@pzy560117/codex-harness 0.1.0 → 0.1.1

package/package-source/docs/codex-harness-engineering/templates/package-assets/skills/vue-arco/SKILL.md

@@ -0,0 +1,119 @@
+---
+name: vue-arco
+description: Vue 3 + Arco Design 开发指南
+---
+
+# Vue 3 + Arco Design 开发指南
+
+## 项目结构
+
+```
+WHartTest_Vue/src/
+├── api/              # API 请求封装
+├── components/       # 通用组件
+├── composables/      # 组合式函数
+├── config/           # 配置文件
+├── features/         # 功能模块
+├── layouts/          # 布局组件
+├── router/           # 路由配置
+├── services/         # 业务服务
+├── store/            # Pinia Store
+├── utils/            # 工具函数
+└── views/            # 页面视图
+```
+
+## 开发规范
+
+### 组件定义 (Composition API)
+```vue
+<script setup lang="ts">
+import { ref, computed, onMounted } from 'vue'
+import { Message } from '@arco-design/web-vue'
+
+interface Props {
+  title: string
+  loading?: boolean
+}
+
+const props = withDefaults(defineProps<Props>(), {
+  loading: false
+})
+
+const emit = defineEmits<{
+  (e: 'submit', data: any): void
+}>()
+
+const data = ref<string[]>([])
+
+onMounted(async () => {
+  // 初始化逻辑
+})
+</script>
+
+<template>
+  <a-card :title="title" :loading="loading">
+    <slot />
+  </a-card>
+</template>
+```
+
+### Pinia Store
+```typescript
+import { defineStore } from 'pinia'
+import { ref, computed } from 'vue'
+
+export const useMyStore = defineStore('my', () => {
+  const items = ref<Item[]>([])
+  const loading = ref(false)
+
+  const itemCount = computed(() => items.value.length)
+
+  async function fetchItems() {
+    loading.value = true
+    try {
+      items.value = await api.getItems()
+    } finally {
+      loading.value = false
+    }
+  }
+
+  return { items, loading, itemCount, fetchItems }
+})
+```
+
+### API 封装
+```typescript
+import axios from 'axios'
+
+const api = axios.create({
+  baseURL: import.meta.env.VITE_API_BASE_URL,
+  timeout: 30000
+})
+
+export const myApi = {
+  getList: () => api.get('/api/items/'),
+  create: (data: CreateDto) => api.post('/api/items/', data),
+  update: (id: number, data: UpdateDto) => api.patch(`/api/items/${id}/`, data),
+  delete: (id: number) => api.delete(`/api/items/${id}/`)
+}
+```
+
+## Arco Design 常用组件
+
+- `a-table` - 数据表格
+- `a-form` / `a-form-item` - 表单
+- `a-modal` - 弹窗
+- `a-button` - 按钮
+- `a-input` / `a-textarea` - 输入框
+- `a-select` - 选择器
+- `a-message` - 消息提示
+- `a-notification` - 通知
+
+## 开发命令
+
+```bash
+cd WHartTest_Vue
+npm run dev      # 开发服务器
+npm run build    # 生产构建
+```
+

package/package-source/docs/codex-harness-engineering/templates/package-assets/skills/webapp-testing/SKILL.md

