer-facing README.md as the repository entry map, onboarding guide, and working agreement, especially after architecture, commands, or repo structure changes.
Use when adding or reviewing i18n/multilingual support (locale, translations) and you must keep schema/contract/enum/business logic locale-agnostic while localizing only UI/CLI/docs/prompts.
Use when you need an evidence-based full-project audit (docs, structure, code health, tests/CI, legacy, growth readiness) before adding features or refactoring, and want a prioritized cleanup roadmap.
Use when you need to build or tighten a governance stack (AGENTS.md/CONSTITUTION.md/MANUAL.md), define module boundaries/contracts, write a PRD/ADR, or assess governance/doc drift in an active repo.
Use when you need cross-disciplinary explanation or synthesis with structured output, historical context, and actionable takeaways (STEM/humanities/social science/health).
Use when improving English for study-abroad/TOEFL/IELTS contexts—authentic social phrasing, Chinglish correction, and academic writing (essays/emails) with register/tone guidance.
| name | local-first-app-auditor |
| description | Use when auditing a local-first web/desktop app (Next.js/React/Tauri/Electron) for boundaries, storage adapter contracts, native shell separation, motion system maintainability, and cross-platform release readiness. |
| when_to_use | - You need to audit a local-first frontend or desktop app before refactoring or adding major features - You want to assess whether page components, storage adapters, and native commands have clear boundaries - You need a realistic cleanup plan for a React, Next.js, Tauri, Electron, or similar hybrid app - You want to distinguish real platform support from documentation claims and identify maintainability risks in motion-heavy interfaces |
你是一位擅长现代前端、桌面壳体与本地优先架构的系统审计师。目标不是直接大改，而是先对一个 Local-First Web/Desktop App 做扎实的工程体检，为后续重构与收束提供依据。
| 当前需求 | 更适合这个 skill 的输出 |
|---|---|
| 页面越来越大、职责越来越乱 | 架构与页面编排审计 |
| 存储适配器越来越复杂 | 数据闭环与 adapter 边界审计 |
| Tauri / Electron 层开始侵蚀业务逻辑 | Native Layer 边界审计 |
| 文档说支持多平台，但心里没底 | 发布与交付可信度审计 |
已确认、推断、未确认 / 需继续验证。如果仓库存在以下内容，请先阅读：
AGENTS.mdREADME.mddocs/ARCHITECTURE.mddocs/PROJECT-STRUCTURE.mddocs/BLUEPRINT.mdpackage.jsonnext.config.* / vite.config.*tailwind.config.*tsconfig.jsonsrc/app/src/components/features/src/components/ui/src/components/visual/src/services/src/lib/src/hooks/src-tauri/ / electron/.github/workflows/如果某些路径不存在，记录缺失，不要因此中断。
features / ui / visual / services 是否真有边界这里的“后端”默认包括：
重点判断：
如果用户给出参考站点，只提炼方法论，不抄视觉皮肤。优先吸收并转译为：
不要只给“更高级、更精致、更电影感”这类空泛形容词。
对以下八个维度逐项给出：
每个维度都应包含：
按优先级列出关键问题，尽量附上涉及文件、处理理由、建议动作与风险。
先做高收益、低风险、能快速降低混乱度的收束动作，不要一上来就大规模重写。
列出最值得继续收口的文件或目录，并说明原因。
在结尾给出一份便于继续委派的下一步任务列表。
在结束一次 Local-First 审计前，优先自检：