@bovinphang/frontend-craft 2.8.0 → 3.0.0

package/README.openclaw.md

@@ -22,6 +22,8 @@
 
 `frontend-craft` ships the OpenClaw-native package for [frontend-craft](https://github.com/bovinphang/frontend-craft): workflow skills, markdown commands, OpenClaw workspace templates, typed hooks, a design MCP reference, and the optional `frontend_craft_init_workspace` tool.
 
+The native package includes **74 workflow skills** and **11 commands exposed through skills (same-name workflows reuse the full skill)**. The 14 specialized agents belong to other runtime adapters and are not native OpenClaw agents.
+
 **Requirements:** Node.js **>= 22**, OpenClaw plugin API **>= 2026.4.20**.
 
 ---
@@ -45,9 +47,9 @@ openclaw plugins install frontend-craft
 From a local tarball built from the main repository:
 
 ```bash
-npm install
-npm run pack:openclaw
-openclaw plugins install ./frontend-craft-<version>.tgz
+pnpm install --frozen-lockfile
+pnpm run pack:openclaw
+openclaw plugins install ./npm-packages/openclaw/frontend-craft-<version>.tgz
 ```
 
 For local development, link the package directory:
@@ -122,7 +124,7 @@ Pixso uses the local MCP URL shown in `.mcp.json`. MockingBot has no MCP integra
 frontend-craft/
 |-- dist/                  # Bundled OpenClaw plugin entry
 |-- skills/                # Workflow skills
-|-- commands/              # Markdown command specs loaded as skills
+|-- commands/              # Source command specs; converted skills are under skills/
 |-- templates/openclaw/    # OpenClaw AGENTS.md and config notes
 |-- templates/shared/      # Shared frontend rules
 |-- .mcp.json              # Design MCP reference
@@ -136,7 +138,7 @@ frontend-craft/
 
 ### Skills
 
-The OpenClaw package includes all 45 public workflow skills from `skills/`, grouped here by use case.
+The OpenClaw package includes all 74 public workflow skills from `skills/`, grouped here by use case.
 
 **Project standards**
 
@@ -148,7 +150,7 @@ The OpenClaw package includes all 45 public workflow skills from `skills/`, grou
 | `fec-nuxt-project-standard`      | Nuxt 3 SSR/SSG, composables, routing, middleware                      |
 | `fec-vite-project-standard`      | Vite config, env safety, HMR, dev proxy, build optimization           |
 | `fec-monorepo-project-standard`  | pnpm workspace, Turborepo, Nx structure and task orchestration        |
-| `fec-typescript-project-standard` | TypeScript config, public API types, declarations, DTOs, and generics |
+| `cc-typescript-project-standard` | TypeScript config, public API types, declarations, DTOs, and generics |
 
 **Implementation capabilities**
 
@@ -188,13 +190,29 @@ The OpenClaw package includes all 45 public workflow skills from `skills/`, grou
 | `fec-performance-optimization` | Core Web Vitals, bundle, rendering, memory, network, and budget reviews         |
 | `fec-refactor-clean`           | Safe dead-code, unused export, style, route, and dependency cleanup             |
 
+**Refactoring**
+
+| Skill | Purpose |
+| --- | --- |
+| `fec-refactoring` | Behavior-preserving refactoring orchestration and safety workflow |
+| `fec-code-smells` | Evidence-based diagnosis of 24 canonical code smells |
+| `fec-refactoring-catalog` | Selection and composition across 61 canonical techniques |
+| `fec-refactoring-functions` | Function-level refactorings |
+| `fec-refactoring-encapsulation` | Encapsulation refactorings |
+| `fec-refactoring-move-features` | Moving-feature refactorings and cleanup routing |
+| `fec-refactoring-data` | Data refactorings |
+| `fec-refactoring-control` | Conditional/control-flow refactorings |
+| `fec-refactoring-api` | API refactorings |
+| `fec-refactoring-inheritance` | Inheritance/delegation refactorings |
+| `fec-refactoring-validation` | Behavior-preservation verification and proof levels |
+
 **Design UI**
 
