Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fishzjp/qa-skillsnpx agentmods add skills/fishzjp/qa-skills/automated-e2e-testingWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fishzjp/qa-skills/automated-e2e-testing)<a href="https://agentmods.dev/skills/fishzjp/qa-skills/automated-e2e-testing"><img src="https://agentmods.dev/badge/skills/fishzjp/qa-skills/automated-e2e-testing.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00100 | $0.04558 |
| Opus 5 | $0.00050 | $0.02279 |
| Sonnet 5 | $0.00020 | $0.00912 |
| Haiku 4.5 | $0.00010 | $0.00456 |
Grade A, and why
automated-e2e-testing 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 3d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
自动化 E2E 测试（automated-e2e-testing）
本 skill 覆盖 Web 应用自动化测试的完整工作流：将手动测试用例（markmap + Schema）转化为 Playwright spec → 运行并验证 → 发现 Bug → 输出测试报告。
核心原则：
- 先熟悉业务再写测试 — 对功能不熟悉时，先用自动化脚本主动探索系统，理解实际行为后再动手写测试代码
- 有疑问就提问，不自行假设 — 编写过程中遇到任何不明确的地方，必须向用户提问澄清，绝不凭猜测写代码
- 每条自动化用例对应一条手动用例，每条 test 只测一个点
- 每个 test 独立（自建数据 + 自清理）
- 必须使用 Page Object — 正式测试中禁止裸写定位器，所有页面交互封装在 Page Object 中
工程约定（脚手架、配置、场景代码模板、Page Object 规范）统一在 references/playwright-conventions.md——写代码时加载；通用 Helper（登录、多会话、证据收集）的参考实现在 references/helpers_reference.md；类型域三类执行片段（a11y 扫描 / 视觉基线 / 多浏览器矩阵）见工程约定第 12–14 节，type_scope 判入对应轴时按档加载取用
When to Use
- 给定测试用例（markmap / Schema），需要生成 Playwright spec 文件并执行
- 编写自动化前，需要小规模业务熟悉探索（踩点页面结构、提取选择器）
- 自动化执行中发现 Bug，需要收集证据并记录测试报告条目
- 需要编写新的 Page Object 或 Helper 函数
When NOT to Use
- 端到端测试整个需求（理解→策略→用例→执行→报告的流水线）→ 用
qaskill 编排 - 编写手动测试用例 → 用
test-case-writingskill - 纯 API 接口测试（无 Web UI 流程）→ 用
api-testingskill - 以理解系统 / 发现风险为目的的独立探索式测试会话（charter 驱动、产出探索笔记）→ 用
exploratory-testingskill；本 skill 的工作流零只做「为写自动化踩点」的小规模探索 - 已确认 Bug 的根因定位、影响分析、回归建议 → 用
bug-analysisskill；本 skill 只负责收集 Bug 证据（截图/API/控制台）并记录报告条目 - 代码变更后判断回归范围 → 用
regression-testingskill - 单元测试 → 用 Jest/Vitest；性能压测 → 专业工具（k6、locust）；安全测试 → 安全审计专项（见
test-strategy的 handoff 约定）
提问时机（必须遵守）
核心规则：不确定就问，宁可多问不要瞎猜。 格式与裁决规则统一按 ../core/clarify-pattern.md（场景用「执行确认」）。
| 场景 | 应提问的内容 | 不要自行假设 |
|---|---|---|
| 元素定位失败 | "在{页面}上找不到{元素}，实际页面结构是否与预期一致？" | 不要随意换选择器猜测 |
| 操作路径不明确 | "测试用例说{操作X}，但页面上没有直接的入口" | 不要自行拼凑操作步骤 |
| 预期行为有歧义 | "预期{结果A}，实际{结果B}，应以哪个为准？" | 不要选择性地相信其中一个 |
| 业务规则不清楚 | "规则{X}的具体边界是什么？" | 不要用常见默认值代替 |
| 探索中发现异常 | "发现{异常行为}，这是预期行为还是 Bug？" | 不要自行判定是 Bug 还是特性 |
| 用例反复超时/不稳定 | "{页面}是否存在长连接或轮询推送（WebSocket/SSE/心跳上报）导致页面永不空闲？" | 不要一律套 networkidle 等待，按等待降级阶梯处理 |
工作流零：业务熟悉（前置必做，为写自动化踩点的小规模探索）
何时需要：从未测试过该功能模块 / 出现不熟悉的页面路由 / 需要编写新的 Page Object / 拿到用例但不知道系统长什么样
本工作流是小规模踩点探索（理解页面结构、提取选择器、落 Page Object），产出服务于工作流一。以理解系统 / 发现风险为目的的完整探索会话（charter 驱动、产出探索笔记）用
exploratory-testingskill。
What ships with it
2 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.
- 3d ago Changed · +1 lines 7293244b177e
- 7d ago First seen · 203 lines · 100 tokens per session scan A 37277a837ab8
automated-e2e-testing is a skill published in the GitHub repository fishzjp/qa-skills (24 stars, last pushed yesterday), licensed MIT. It adds 100 tokens to every session and 4,558 once invoked, about $0.0005 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
qa-expert
Expert-level quality assurance, testing strategies, automation, and QA processes. Use when the user mentions testing, test automation, quality assurance, or Selenium, or when the task involves Testing Types, QA Processes, Test Strategy, or Defect Management.
playwright-expert
Expert in Playwright E2E testing framework, auto-waiting mechanisms, test generation, trace viewer, and CI/CD integration. Use when the user mentions testing, end-to-end tests, QA, automation, end-to-end testing, or test automation, or when the task involves Playwright Framework, Test Organization, Advanced Features…
selenium-expert
Expert in Selenium WebDriver, Selenium Grid, page object model, waits, cross-browser testing, and test automation frameworks. Use when the user mentions testing, end-to-end tests, QA, automation, WebDriver, or Selenium grid, or when the task involves Selenium Components, Browser Support, Advanced Features, or Basic…
playwright
When the user wants to design, implement, debug, stabilize, or scale Playwright tests. Use when the user mentions "Playwright," "playwright.config.ts," "page.locator," "page.getByRole," "browser context," "fixtures," "test.beforeEach," "trace viewer," "codegen," "Playwright Test," "Playwright MCP," "PWT," "WebKit…
cypress
When the user wants to design, implement, debug, stabilize, or scale Cypress tests. Use when the user mentions "Cypress," "cypress.config.js," "cy.intercept," "cy.session," "cy.visit," "component testing in Cypress," "Cypress Cloud," "cypress run," "cypress open," "cy.task," "Mocha," or "Chai." For Playwright-specific…
selenium-grid
When the user wants to design, deploy, scale, or troubleshoot a self-hosted Selenium Grid 4 cluster — hub, nodes, distributors, sessions, K8s deployment, autoscaling. Use when the user mentions "Selenium Grid," "Selenium Grid 4," "grid hub," "grid node," "selenium docker-selenium," "session queue," "selenoid," "moon,"…