@@ -0,0 +1,179 @@
+---
+name: webapp-testing
+description: Web App Testing Skill
+---
+
+# Web App Testing Skill
+
+Web 应用自动化测试：E2E 测试、DevTools MCP、CI/CD 集成。
+
+## 测试策略
+
+| 类型 | 工具 | 用途 |
+|------|------|------|
+| E2E | Playwright / DevTools MCP | 模拟用户操作 |
+| 组件 | Vitest + Testing Library | 组件逻辑验证 |
+| API | MSW | Mock 接口测试 |
+
+## DevTools MCP 测试
+
+### 核心原则
+
+```markdown
+## 禁止事项
+- ❌ 不要直接 navigate 到目标页面（除首页）
+- ❌ 不要直接操作 DOM 或执行 JS
+- ❌ 不要跳过中间步骤
+
+## 必须遵循
+- ✅ 从首页开始，通过点击导航
+- ✅ 模拟真实用户操作路径
+- ✅ 每次操作前 take_snapshot 获取最新 uid
+- ✅ 等待页面加载完成再操作
+```
+
+### 测试执行示例
+
+```
+测试：用户登录
+
+步骤 1: 打开首页
+- mcp_chrome_devtools_navigate_page(url: "http://localhost:5173")
+- mcp_chrome_devtools_take_snapshot()
+
+步骤 2: 点击登录
+- mcp_chrome_devtools_click(uid: "登录按钮uid")
+- mcp_chrome_devtools_wait_for(text: "登录")
+
+步骤 3: 填写表单
+- mcp_chrome_devtools_fill(uid: "邮箱uid", value: "test@example.com")
+- mcp_chrome_devtools_fill(uid: "密码uid", value: "password123")
+
+步骤 4: 提交
+- mcp_chrome_devtools_click(uid: "提交按钮uid")
+- mcp_chrome_devtools_wait_for(text: "仪表盘")
+
+步骤 5: 验证
+- mcp_chrome_devtools_take_snapshot()
+- 确认页面包含用户信息
+```
+
+## Playwright 测试
+
+```typescript
+// tests/e2e/login.spec.ts
+import { test, expect } from '@playwright/test';
+
+test('登录成功', async ({ page }) => {
+  await page.goto('/');
+  await page.getByRole('button', { name: '登录' }).click();
+  
+  await page.getByLabel('邮箱').fill('test@example.com');
+  await page.getByLabel('密码').fill('password123');
+  await page.getByRole('button', { name: '登录' }).click();
+  
+  await expect(page).toHaveURL('/dashboard');
+  await expect(page.getByTestId('user-avatar')).toBeVisible();
+});
+
+test('登录失败', async ({ page }) => {
+  await page.goto('/');
+  await page.getByRole('button', { name: '登录' }).click();
+  
+  await page.getByLabel('邮箱').fill('test@example.com');
+  await page.getByLabel('密码').fill('wrong');
+  await page.getByRole('button', { name: '登录' }).click();
+  
+  await expect(page.getByText('用户名或密码错误')).toBeVisible();
+});
+```
+
+## 测试用例模板
+
+```markdown
+# 测试用例：[功能名称]
+
+## 基本信息
+- 用例ID: TC-XXX-001
+- 优先级: P0/P1/P2
+- 前置条件: [描述]
+
+## 测试步骤
+
+### 步骤 1: [操作]
+- 操作: [具体操作]
+- 预期: [预期结果]
+
+## 验证点
+- [ ] [验证点1]
+- [ ] [验证点2]
+```
+
+## CI/CD 集成
+
+```yaml
+# .github/workflows/test.yml
+name: Test
+
+on: [push, pull_request]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: 'npm'
+      
+      - run: npm ci
+      - run: npm run type-check
+      - run: npm run lint
+      - run: npm run test:unit
+      
+      - run: npx playwright install --with-deps
+      - run: npm run test:e2e
+        env:
+          VITE_USE_MOCK: 'true'
+      
+      - uses: actions/upload-artifact@v4
+        if: failure()
+        with:
+          name: playwright-report
+          path: playwright-report/
+```
+
+## Playwright 配置
+
+```typescript
+// playwright.config.ts
+import { defineConfig } from '@playwright/test';
+
+export default defineConfig({
+  testDir: './tests/e2e',
+  fullyParallel: true,
+  retries: process.env.CI ? 2 : 0,
+  workers: process.env.CI ? 1 : undefined,
+  reporter: 'html',
+  use: {
+    baseURL: 'http://localhost:5173',
+    trace: 'on-first-retry',
+    screenshot: 'only-on-failure',
+  },
+  webServer: {
+    command: 'npm run dev',
+    url: 'http://localhost:5173',
+    reuseExistingServer: !process.env.CI,
+  },
+});
+```
+
+## 常见问题
+
+| 问题 | 解决 |
+|------|------|
+| 元素找不到 | 等待元素可见或使用更稳定的选择器 |
+| 测试不稳定 | 增加等待、使用 waitFor |
+| CI 超时 | 增加 timeout 或优化测试 |
+

