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.
git clone --depth 1 https://github.com/an8079/take-skillsWrote 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/commands/an8079/take-skills/takes-qa)<a href="https://agentmods.dev/commands/an8079/take-skills/takes-qa"><img src="https://agentmods.dev/badge/commands/an8079/take-skills/takes-qa/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/an8079/take-skills/takes-qa"><img src="https://agentmods.dev/badge/commands/an8079/take-skills/takes-qa.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00033 | $0.02504 |
| Opus 5 | $0.00016 | $0.01252 |
| Sonnet 5 | $0.00007 | $0.00501 |
| Haiku 4.5 | $0.00003 | $0.00250 |
Grade A, and why
qa 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 9d 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.
This is a copy
88% identical to qa-only — 76 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qa - 自动化测试与修复
对 Web 应用进行系统性 QA 测试,找到 bug 后修复代码并原子提交,最后重新验证。生成带证据的结构化报告。
使用方式
/qa # 标准 QA 测试
/qa https://example.com # 测试指定 URL
/qa --quick # 快速冒烟测试(30秒)
/qa --exhaustive # 穷举测试(包含 low/cosmetic)
测试层级
| 层级 | 覆盖范围 |
|---|---|
| Quick | Critical + High 严重级别 |
| Standard | + Medium 严重级别(默认) |
| Exhaustive | + Low / Cosmetic 严重级别 |
Phase 1: 初始化
检测项目运行时:
[ -f package.json ] && echo "RUNTIME:node"
[ -f Gemfile ] && echo "RUNTIME:ruby"
[ -f requirements.txt ] || [ -f pyproject.toml ] && echo "RUNTIME:python"
[ -f go.mod ] && echo "RUNTIME:go"
[ -f Cargo.toml ] && echo "RUNTIME:rust"
检测测试框架:
ls jest.config.* vitest.config.* playwright.config.* .rspec pytest.ini pyproject.toml phpunit.xml 2>/dev/null
ls -d test/ tests/ spec/ __tests__/ cypress/ e2e/ 2>/dev/null
创建输出目录:
mkdir -p .claude-studio/qa-reports/screenshots
Phase 2: 目标 URL
优先从用户请求中解析 URL:
- 用户提供了 URL → 直接使用
- 用户未提供 URL → 检查本地端口(
localhost:3000/4000/8080) - 无法检测 → 询问用户
检查 git 分支(diff-aware 模式):
git branch --show-current
git diff main...HEAD --name-only
git log main..HEAD --oneline
如果提供了 URL 但在特性分支上,优先测试受分支变更影响的页面。
Phase 3: 探索
Orient - 应用地图
- 访问目标 URL
- 获取导航结构(
links或snapshot -i) - 检查控制台错误
- 检测框架:
- HTML 含
__next→ Next.js - 含
csrf-token→ Rails - 含
wp-content→ WordPress - 客户端路由无页面重载 → SPA
- HTML 含
Explore - 系统性遍历
每个页面:
- 截图存档(
screenshot) - 检查控制台错误(
console --errors) - 点击所有按钮/链接,验证响应
- 填写表单并提交(空提交、无效数据、边界值)
- 检查导航路径
- 检查各状态(空状态、加载状态、错误状态、溢出状态)
- 响应式检查(移动端 viewport)
优先级: 核心功能(首页、仪表盘、结账、搜索)多花时间,次要页面(关于页、条款页)少花时间。
Quick 模式
仅访问首页 + 顶部 5 个导航目标。检查:页面加载?控制台错误?可见的失效链接?无详细问题文档。
Phase 4: 记录
每个问题立即记录,不要批量。
截图证据要求:
- 交互式 bug:操作前截图 → 执行操作 → 结果截图
- 静态 bug(布局问题、错字):单张带标注截图
使用 Read 工具展示截图给用户。
Phase 5: 健康评分
计算各类别分数(0-100),取加权平均。
评分规则
| 类别 | 权重 |
|---|---|
| Console | 15% |
| Links | 10% |
| Visual | 10% |
| Functional | 20% |
| UX | 15% |
| Performance | 10% |
| Content | 5% |
| Accessibility | 15% |
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.
- 9d ago First seen · 313 lines · 33 tokens per session scan A fe06dce4ccee
qa is a command published in the GitHub repository an8079/take-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 2,504 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to qa-only, differing in 76 lines, and is treated as a copy.
Other commands, from other repositories
playwright-test-heal
Run all my tests and fix the failing ones.
paul:verify
Guide manual user acceptance testing of recently built features.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
ui-snapshot.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.