 | Skill                         | Purpose                                                                              |
 | ----------------------------- | ------------------------------------------------------------------------------------ |
 | `fec-ui-design`               | UI direction, visual identity, polish, states, visual QA                             |
-| `fec-image-generation`        | Diagrams, image generation/editing, visual assets, and PNG QA repair loops           |
-| `fec-drawio-studio`           | Editable draw.io / diagrams.net technical diagrams, shape lookup, and code maps      |
+| `fec-image-generation`        | UI, product and brand image generation/editing with shared PNG QA |
+| `cc-drawio-studio`           | Editable draw.io / diagrams.net technical diagrams, shape lookup, and code maps      |
 | `fec-web-video-presentation`  | Recordable 16:9 step-driven web presentations from articles, scripts, lessons, demos |
 | `fec-tailwind-design-system`  | Tailwind tokens, theme extension, variants, class governance, dark mode              |
 | `fec-responsive-layout`       | Mobile-first layouts, container queries, data-dense responsive UI                    |
@@ -202,6 +220,10 @@ The OpenClaw package includes all 45 public workflow skills from `skills/`, grou
 | `fec-implement-from-design`   | Implement UI from Figma, Sketch, MasterGo, Pixso, Modao, or screenshots              |
 | `fec-storybook-component-doc` | Storybook component docs, design-system presentation, isolated state previews        |
 
+Technical diagram quality: `cc-technical-diagrams` prefers local Mermaid for standard sequence/workflow diagrams and the draw.io workflow for editable architecture, with JSON/HTML fallback when tools are unavailable. Export a browser-measured manifest scaled to the PNG, run QA and inspect the final image. Preserve complete text, explicit layout and relationships; repair the source for at most two automatic rounds and report unresolved issues. Reproducible fixtures are in `skills/cc-technical-diagrams/assets/quality-examples/`.
+
+[Review and technical diagram guide](docs/review-and-diagram-workflows.md).
+
 **Legacy migration**
 
 | Skill                            | Purpose                                                                     |
@@ -221,11 +243,11 @@ The OpenClaw package includes all 45 public workflow skills from `skills/`, grou
 | ------------------------------- | ---------------------------------------------------------------------------------- |
 | `fec-backend-requirements-handoff` | Frontend-to-backend handoff for UI data needs, actions, states, rules, questions |
 | `fec-doc-sync`                  | Keep frontend docs in sync with code, config, scripts, routes, APIs, and env facts |
-| `fec-source-driven-development` | Verify version-sensitive frontend decisions against project facts and sources      |
+| `cc-source-driven-development` | Verify version-sensitive frontend decisions against project facts and sources      |
 
 ### Using skills (scenarios & examples)
 
-Skills live under `skills/<id>/SKILL.md`. OpenClaw exposes them as plugin skill roots (`openclaw.plugin.json` lists `skills` and `commands`). The harness typically **auto-selects** a workflow when your plain-language request matches a skill’s frontmatter `description`; exact behavior depends on your OpenClaw / agent setup. You do **not** need to know internal skill ids—describe the outcome you want. (Power users may still mention an id if they know it.)
+Skills live under `skills/<id>/SKILL.md`. OpenClaw exposes them as plugin skill roots (`openclaw.plugin.json` lists `skills`; command workflows are converted during packaging). The harness typically **auto-selects** a workflow when your plain-language request matches a skill’s frontmatter `description`; exact behavior depends on your OpenClaw / agent setup. You do **not** need to know internal skill ids—describe the outcome you want. (Power users may still mention an id if they know it.)
 
 This section is a quick OpenClaw-oriented sample, not the full prompt catalog. For complete scenario-based prompts across skills, agents, commands, design workflows, testing, maintenance, and runtime setup, see [docs/example-prompts.md](docs/example-prompts.md).
 