package/package-source/docs/codex-harness-engineering/templates/package-assets/skills/xlsx/SKILL.md

@@ -0,0 +1,142 @@
+---
+name: xlsx
+description: Excel 表格处理指南
+---
+
+# Excel 表格处理指南
+
+## 触发条件
+Excel 读写、xlsx 文件、表格导出、数据报表
+
+## 推荐库
+- **exceljs** (推荐): 功能全面，支持样式和流式处理
+- **xlsx/sheetjs**: 轻量级，读写速度快
+- **xlsx-populate**: API 简洁
+
+## 基础用法 (ExcelJS)
+
+```typescript
+import ExcelJS from 'exceljs';
+
+/**
+ * 创建 Excel 文件
+ */
+async function createExcel() {
+  const workbook = new ExcelJS.Workbook();
+  const sheet = workbook.addWorksheet('Sheet1');
+
+  // 设置列
+  sheet.columns = [
+    { header: 'ID', key: 'id', width: 10 },
+    { header: '名称', key: 'name', width: 20 },
+    { header: '金额', key: 'amount', width: 15 },
+  ];
+
+  // 添加数据
+  sheet.addRows([
+    { id: 1, name: '产品A', amount: 100 },
+    { id: 2, name: '产品B', amount: 200 },
+  ]);
+
+  await workbook.xlsx.writeFile('output.xlsx');
+}
+```
+
+## 读取 Excel
+
+```typescript
+/**
+ * 读取 Excel 文件
+ */
+async function readExcel(filePath: string) {
+  const workbook = new ExcelJS.Workbook();
+  await workbook.xlsx.readFile(filePath);
+  
+  const sheet = workbook.getWorksheet(1);
+  const data: any[] = [];
+  
+  sheet.eachRow((row, rowNumber) => {
+    if (rowNumber > 1) { // 跳过表头
+      data.push({
+        id: row.getCell(1).value,
+        name: row.getCell(2).value,
+        amount: row.getCell(3).value,
+      });
+    }
+  });
+  
+  return data;
+}
+```
+
+## 样式设置
+
+```typescript
+// 表头样式
+sheet.getRow(1).eachCell(cell => {
+  cell.fill = {
+    type: 'pattern',
+    pattern: 'solid',
+    fgColor: { argb: 'FF4472C4' },
+  };
+  cell.font = { bold: true, color: { argb: 'FFFFFFFF' } };
+  cell.alignment = { horizontal: 'center' };
+});
+
+// 边框
+cell.border = {
+  top: { style: 'thin' },
+  left: { style: 'thin' },
+  bottom: { style: 'thin' },
+  right: { style: 'thin' },
+};
+
+// 数字格式
+cell.numFmt = '#,##0.00';
+```
+
+## 流式写入 (大数据量)
+
+```typescript
+/**
+ * 流式写入，适合大数据量
+ */
+async function streamWrite(data: any[], outputPath: string) {
+  const workbook = new ExcelJS.stream.xlsx.WorkbookWriter({
+    filename: outputPath,
+  });
+  
+  const sheet = workbook.addWorksheet('Data');
+  sheet.columns = [
+    { header: 'ID', key: 'id' },
+    { header: 'Value', key: 'value' },
+  ];
+  
+  for (const item of data) {
+    sheet.addRow(item).commit();
+  }
+  
+  await workbook.commit();
+}
+```
+
+## 公式和图表
+
+```typescript
+// 公式
+sheet.getCell('D2').value = { formula: 'SUM(C2:C100)' };
+
+// 数据验证（下拉列表）
+sheet.getCell('B2').dataValidation = {
+  type: 'list',
+  allowBlank: true,
+  formulae: ['"选项1,选项2,选项3"'],
+};
+```
+
+## 最佳实践
+- 大数据量使用流式 API
+- 日期处理注意时区问题
+- 合并单元格后注意样式应用
+- 导出前验证数据类型一致性
+

