菜单
Run user story acceptance tests using Playwright browser automation. Executes test steps from user-stories/*.md files and reports pass/fail status with reasons. Use when user says "run user stories", "test user stories", "acceptance test", or "run e2e tests".
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | run-user-stories |
| version | 1.1.0 |
| description | Run user story acceptance tests using Playwright browser automation. Executes test steps from user-stories/*.md files and reports pass/fail status with reasons. Use when user says "run user stories", "test user stories", "acceptance test", or "run e2e tests". |
| allowed-tools | Task, Read, Glob, Grep, Bash, AskUserQuestion, ToolSearch, mcp__playwright__browser_navigate, mcp__playwright__browser_snapshot, mcp__playwright__browser_click, mcp__playwright__browser_type, mcp__playwright__browser_fill_form, mcp__playwright__browser_press_key, mcp__playwright__browser_tabs, mcp__playwright__browser_take_screenshot, mcp__playwright__browser_evaluate, mcp__playwright__browser_console_messages, mcp__playwright__browser_wait_for, mcp__playwright__browser_hover, mcp__playwright__browser_select_option |
| context | fork |
| model | sonnet |
Run acceptance tests from user-stories/*.md files in a browser and report pass/fail results.
<when_to_use>
Invoke when user says:
</when_to_use>
The skill accepts optional arguments to specify scope directly:
| Argument | Example | Description |
|---|---|---|
| (none) | /run-user-stories | Prompts for scope selection |
| Story ID | /run-user-stories US-AUTH-01 | Run single story |
| Area code | /run-user-stories AUTH | Run all stories in area |
| Multiple IDs | /run-user-stories US-AUTH-01 US-AUTH-02 | Run specific stories |
Valid area codes: AUTH, RECIPE, SEARCH, SHARE, PANTRY, SHOP, HOME, IMPORT
| Phase | Action | Gate |
|---|---|---|
| 1 | Select test scope | User choice |
| 2 | Parse selected user stories | - |
| 3 | Setup browser session | - |
| 4 | Execute tests sequentially | - |
| 5 | Generate summary report | - |
IMPORTANT: Use the Playwright MCP tools (mcp__playwright__*) for all browser automation. Do NOT use Claude-in-Chrome tools.
Read .claude/skills/run-user-stories/references/runner-instructions.md for detailed execution instructions, then execute.
Scope Selection: Check arguments first, then prompt if none provided:
/run-user-stories US-AUTH-01 — runs single story directly/run-user-stories AUTH — runs all stories in an area/run-user-stories — prompts for scope selectionEnvironment: Tests run against http://localhost:3000 by default. Ensure:
pnpm dev is runningpostgrest postgrest.cfg)Authentication: Many tests require login. The runner will:
test@example.com / password123To run just the user registration test:
/run-user-stories US-AUTH-01
This will:
user-stories/01-authentication.mdUS-AUTH-01: User Registration<test_areas>
| Area ID | File | Stories | Description |
|---|---|---|---|
| AUTH | 01-authentication.md | 5 | Login, register, logout |
| RECIPE | 02-recipe-management.md | 6 | CRUD, copy, like recipes |
| SEARCH | 03-recipe-search.md | 5 | Search, filter, browse |
| SHARE | 04-recipe-sharing.md | 5 | Share links, anonymous |
| PANTRY | 05-pantry-management.md | 5 | Pantry CRUD, matching |
| SHOP | 06-shopping-list.md | 6 | Shopping list features |
| HOME | 07-household.md | 6 | Household management |
| IMPORT | 08-recipe-import.md | 5 | URL import, AI parsing |
</test_areas>
<result_format>
Results are presented in a structured summary:
## Test Results Summary
**Passed**: 12 | **Failed**: 3 | **Skipped**: 2
### Failed Tests
| Story ID | Title | Reason |
| ------------ | ------------------ | -------------------------------- |
| US-AUTH-02 | User Login | Password field not found |
| US-RECIPE-01 | Create New Recipe | Save button disabled |
### Passed Tests
| Story ID | Title |
| ------------ | ------------------ |
| US-AUTH-01 | User Registration |
| US-AUTH-05 | Logout |
...
### Skipped Tests
| Story ID | Title | Reason |
| ------------ | ------------------ | -------------------------------- |
| US-AUTH-03 | Google OAuth | Requires manual OAuth flow |
</result_format>
<skip_criteria>
Some tests are automatically skipped:
Mark these as "Skipped" with reason in the report.
</skip_criteria>
<approval_gates>
| Gate | Phase | Question |
|---|---|---|
| Scope | 1 | "Which tests to run? All / Area / Single story" |
</approval_gates>
Kill all running local development processes (TanStack Start dev, email service, PostgREST), wait for termination, then restart them. Use when user says "boot local", "restart local", "reboot dev", or needs to refresh local services.
Scrape, load, and manage the base recipe pool for the meal planner. Handles scraping Swedish recipe sites, loading into database, and verifying integration. Use when user says "scrape recipes", "load base recipes", "base recipe pool", or "update base recipes".
Evaluate test coverage and create appropriate tests based on risk assessment. Use when user says "build tests", "update tests", "add test coverage", "write tests for this", or "improve test coverage".
Reviews code quality, pattern adherence, and architecture with red-team validation. Use when user says "check your code", "code quality review", "is this well-written", or "review code quality". Different from check-your-work which finds bugs.
Orchestrates 6 quality agents in parallel (duplicate-detector, user-intent, deep-bug-hunter, security, performance, correctness) with severity validation. Use when user says "check your work", "review what we wrote", "quality check", or after writing new features.
Create distinctive, production-grade frontend interfaces with high design quality. Use when user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.