@@ -239,7 +261,7 @@ This section is a quick OpenClaw-oriented sample, not the full prompt catalog. F
 
 | Scenario                                   | Skill (reference)                | Example prompt (no skill names)                                                                                                                  |
 | ------------------------------------------ | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |
-| PR or branch review before merge           | `fec-code-review`                | “Please review `src/features/checkout/` before I merge: architecture, types, a11y, and tests. Save a markdown report under `reports/`.”          |
+| Review a specified directory           | `fec-code-review`                | “Please review `src/features/checkout/` before I merge: architecture, types, a11y, and tests. Save a markdown report under `reports/`.”          |
 | Focus on XSS, secrets, dangerous DOM       | `fec-security-review`            | “Audit `src/lib/auth.ts` and anything that renders or stores user-controlled HTML for XSS and secret leaks; list fixes by severity.”             |
 | New dialog / form — keyboard & ARIA        | `fec-accessibility-check`        | “Check `src/components/ConfirmDialog.tsx` for keyboard traps, focus order, labels, and ARIA; suggest concrete fixes.”                            |
 | Align a React module with team conventions | `fec-react-project-standard`     | “We use React 18 and TanStack Query. Review `src/pages/Dashboard/` against solid React + TS patterns and our existing abstractions.”             |
@@ -281,6 +303,9 @@ These are loaded as command specs; use them when you want a **fixed checklist**
 | `fec-tdd.md`             | Red-green-refactor implementation workflow.                                                                 | “Use a TDD loop for this filter component: write the failing test first, then implement the minimum behavior.”                |
 | `fec-debug.md`           | Diagnose build, runtime, UI, or API/data failures.                                                          | “The dashboard crashes after login; inspect the error path, isolate the cause, and write a debug report.”                    |
 | `fec-refactor-clean.md`  | Classify and safely remove dead code, unused exports, styles, and dependencies.                              | “Clean up unused exports and styles in `src/features/billing/`, preserving behavior and reporting what changed.”             |
+| `fec-smell.md`         | Diagnose structural code smells without changing business code.                                         | “Find code smells in `Compose.tsx`, show evidence, but do not edit it.”                                                       |
+| `fec-refactor-plan.md` | Build an ordered behavior-preserving refactoring plan.                                                   | “Plan a safe refactor for this large compose module before editing.”                                                          |
+| `fec-refactor.md`      | Execute behavior-preserving refactoring one validated step at a time.                                   | “Refactor this module without changing observable behavior, validating every step.”                                           |
 | `fec-doc-sync.md`        | Sync README, docs, env notes, script lists, API/route notes, and deploy facts.                               | “Check whether the README command list still matches package scripts and update the docs that drifted.”                      |
 