package/package-source/docs/codex-harness-engineering/templates/package-assets/workflows/README.md

@@ -0,0 +1,15 @@
+# Workflows
+
+本目录现在只保留**独立 workflow**，不再保留与 `skills/` 一一镜像的平铺副本。
+
+## 当前范围
+
+- `speckit.*.md`
+  Speckit 相关的独立流程文档。
+
+## 已迁移内容
+
+- 与 `skills/` 重名的 workflow 镜像已移到 `../archive/workflows/skill-mirrors/`
+- 废弃副本如 `code-review copy.md` 已移到 `../archive/workflows/deprecated/`
+
+如果某个主题已经在 `skills/<name>/SKILL.md` 中维护，优先以 skill 目录为准。

package/package-source/docs/codex-harness-engineering/templates/package-assets/workflows/speckit.analyze.md

@@ -0,0 +1,149 @@
+---
+description: Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
+---
+
+## User Input
+
+```text
+$ARGUMENTS
+```
+
+You **MUST** consider the user input before proceeding (if not empty).
+
+## 语言要求
+
+- 输出给用户的分析报告必须使用简体中文。
+- 报告中的表格标题、问题描述、修复建议、后续命令建议全部使用简体中文。
+- 保留需求编号、任务 ID、路径、命令、协议名等技术标识原样不变。
+
+## Goal
+
+Identify inconsistencies, duplications, ambiguities, and underspecified items across the three core artifacts (`spec.md`, `plan.md`, `tasks.md`) before implementation. This command MUST run only after `/speckit.tasks` has successfully produced a complete `tasks.md`.
+
+## Operating Constraints
+
+**STRICTLY READ-ONLY**: Do **not** modify any files. Output a structured analysis report. Offer an optional remediation plan (user must explicitly approve before any follow-up editing commands would be invoked manually).
+
+**Constitution Authority**: The project constitution (`.agents/.specify/memory/constitution.md`) is **non-negotiable** within this analysis scope. Constitution conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks—not dilution, reinterpretation, or silent ignoring of the principle.
+
+## Execution Steps
+
+### 1. Initialize Analysis Context
+
+Run `.agents/.specify/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks` once from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS. Derive absolute paths:
+
+- SPEC = FEATURE_DIR/spec.md
+- PLAN = FEATURE_DIR/plan.md
+- TASKS = FEATURE_DIR/tasks.md
+
+Abort with an error message if any required file is missing.
+
+### 2. Load Artifacts (Progressive Disclosure)
+
+Load only the minimal necessary context from each artifact:
+
+**From spec.md:**
+- Overview/Context
+- Delivery mode / integration boundary
+- Functional Requirements
+- Non-Functional Requirements
+- User Stories
+- Edge Cases (if present)
+
+**From plan.md:**
+- Delivery mode gate
+- OSS reuse matrix
+- Integration blockers & evidence
+- Connector / adapter strategy
+- Architecture/stack choices
+- Data Model references
+- Phases
+- Technical constraints
+
+**From tasks.md:**
+- Task IDs
+- Descriptions
+- Phase grouping
+- Parallel markers [P]
+- Delivery attributes, blockers, evidence paths, verification layers
+- Referenced file paths
+
+**From constitution:**
+- Load `.agents/.specify/memory/constitution.md` for principle validation
+
+### 3. Build Semantic Models
+
+Create internal representations (do not include raw artifacts in output):
+- **Requirements inventory**: Each functional + non-functional requirement with a stable key
+- **User story/action inventory**: Discrete user actions with acceptance criteria
+- **Task coverage mapping**: Map each task to one or more requirements or stories
+- **Constitution rule set**: Extract principle names and MUST/SHOULD normative statements
+
+### 4. Detection Passes (Token-Efficient Analysis)
+
