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 skills add majiayu000/spellbook --skill css-debuggit clone --depth 1 https://github.com/majiayu000/spellbookWrote 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/majiayu000/spellbook/css-debug)<a href="https://agentmods.dev/skills/majiayu000/spellbook/css-debug"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/css-debug/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/skills/majiayu000/spellbook/css-debug"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/css-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.01606 |
| Opus 5.5 | $0.00014 | $0.00642 |
| Sonnet 5.5 | $0.00007 | $0.00321 |
| Haiku 4.5 | $0.00003 | $0.00161 |
Grade A, and why
css-debug 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 1mo 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CSS Debug Skill
css-debug true
使用场景
当用户遇到以下问题时使用此 skill:
- CSS 定位问题(元素位置不正确、被裁剪、溢出等)
- React 组件渲染问题
- Tailwind CSS 类不生效
- 绝对定位/相对定位问题
- Flexbox/Grid 布局问题
- z-index 层叠问题
调试步骤
1. 收集信息
首先向用户询问或获取:
- 浏览器开发者工具中的 HTML 结构
- 相关元素的 computed styles
- 父容器的 CSS 属性(特别是 position、overflow、display)
- 截图(如果有的话)
2. 常见问题检查清单
绝对定位内容被裁剪
问题:position: absolute 的元素被父容器裁剪
检查:
- [ ] 父容器是否有 overflow: hidden 或 overflow: auto
- [ ] 祖先容器是否有 overflow: hidden
- [ ] 父容器是否设置了 position: relative
- [ ] 元素的 top/left/right/bottom 值是否超出父容器
解决方案:
1. 将 overflow: hidden 改为 overflow: visible
2. 或将绝对定位元素移到更外层的容器
3. 或使用 fixed 定位(相对于视口)
元素位置偏移
问题:元素位置与预期不符
检查:
- [ ] positionX/positionY 或 left/top 值是否正确
- [ ] 最近的 position: relative 祖先是哪个
- [ ] 是否有 margin/padding 影响
- [ ] transform 是否影响定位上下文
解决方案:
1. 确认定位参考点是正确的祖先元素
2. 检查 CSS 单位(px vs % vs rem)
3. 使用浏览器检查器的"元素选择"功能定位问题
内容不显示
问题:React 组件渲染但内容不可见
检查:
- [ ] 元素是否有 width/height(可能为 0)
- [ ] opacity 是否为 0
- [ ] visibility 是否为 hidden
- [ ] display 是否为 none
- [ ] z-index 是否被其他元素遮挡
- [ ] color 是否与背景色相同
解决方案:
1. 在开发者工具中检查 Computed 面板
2. 临时添加边框或背景色调试:border: 1px solid red
3. 检查条件渲染逻辑
Tailwind 类不生效
问题:Tailwind CSS 类没有应用
检查:
- [ ] 类名拼写是否正确
- [ ] 是否被更高优先级的样式覆盖
- [ ] 动态类名是否正确生成(字符串拼接问题)
- [ ] tailwind.config.js 中 content 配置是否包含该文件
解决方案:
1. 使用 !important 临时测试:!overflow-visible
2. 检查 className 是否正确传递
3. 使用内联 style 作为备选方案
3. 浏览器调试命令
在浏览器控制台运行:
// 高亮所有绝对定位元素
document.querySelectorAll('[style*="position: absolute"]').forEach(el => {
el.style.outline = '2px solid red';
console.log(el, getComputedStyle(el));
});
// 查找 overflow: hidden 的容器
document.querySelectorAll('*').forEach(el => {
const style = getComputedStyle(el);
if (style.overflow === 'hidden' || style.overflowX === 'hidden' || style.overflowY === 'hidden') {
el.style.outline = '2px dashed blue';
console.log('overflow-hidden:', el);
}
});
// 检查元素的完整 computed 样式
const el = document.querySelector('.your-selector');
console.table({
position: getComputedStyle(el).position,
overflow: getComputedStyle(el).overflow,
display: getComputedStyle(el).display,
width: getComputedStyle(el).width,
height: getComputedStyle(el).height,
top: getComputedStyle(el).top,
left: getComputedStyle(el).left,
});
// 查找定位祖先
function findPositionedAncestor(el) {
let current = el.parentElement;
while (current) {
const position = getComputedStyle(current).position;
if (position !== 'static') {
console.log('Positioned ancestor:', current, 'position:', position);
return current;
}
current = current.parentElement;
}
console.log('No positioned ancestor found, using viewport');
return null;
}
findPositionedAncestor(document.querySelector('.your-selector'));
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.
- 1mo ago First seen · 216 lines · 35 tokens per session scan A 38bfe7d7ab0b
css-debug is a skill published in the GitHub repository majiayu000/spellbook (288 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 1,606 once invoked, about $0.0001 per session on Opus 5.5. 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
workflow
A workflow skill for embedded-device projects that plans and runs building, flashing, debugging, observing, and diagnosis tasks.
RootCauseAnalysis
Structured incident investigation using Five Whys, Fishbone, blameless Postmortem, Fault Tree, Kepner-Tregoe, and FMEA — traces failures to systemic root causes rather than blaming humans. USE WHEN root cause, RCA, 5 whys, fishbone, postmortem, incident analysis, fault tree, why does this keep failing, blameless…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
recipe-diagnose
Investigate problem, verify findings, and derive solutions.
Vitals
Read-only macOS performance inspection: a deterministic CLI gathers the numbers, Interpretation.md turns them into a diagnosis instead of a data dump.
cao-session-management
Find available CAO (CLI Agent Orchestrator) agent profiles, and talk to the conductor and worker terminals of a running CAO session, including unblocking a stuck worker. Use when choosing a profile to launch, messaging or unblocking workers, or diagnosing a stuck session. For preflight, launching, session commands…