 ### Hooks
@@ -318,3 +343,53 @@ npm run pack:openclaw
 ## License
 
 MIT
+
+### Review scope
+
+Code and security review skills use three modes. In OpenClaw, request them in natural language; the slash-command examples below apply to runtimes that expose `/fec-review`:
+
+- **Change review:** explicitly request recent/current/staged changes, a PR or a commit, or use an established change context. With no changes, report that there is nothing to review; do not automatically review recent commits.
+- **Targeted review:** specify a file or directory to review existing code, including unchanged code, without requiring a Git diff.
+- **Project review (default):** with no scope or change context, or when the entire project is requested, inventory project-owned frontend code, related tests, configuration and dependency declarations, then review by module.
+
+A file/directory request reviews its full contents; add "recent changes" to review only its diff. A natural-language request such as "Review the code" reviews the project even when changes exist. State mode and scope before review. Automatic review after edits must pass the current change scope explicitly.
+
+Examples: `/fec-review`,`/fec-review review recent changes`,  `/fec-review review src/components/Button.tsx`, `/fec-review review src/features/`, and `/fec-review review the entire project`. These are natural-language instructions, not CLI flags. Explicit scope takes precedence over the default.
+
+Dependency directories, build outputs, caches, generated files and third-party code are excluded by default. Reports record the mode, target scope, reviewed and unreviewed files/modules, exclusions, completion status and verification results. Limited coverage is marked partial; reading callers or running project-wide lint/typecheck does not establish manual review coverage. Change reviews retain merge recommendations; targeted/project reviews assess risk within reviewed scope. The frontend review does not replace a backend audit, and reviewers do not edit business code unless repairs are requested.
+
+## Common capabilities
+
+Shared capabilities are delivered from craft-common with this product:
+
+- `cc-debug-methodology`
+- `cc-doc-sync-core`
+- `cc-drawio-studio`
+- `cc-refactoring-core`
+- `cc-source-driven-development`
+- `cc-tdd-methodology`
+- `cc-technical-diagrams`
+
+## Cross-domain language capabilities
+
+These common entries apply to libraries, CLI tools, desktop cores and services; product names do not constrain languages.
+
+| Skill | Purpose |
+| --- | --- |
+| `cc-c-project-standard` | C project engineering |
+| `cc-cpp-project-standard` | C++ project engineering |
+| `cc-go-concurrency` | Go concurrency lifecycle |
+| `cc-go-project-standard` | Go project engineering |
+| `cc-java-project-standard` | Java project engineering |
+| `cc-java-runtime` | Java runtime diagnosis |
+| `cc-native-memory-safety` | Native memory and FFI safety |
+| `cc-python-async` | Python async lifecycle |
+| `cc-python-project-standard` | Python project engineering |
+| `cc-rust-async` | Rust async lifecycle |
+| `cc-rust-project-standard` | Rust project engineering |
+| `cc-typescript-project-standard` | TypeScript project specifications |
+
+| `cc-tauri-project-standard` | Tauri application engineering |
+| `cc-electron-project-standard` | Electron application engineering |
+
+The common dependency is pinned exactly to craft-common 2.0.0, prepared for publication. Frontend3.0.0 and backend 1.0.0 remain unreleased with unchanged versions; publishing common does not publish or activate this native plugin.

package/README.openclaw.zh-CN.md

@@ -22,6 +22,8 @@
 
 `frontend-craft` 是 [frontend-craft](https://github.com/bovinphang/frontend-craft) 的 OpenClaw 原生打包产物，包含工作流技能、Markdown 命令、OpenClaw 工作区模板、typed hooks、设计工具 MCP 参考配置，以及可选的 `frontend_craft_init_workspace` 初始化工具。
 
+该原生包提供 **74 个工作流技能**，并将 **11 个命令工作流通过技能提供（同名工作流复用完整技能）**。14 个专业 Agent 属于其他运行时适配器，不是 OpenClaw 原生 Agent。
+
 **环境要求：** Node.js **>= 22**，OpenClaw plugin API **>= 2026.4.20**。
 
 ---
@@ -45,9 +47,9 @@ openclaw plugins install frontend-craft
 从主仓库构建出的本地 tarball 安装：
 
 ```bash
-npm install
-npm run pack:openclaw
-openclaw plugins install ./frontend-craft-<version>.tgz
+pnpm install --frozen-lockfile
+pnpm run pack:openclaw
+openclaw plugins install ./npm-packages/openclaw/frontend-craft-<version>.tgz
 ```
 
 本地开发时可链接包目录：
@@ -122,7 +124,7 @@ Pixso 使用 `.mcp.json` 中的本地 MCP URL。摹客暂无 MCP 集成，请使
 frontend-craft/
 |-- dist/                  # 打包后的 OpenClaw 插件入口
 |-- skills/                # 工作流技能
-|-- commands/              # 作为技能加载的 Markdown 命令说明
+|-- commands/              # 命令源文件；转换后的技能位于 skills/
 |-- templates/openclaw/    # OpenClaw AGENTS.md 与配置说明
 |-- templates/shared/      # 共享前端规则
 |-- .mcp.json              # 设计工具 MCP 参考配置
@@ -136,7 +138,7 @@ frontend-craft/
 
 ### 技能
 
-OpenClaw 包包含 `skills/` 下全部 45 个公开工作流技能，按使用场景分组如下。
+OpenClaw 包包含 `skills/` 下全部 74 个公开工作流技能，按使用场景分组如下。
 
