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/backtocimacoppi/praxis/doc-html-stylenpx skills add BackToCimaCoppi/Praxis --skill doc-html-stylegit clone --depth 1 https://github.com/BackToCimaCoppi/PraxisWrote 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/backtocimacoppi/praxis/doc-html-style)<a href="https://agentmods.dev/skills/backtocimacoppi/praxis/doc-html-style"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/doc-html-style.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 | $0.00068 | $0.02131 |
| Opus 5 | $0.00034 | $0.01066 |
| Sonnet 5 | $0.00014 | $0.00426 |
| Haiku 4.5 | $0.00007 | $0.00213 |
Grade A, and why
doc-html-style 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 5d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
桌面端富色彩文档 HTML 样式规范
一句话：先判形状、按语义角色配色、token 化明暗主题、桌面优先、自包含单文件——不套模板，套的是判断力 + 一组硬规则 + 一个自检脚本。
0. 适用/不适用
| 场景 | 处理方式 | |
|---|---|---|
| ✅ 适用 | 技术文档、设计文档、业务QA、评审报告、复盘总结等要写成 HTML 成品供人在电脑上阅读 | 走本 skill 全流程 |
| ➡️ 交接 | 手机端页面预览/效果图（如小程序页面还原） | 转 design-preview，那是750px舞台+手机边框的约定，和本skill的桌面优先方向相反 |
| ➡️ 交接 | 产物是 Claude Artifact（走 Artifact 工具发布） | 转 artifact-design，那边受 CSP 沙盒限制（字体要内联data URI等），本skill的文档是普通本地/仓库文件，没有这层限制 |
| ➡️ 交接 | 文档里要嵌入真实数据图表（折线图/柱状图/散点图等） | 图表内部的配色、图例、可区分度规则转 dataviz，本skill只管文档整体的版式和色彩体系，不重新发明图表配色 |
| ➡️ 交接 | "这段内容该写进L几层文档""这个矛盾该听哪份文档的" | 转 doc-layer-system，本skill不管内容归层，只管已经定好要写的内容怎么呈现成HTML |
1. 先判断文档形状（核心机制，替代"选模板"）
动笔前必须先想清楚，而不是从骨架库里选一个：
| 问题 | 影响什么 |
|---|---|
| 读者是谁？（同事/客户/长辈/自己存档） | 决定语气克制度、术语密度 |
| 篇幅多大？一屏能看完，还是要翻很久？ | 决定要不要加目录导航（见第2节） |
| 主信息载体是什么？代码 / 决策表格 / 问答对 / 时间线 / 纯叙述 | 决定主视觉语言用什么承载——不是套哪个骨架，是这份文档"主要靠什么讲话" |
| 要不要导出打印/转PDF分享？ | 决定要不要写 @media print |
| 这次投入多大的视觉设计精力？ | 借用"实用 vs 精修"这把尺子——内部小QA记录用不着跟对外设计文档一样精修，先掂量清楚再动笔，别每次都往最大做 |
references/形态标定样例.md 里有三种典型形状的落地片段，遇到没见过的形状（比如时间线/复盘）现场按这套判断逻辑推，不强行往三个例子里套。
2. 硬规则（结构，任何形状都适用）
- 自包含单文件：CSS/JS 全部内联在
<style>/<script>里，不外链 CDN 字体或脚本。 - 桌面优先尺寸：内容区一般
max-width定在 1000–1400px 之间居中，用clamp()做流式排版。明确不用 375/750px 手机舞台或scale(0.5)——那是design-preview的约定，本skill反过来。 - token 化明暗主题（抄
artifact-design验证过的机制，三层缺一不可）：- 语义色定义在
:root的自定义属性上； - 用
@media (prefers-color-scheme: dark)覆盖同一批变量，跟随系统； - 再用
:root[data-theme="dark"]/:root[data-theme="light"]覆盖一层，保证手动切换能压过系统偏好。 组件样式只准吃这些 token，不准在组件规则里写死颜色值。
- 语义色定义在
- 宽内容自己滚，页面不滚：表格、代码块等宽内容各自套
overflow-x:auto的容器，body本身绝不允许横向滚动。 - 数字对齐：表格里的数字列用
font-variant-numeric: tabular-nums。 - 目录导航看篇幅给：长文档（需要翻页/多个大章节）才加 sticky 目录或锚点导航；一屏能看完的短文档不强行加目录，加了反而是噪音。
3. 色彩纪律（本skill的差异化重点——"更丰富但不失控"）
本 skill 的目标是比朴素的单色调更丰富的配色，但"丰富"不等于"随便加颜色"，靠以下纪律兜底：
- 颜色按语义角色/轴分配，不做装饰性撒色。常见轴：状态轴（完成/进行中/阻塞/风险）、类别轴（不同模块/类型）、结论轴（通过/待定/驳回）。同一个轴的色相在同一份文档里固定，不中途洗牌。
