agentleFS
voidningvoidning/skills/test-guide-html/SKILL.md

test-guide-html

Skill0 starsChanged 56 days agoMITView on GitHub

Generate a clean, OpenAI-styled single-file HTML test guide for QA testers. Use when the user asks for a test guide, test plan HTML, testing instructions document, or QA verification guide in Chinese.

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. About 0 are common, 12 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈12

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user asks for:

    line 18
  2. Distinctive:

    Default output language is Chinese (zh-CN) unless the user explicitly asks for English.

    line 25
  3. Very specific:

    Always output a single self-contained .html file with:

    line 29
  4. Very specific:

    If openai-aesthetic is not available, fall back to the tokens above.

    line 52
  5. Distinctive:

    Document type label: "Test Guide"

    line 57
  6. Very specific:

    Use a checkbox-style list (☐).

    line 66
  7. Distinctive:

    Keep items short and checkable.

    line 67
  8. Distinctive:

    Do not ask testers to fill in URLs, dates, names, or pass/fail columns.

    line 85
  9. Distinctive:

    Do not include technical implementation details (code paths, Redis commands, etc.).

    line 86
  10. Distinctive:

    Do not make it look like a Jira ticket or Excel sheet.

    line 87
  11. Distinctive:

    Do not use localhost-specific URLs unless explicitly requested.

    line 88
  12. Distinctive:

    Do not use colored left borders on callouts.

    line 89
  13. Distinctive:

    Do not use more than one accent color, and never as large-area fills.

    line 90
  14. Distinctive:

    Do not reproduce OpenAI's wordmark or Blossom icon.

    line 91
  15. Distinctive:

    Ask for the scope only if unclear: "这个指南要覆盖哪个功能或系统?"

    line 137

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Test Guide HTML Generator

Generate a single-file HTML test guide that QA testers can read in a browser or print. The guide should be concise, actionable, and visually clean in the OpenAI aesthetic.

When to Use

Use this skill when the user asks for:

  • "生成测试指南 HTML"
  • "给测试写个测试说明"
  • "QA 测试指南"
  • "测试计划 HTML"
  • "验证步骤文档"

Default output language is Chinese (zh-CN) unless the user explicitly asks for English.

Output Format

Always output a single self-contained .html file with:

  • Embedded CSS (no external dependencies)
  • No JavaScript required
  • Printable layout (@media print should remove horizontal padding)
  • Responsive for desktop and mobile

Styling

  1. First, apply the openai-aesthetic skill.
  2. Then apply these report-specific conventions:
    • Page max-width: 800px
    • H1 (page title): 28px / weight 600 / color #181818
    • H2 (section): 22px / weight 600 / color #181818 / bottom hairline border
    • H3 (subsection): 16px / weight 600 / color #181818
    • Body: 16px / weight 400 / line-height 1.6 / color #181818
    • Meta label: 13px / weight 500 / uppercase / color #8f8f8f
    • Font stack: "OpenAI Sans", Inter, ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", "Microsoft YaHei", sans-serif
    • Accent (at most one): links #3b5bdb; small monoline icons may also use it
    • Status colors (text or small dots only, never backgrounds): success #2f9e44, error #d64545, warning #e8890c
    • Cards/callouts: #f9f9f9 background, 8px radius, 16–20px padding
    • Tables: hairline borders, hover state #f9f9f9
    • Checklists: ☐ prefix, no native checkbox inputs

If openai-aesthetic is not available, fall back to the tokens above.

Required Sections

  1. Header
    • Document type label: "Test Guide"
    • Title
    • One-line subtitle describing the scope
  2. 测试范围 / Scope
    • 1–2 sentences explaining what is being tested.
    • Any critical environment note (e.g., "do not use localhost").
  3. 前置条件 / Prerequisites
    • Use a checkbox-style list (☐).
    • Keep items short and checkable.
  4. 测试场景 / Test Scenarios
    • One section per major scenario.
    • Each scenario contains:
      • 操作步骤: numbered list of actions
      • 预期结果: a highlighted callout box
      • 验证要点: bullet list of things to verify
  5. 常见异常处理 / Common Issues
    • Use a table: 报错 / 原因 / 处理.
    • Keep rows short.
  6. 边界场景 / Edge Cases
    • Checkbox list of additional scenarios to verify.

What to Avoid

  • Do not ask testers to fill in URLs, dates, names, or pass/fail columns.
  • Do not include technical implementation details (code paths, Redis commands, etc.).
  • Do not make it look like a Jira ticket or Excel sheet.
  • Do not use localhost-specific URLs unless explicitly requested.
  • Do not use colored left borders on callouts.
  • Do not use more than one accent color, and never as large-area fills.
  • Do not reproduce OpenAI's wordmark or Blossom icon.

Worked Mini-Example

<!DOCTYPE html>
<html lang="zh-CN">
<head>
  <meta charset="UTF-8">
  <title>示例测试指南</title>
  <style>
    body {
      font-family: Inter, system-ui, "Microsoft YaHei", sans-serif;
      font-size: 16px;
      line-height: 1.6;
      color: #181818;
      max-width: 800px;
      margin: 0 auto;
      padding: 72px 32px;
    }
    h1 { font-size: 28px; font-weight: 600; }
    a { color: #3b5bdb; }
    h2 { font-size: 22px; font-weight: 600; border-bottom: 1px solid #ededed; padding-bottom: 10px; }
    .callout { background: #f9f9f9; border-radius: 8px; padding: 16px 20px; }
    .checklist { list-style: none; margin-left: 0; }
    .checklist li { padding-left: 28px; position: relative; }
    .checklist li::before { content: "☐"; position: absolute; left: 0; color: #8f8f8f; }
  </style>
</head>
<body>
  <h1>示例测试指南</h1>
  <h2>1. 测试范围</h2>
  <p>...</p>
  <h2>2. 前置条件</h2>
  <ul class="checklist"><li>账号已注册</li></ul>
  <h2>3. 操作步骤</h2>
  <ol><li>打开页面</li></ol>
  <h3>预期结果</h3>
  <div class="callout">页面正常加载。</div>
</body>
</html>

Generation Workflow

  1. Identify the system/feature being tested from the user's request.
  2. Ask for the scope only if unclear: "这个指南要覆盖哪个功能或系统?"
  3. Draft the guide using the structure above.
  4. Apply the OpenAI aesthetic and report-specific conventions.
  5. Save as a single .html file and tell the user the path.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.