 **项目规范**
 
@@ -148,7 +150,7 @@ OpenClaw 包包含 `skills/` 下全部 45 个公开工作流技能，按使用
 | `fec-nuxt-project-standard`      | Nuxt 3 SSR/SSG、组合式函数、路由、中间件            |
 | `fec-vite-project-standard`      | Vite 配置、环境变量安全、HMR、开发代理、构建优化    |
 | `fec-monorepo-project-standard`  | pnpm workspace、Turborepo、Nx 结构与任务编排        |
-| `fec-typescript-project-standard` | TypeScript 配置、公开类型、声明文件、DTO 和泛型     |
+| `cc-typescript-project-standard` | TypeScript 配置、公开类型、声明文件、DTO 和泛型     |
 
 **实现能力**
 
@@ -188,13 +190,29 @@ OpenClaw 包包含 `skills/` 下全部 45 个公开工作流技能，按使用
 | `fec-performance-optimization` | Core Web Vitals、bundle、渲染、内存、网络和预算评审      |
 | `fec-refactor-clean`           | 安全清理死代码、未用导出、样式、路由与依赖               |
 
+**重构**
+
+| 技能 | 用途 |
+| --- | --- |
+| `fec-refactoring` | 保持行为的重构编排与安全工作流 |
+| `fec-code-smells` | 基于证据诊断 24 种标准代码坏味道 |
+| `fec-refactoring-catalog` | 在 61 项标准手法中选择和组合 |
+| `fec-refactoring-functions` | 函数类重构 |
+| `fec-refactoring-encapsulation` | 封装类重构 |
+| `fec-refactoring-move-features` | 搬移特性类重构与清理路由 |
+| `fec-refactoring-data` | 数据重构 |
+| `fec-refactoring-control` | 条件/控制流重构 |
+| `fec-refactoring-api` | API 重构 |
+| `fec-refactoring-inheritance` | 继承/委托重构 |
+| `fec-refactoring-validation` | 行为保持验证与证明等级 |
+
 **设计 UI**
 
 | 技能                          | 用途                                                       |
 | ----------------------------- | ---------------------------------------------------------- |
 | `fec-ui-design`               | UI 方向、视觉识别、界面打磨、状态与视觉 QA                 |
-| `fec-image-generation`        | 图表、图片生成/编辑、视觉资产与 PNG QA 修复循环            |
-| `fec-drawio-studio`           | 可编辑 draw.io / diagrams.net 技术图、形状检索与代码结构图 |
+| `fec-image-generation`        | UI、产品和品牌视觉生成与编辑，复用公共 PNG 质检 |
+| `cc-drawio-studio`           | 可编辑 draw.io / diagrams.net 技术图、形状检索与代码结构图 |
 | `fec-web-video-presentation`  | 将文章、口播稿、课程和 demo 转成可录屏的 16:9 步进网页演示 |
 | `fec-tailwind-design-system`  | Tailwind token、主题扩展、组件变体、class 治理和暗色模式   |
 | `fec-responsive-layout`       | 移动优先布局、容器查询、数据密集型响应式界面               |
@@ -202,6 +220,10 @@ OpenClaw 包包含 `skills/` 下全部 45 个公开工作流技能，按使用
 | `fec-implement-from-design`   | 基于 Figma、Sketch、MasterGo、Pixso、墨刀或截图实现 UI     |
 | `fec-storybook-component-doc` | Storybook 组件文档、设计系统展示与隔离状态预览             |
 
+技术图质量工作流：`cc-technical-diagrams` 的标准时序/流程图优先本地 Mermaid，架构图复用 draw.io 工作流，工具缺失时使用 JSON/HTML。导出 PNG 时生成实际测量且与缩放一致的 manifest，再运行 QA 并检查最终 PNG；保留完整文字、显式布局与关系，最多自动修复两轮，未解决问题需明确报告。可复现样例位于 `skills/cc-technical-diagrams/assets/quality-examples/`。
+
+[审核范围与技术图交付指南](docs/zh-CN/review-and-diagram-workflows.md).
+
 **遗留迁移**
 
 | 技能                             | 用途                                       |
@@ -221,11 +243,11 @@ OpenClaw 包包含 `skills/` 下全部 45 个公开工作流技能，按使用
 | ------------------------------- | -------------------------------------------------------- |
 | `fec-backend-requirements-handoff` | 面向后端交接 UI 数据需求、用户动作、状态、规则和问题   |
 | `fec-doc-sync`                  | 同步 README、配置、脚本、路由/API、环境变量与部署事实   |
-| `fec-source-driven-development` | 根据项目事实和官方来源校验版本敏感的前端决策             |
+| `cc-source-driven-development` | 根据项目事实和官方来源校验版本敏感的前端决策             |
 
