Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/seed-forge/harness-ai-kit/devlab-web-test-e2enpx skills add seed-forge/harness-ai-kit --skill devlab-web-test-e2egit clone --depth 1 https://github.com/seed-forge/harness-ai-kitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00061 | $0.03752 |
| Opus 5 | $0.00030 | $0.01876 |
| Sonnet 5 | $0.00012 | $0.00750 |
| Haiku 4.5 | $0.00006 | $0.00375 |
Grade A, and why
devlab-web-test-e2e scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web E2E 测试专家技能
专注 Vue/React 前端项目的浏览器端到端测试能力。
基于 Playwright + AI Agent 实现从测试计划生成 → 代码生成 → 失败修复的完整闭环。
触发条件
当用户提到以下关键词时触发此 Skill:
- "Vue/React 组件测试" / "web component test"
- "浏览器自动化测试" / "browser automation"
- "Playwright 测试" / "E2E 测试"
- "视觉回归测试" / "visual regression"
- "Flaky test 治理" / "不稳定测试修复"
技术栈依赖
核心 CLI
# 必须安装
npm install -D @playwright/test
# 可选增强
npm install -D vitest # 单元测试补充
AI Agent 初始化
npx playwright init-agents --loop=claude
# 或
npx playwright init-agents --loop=codex
功能范围
Phase 1: 测试场景识别与计划生成
输入:
- 应用 URL(本地开发环境)
- (可选)PRD/User Story 描述
- (可选)现有测试代码模式参考
输出:
specs/features/*.md— 功能测试计划(Gherkin 格式)specs/regression.md— 视觉回归检查清单specs/performance.md— 性能基准要求
工作流程:
Step 1.1: UI 探索分析
// AI 自动打开浏览器扫描应用
const page = await context.newPage();
await page.goto('http://localhost:3000');
// 提取关键元素
const elements = await page.locator('button, input, a').all();
const routes = await extractRoutes(page);
输出物:
# UI Structure Analysis
- 路由表:`/, /login, /dashboard, /settings`
- 主要组件:登录表单、导航栏、数据表格、操作按钮
- 交互点:47 个可点击元素,12 个表单字段
Step 1.2: 生成测试计划
# specs/features/user-authentication.md
Feature: User Authentication
As a registered user
I want to log in securely
So that I can access my account
Scenario: Successful login with valid credentials
Given I am on the login page
When I enter valid email and password
And I click "Sign In" button
Then I should see the dashboard
And I should receive a welcome message
Scenario Outline: Login validation
When I enter "<email>" as email
And I submit the form
Then I should see error "<error_message>"
Examples:
| email | error_message |
| invalid | Invalid email format|
| empty@ | Invalid email format|
| | Email is required |
Phase 2: Playwright 测试代码生成
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 491 lines · 61 tokens per session scan A fb6b3ef3a1b5
devlab-web-test-e2e is a skill published in the GitHub repository seed-forge/harness-ai-kit (21 stars, last pushed 6d ago), licensed Apache-2.0. It adds 61 tokens to every session and 3,752 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
browser-testing-with-devtools
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…
qa/e2e-playwright
Playwright E2E 测试完整方法论,涵盖项目初始化、Page Object Model、认证复用、API Mock、视觉回归、多浏览器测试、CI 集成和调试技巧.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
common-tasks
Copy-paste AI prompt templates for common Playwright scaffold development tasks — adding page objects, functional/E2E/API tests, Zod schemas, factories, fixtures, and components. Use when the user asks "how do I add a ...", "give me a prompt for ...", "create a new [page object | test | schema | factory | fixture |…
selectors
Selector strategy, exploration-first workflow, locator priority order (getByRole then getByLabel then getByPlaceholder then getByText then getByTestId), and feedback/validation-message selector rules for Playwright page objects. Use when creating page objects, writing or updating locators, generating UI tests, or…
planr-verify-web
Frozen-source live verification for a web FeatureRun. Consumes a canonical verification work packet, uses the configured Evidence capability, and records trusted proof without editing product source.