- 同时出现的语义轴建议不超过 2–3 个——这是防止"更丰富"滑向"大杂烩"的唯一硬限制。轴一旦超过3个，说明这份文档想同时表达的维度太多，应该拆分层级（比如用嵌套分组）而不是继续加色相。
- 写完配色，跑一遍自检脚本：
scripts/check_contrast.py，把每个语义色在浅色模式和深色模式下的"文字色-背景色"组合都跑一遍，任何一组不达标（正文对比度<4.5:1，大字/图形<3:1）都要回去调整，不能凭肉眼感觉"应该还行"。 - 参考起点：
references/色彩与主题参考.md里有一套浅/深两色系的示例语义色，可以当起点看效果、照着调整，不是强制调色板，照抄整套等于又做了个模板。 - "AI感"反模式清单（文档场景专用，出现即可视为设计投入不走心）：
- 每一张卡片不分主次都套同样的阴影+圆角；
- 标题滥用渐变文字；
- 强调色没有语义绑定，纯粹"好看就用"；
- emoji 当图标大量堆砌当装饰；
- 大面积紫蓝渐变当背景/hero区。
What ships with it
3 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.
- 5d ago First seen · 98 lines · 68 tokens per session scan A 5eaaa35d67ea
doc-html-style is a skill published in the GitHub repository BackToCimaCoppi/Praxis (6 stars, last pushed 11d ago), licensed Apache-2.0. It adds 68 tokens to every session and 2,131 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 2026-08-31.
Other skills, from other repositories
release-sync
Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.
signature-request
Pre-signature gate and routing plan for a finalized document — verifies exact legal entity names, signatory authority, attached exhibits, filled blanks, consistent dates, and counterparty details, then sets the signing order (sequential vs. parallel, with reasons), writes envelope instructions for any e-sign tool, and…
tax-prep
Organizes tax season — an organizer, not tax advice: a document checklist by category (income, expenses, assets, payroll, prior filings), an expense-category sweep that flags plausibly missed deductions in generic jurisdiction-agnostic categories, a quarterly-estimate calendar template, a clean handoff pack for the…
ai-seo
Optimizes content to get cited by AI assistants (ChatGPT, Perplexity, Google AI Overviews) and rank in classic SERPs — entity-rich intros, question-shaped H2s, 40-60 word extractable answers, schema.org JSON-LD, llms.txt, internal links, and E-E-A-T signals. Runs in audit or rewrite mode. Use when the user says…
pipeline-review
Audits pipeline health from a deal list (CSV, table or plain notes) — prioritises deals, flags zombies and single-threaded risks, checks close-date realism and outputs a weekly action plan. Use when the user says "review my pipeline", "which deals should I focus on", "why is nothing closing", or shares a list of open…
second-reader
Build and run a source-verified Markdown knowledge vault (opens as an Obsidian vault). Ingests books, PDFs, transcripts, and articles into atomic, cross-linked, cited notes, then gates every note and every answer behind an independent verification pass that re-reads the source cold and loops until a round finds…