 ### 技能使用：场景与示例
 
-技能定义在 `skills/<id>/SKILL.md`。本插件在 `openclaw.plugin.json` 中将 `skills` 与 `commands` 注册为技能根。运行时一般会按各技能前置元数据里的 **description** 与当前任务做 **自动匹配**；具体行为取决于你的 OpenClaw / Agent 配置。**普通用户不必知道内部技能 id**，用自然语言说明目标即可；熟悉仓库的人若知道 id 也可以显式写出。
+技能定义在 `skills/<id>/SKILL.md`。本插件在 `openclaw.plugin.json` 中将 `skills` 注册为技能根；命令工作流在打包时转换为技能。运行时一般会按各技能前置元数据里的 **description** 与当前任务做 **自动匹配**；具体行为取决于你的 OpenClaw / Agent 配置。**普通用户不必知道内部技能 id**，用自然语言说明目标即可；熟悉仓库的人若知道 id 也可以显式写出。
 
 本节是面向 OpenClaw 的快速示例，不是完整提示词清单。完整的按场景组织的提示词库覆盖 skills、agents、commands、设计工作流、测试、维护和 runtime 初始化，见 [docs/zh-CN/example-prompts.md](docs/zh-CN/example-prompts.md)。
 
@@ -239,7 +261,7 @@ OpenClaw 包包含 `skills/` 下全部 45 个公开工作流技能，按使用
 
 | 场景                         | 技能（供查阅）                   | 示例话术（不出现技能名）                                                                                                               |
 | ---------------------------- | -------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- |
-| 合并前做 PR / 分支评审       | `fec-code-review`                | 「合并前请评审 `src/features/checkout/`：架构、类型、无障碍和测试；把 Markdown 报告写到 `reports/`。」                                 |
+| 指定目录评审       | `fec-code-review`                | 「合并前请评审 `src/features/checkout/`：架构、类型、无障碍和测试；把 Markdown 报告写到 `reports/`。」                                 |
 | 聚焦 XSS、密钥、危险 DOM     | `fec-security-review`            | 「请审计 `src/lib/auth.ts` 以及所有渲染或存储用户 HTML 的代码，按严重程度列出 XSS 与密钥泄露风险及修复建议。」                         |
 | 新弹窗 / 表单 — 键盘与 ARIA  | `fec-accessibility-check`        | 「检查 `src/components/ConfirmDialog.tsx` 的键盘陷阱、焦点顺序、标签与 ARIA，并给出可落地的修改建议。」                                |
 | 对齐 React 工程约定          | `fec-react-project-standard`     | 「我们使用 React 18 和 TanStack Query，请对照成熟 React + TS 实践评审 `src/pages/Dashboard/`，并贴合现有抽象。」                       |
@@ -281,6 +303,9 @@ OpenClaw 包包含 `skills/` 下全部 45 个公开工作流技能，按使用
 | `fec-tdd.md`             | 使用 red-green-refactor 的测试驱动实现流程。                                             | 「这个筛选组件请按 TDD 做：先写失败测试，再实现最小行为。」                                                       |
 | `fec-debug.md`           | 诊断构建、运行时、UI 或 API/data 失败。                                                  | 「登录后 dashboard 崩溃，请检查错误路径、定位根因，并写一份 debug 报告。」                                        |
 | `fec-refactor-clean.md`  | 分类并安全清理死代码、未用导出、样式和依赖。                                             | 「清理 `src/features/billing/` 里的未用导出和样式，保持行为不变并报告变更。」                                     |
+| `fec-smell.md`         | 诊断结构代码坏味道，不修改业务代码。                                                     | 「找出 `Compose.tsx` 的代码坏味道并给出证据，先不要改。」                                                       |
+| `fec-refactor-plan.md` | 生成有顺序、保持行为的小步重构计划。                                                     | 「先为这个大型写信模块设计安全重构计划，不改代码。」                                                         |
+| `fec-refactor.md`      | 一次执行一个经过验证的保持行为重构步骤。                                                 | 「保持可观察行为不变地重构这个模块，并逐步验证。」                                                           |
 | `fec-doc-sync.md`        | 同步 README、文档、环境说明、脚本列表、API/路由说明和部署事实。                          | 「检查 README 命令列表是否还匹配 package scripts，并更新漂移的文档。」                                            |
 