+Focus on high-signal findings. Limit to 50 findings total.
+
+- **A. Duplication Detection**: Identify near-duplicate requirements
+- **B. Ambiguity Detection**: Flag vague adjectives lacking measurable criteria
+- **C. Underspecification**: Requirements with verbs but missing object or measurable outcome
+- **D. Constitution Alignment**: Any requirement or plan element conflicting with a MUST principle
+- **E. Coverage Gaps**: Requirements with zero associated tasks
+- **F. Inconsistency**: Terminology drift, conflicting requirements
+- **G. Delivery Mode Drift**: Prototype/spike deliverables masquerading as completed formal `FR-*`
+- **H. Integration Downgrade**: Requirements tied to predefined OSS/external systems but implemented only as local mock/sample without explicit downgrade note
+- **I. Reuse Matrix Gap**: Missing or incomplete OSS reuse matrix rows for predefined stack / external systems
+- **J. Blocker Gate Failure**: Related `TBD-*` still open while tasks try to close the linked requirement
+- **K. Ordering Risk**: UI/BFF tasks are planned ahead of environment evidence, real connector, or integration-prep tasks they depend on
+- **L. Task Compression Risk**: A story or feature is represented by a single oversized task that spans blockers/evidence, connector work, bridge logic, API/BFF, UI, and final verification, hiding progress and making stop-hook continuation ineffective
+
+### 5. Severity Assignment
+
+- **CRITICAL**: Violates constitution MUST, missing core spec artifact, or open integration blocker falsely treated as complete
+- **HIGH**: Duplicate or conflicting requirement, ambiguous security/performance attribute, or a single oversized integration task that hides multiple execution layers
+- **MEDIUM**: Terminology drift, missing non-functional task coverage, or missing explicit downgrade record
+- **LOW**: Style/wording improvements, minor redundancy
+
+### 6. Produce Compact Analysis Report
+
+Output a Markdown report in Simplified Chinese (no file writes) with:
+
+| ID | Category | Severity | Location(s) | Summary | Recommendation |
+|----|----------|----------|-------------|---------|----------------|
+
+**Coverage Summary Table:**
+
+| Requirement Key | Has Task? | Task IDs | Notes |
+|-----------------|-----------|----------|-------|
+
+**Constitution Alignment Issues:** (if any)
+
+**Unmapped Tasks:** (if any)
+
+**Metrics:**
+- Total Requirements
+- Total Tasks
+- Coverage % (requirements with >=1 task)
+- Integration Requirements Count
+- Open `TBD-*` Count
+- Compressed Story Count
+- Ambiguity Count
+- Duplication Count
+- Critical Issues Count
+
+### 7. Provide Next Actions
+
+- If CRITICAL issues exist: Recommend resolving before `/speckit.implement`
+- If Task Compression Risk exists: Recommend splitting the affected task into 4-6 acceptance-sized tasks before `/speckit.implement`
+- If only LOW/MEDIUM: User may proceed, but provide improvement suggestions
+- Provide explicit command suggestions
+
+### 8. Offer Remediation
+
+Ask the user: "Would you like me to suggest concrete remediation edits for the top N issues?" (Do NOT apply them automatically.)
+
+## Operating Principles
+
+- **NEVER modify files** (this is read-only analysis)
+- **NEVER hallucinate missing sections** (if absent, report them accurately)
+- **Prioritize constitution violations** (these are always CRITICAL)
+- **Report zero issues gracefully** (emit success report with coverage statistics)