 ### Hooks
@@ -318,3 +343,53 @@ npm run pack:openclaw
 ## License
 
 MIT
+
+### 审核范围
+
+代码和安全审核 skill 采用三种模式。在 OpenClaw 中使用自然语言提出请求；以下斜杠命令示例适用于提供 `/fec-review` 的运行时：
+
+- **改动审核**：明确要求最近改动、本次修改、暂存区、PR 或提交，或当前任务已明确这些改动上下文。无改动时说明没有可审核的改动，不自动审核最近提交。
+- **指定范围审核**：指定文件或目录，审核其中现有代码，包括未改动代码，不要求 Git 差异。
+- **全项目审核（默认）**：未指定范围或改动上下文，或明确要求审核整个项目时，先建立项目自有前端代码、相关测试、配置和依赖声明清单，再按模块审核。
+
+指定文件或目录默认审核其全部代码；加上“本次改动”才仅审核差异。自然语言请求“审核代码”即使有改动也默认全项目；开始时说明模式和范围，修改后自动委托审核须显式传入本次改动范围。
+
+示例：`/fec-review`、`/fec-review 审核最近改动`、`/fec-review 审核 src/components/Button.tsx`、`/fec-review 审核 src/features/`、`/fec-review 审核整个项目`。这些是自然语言指令，不是 CLI 参数；明确指定的范围优先于默认模式。
+
+默认排除依赖目录、构建产物、缓存、生成文件和第三方代码。报告记录模式、目标范围、已审核及未覆盖文件或模块、排除项、完成状态和验证结果；覆盖不足时标记部分完成。读取调用方或执行全项目 lint/类型检查不等于完成人工审核。改动审核保留合并建议，指定范围和全项目审核评估已审核范围的风险。前端审核不替代后端专项审核；未要求修复时不修改业务代码。
+
+## 公共能力
+
+公共能力由 craft-common 随产品提供：
+
+- `cc-debug-methodology`
+- `cc-doc-sync-core`
+- `cc-drawio-studio`
+- `cc-refactoring-core`
+- `cc-source-driven-development`
+- `cc-tdd-methodology`
+- `cc-technical-diagrams`
+
+## 跨领域语言能力
+
+以下公共入口同时用于库、CLI、桌面核心和服务，不按前后端划分语言。
+
+| Skill | 用途 |
+| --- | --- |
+| `cc-c-project-standard` | C 工程规范 |
+| `cc-cpp-project-standard` | C++ 工程规范 |
+| `cc-go-concurrency` | Go 并发生命周期 |
+| `cc-go-project-standard` | Go 工程规范 |
+| `cc-java-project-standard` | Java 工程规范 |
+| `cc-java-runtime` | Java 运行时诊断 |
+| `cc-native-memory-safety` | 原生内存与 FFI 安全 |
+| `cc-python-async` | Python 异步生命周期 |
+| `cc-python-project-standard` | Python 工程规范 |
+| `cc-rust-async` | Rust 异步生命周期 |
+| `cc-rust-project-standard` | Rust 工程规范 |
+| `cc-typescript-project-standard` | TypeScript 项目规范 |
+
+| `cc-tauri-project-standard` | Tauri 应用工程 |
+| `cc-electron-project-standard` | Electron 应用工程 |
+
+公共依赖精确固定为craft-common2.0.0，当前待发布；frontend3.0.0和backend1.0.0继续未发布，版本号不变。发布common不自动发布或启用本原生插件。