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 wpsnote/wpsnote-skills --skill wpsnote-beautifiergit clone --depth 1 https://github.com/wpsnote/wpsnote-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/skills/wpsnote/wpsnote-skills/wpsnote-beautifier)<a href="https://agentmods.dev/skills/wpsnote/wpsnote-skills/wpsnote-beautifier"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/wpsnote-beautifier/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/wpsnote/wpsnote-skills/wpsnote-beautifier"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/wpsnote-beautifier.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 | $0.00232 | $0.03128 |
| Opus 5.5 | $0.00093 | $0.01251 |
| Sonnet 5.5 | $0.00046 | $0.00626 |
| Haiku 4.5 | $0.00023 | $0.00313 |
Grade A, and why
wpsnote-beautifier 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WPS 笔记智能美化
概述
对 WPS 笔记进行智能美化，包括：结构层级优化、高亮块/分栏强调重点、配色方案应用、富文本样式写入。通过 WPS 笔记 MCP 工具（user-wpsnote）完成所有读写操作。
颜色克制总原则（最高优先级）
美化的核心目标是提升可读性，而非"让文档变得五颜六色"。必须遵守以下约束：
- 全文只用 1 种主色调 — 从配色方案中选定一个色系后，标题、加粗关键词、高亮块-要点、分栏-正面全部使用该色系，不混入其他色系
- 辅助色最多 1 种 — 仅用于"提示/注意"型高亮块（如黄色系），且全文该类型不超过 1-2 处
- 警告色按需使用 — 红色系仅在文档确实存在风险/警告内容时才使用，没有则不加
- 高亮块总数控制 — 全文高亮块不超过 3-5 个（短文档 1-2 个），类型不超过 2 种
- 分栏总数控制 — 全文分栏不超过 2-3 处，背景色使用同色系浅色
- 行内高亮极度克制 — 全文行内高亮不超过 5-8 处，颜色统一为 1 种
- 正文不上色 — 普通段落文字保持默认黑色，绝不给整段文字加颜色
- 宁少勿多 — 不确定是否需要加颜色/高亮时，选择不加
工作流程
Phase 1: 分析文档现状
必须先执行以下步骤，不要跳过：
- 调用
get_note_outline获取笔记大纲（包含 block_id、类型、文本预览） - 调用
read_note读取全文 XML - 调用
read_file读取本 Skill 的 XML 参考文件（首次美化时）
分析要点：
- 当前标题层级是否合理（是否全是
<p>没有标题、标题层级跳跃等） - 是否存在大段纯文本缺乏视觉分隔
- 是否有适合用高亮块强调的重点内容（结论、核心观点、警告、提示）
- 是否有适合用分栏对比展示的内容（对比、并列关系、优缺点）
- 现有格式元素（加粗、颜色等）的使用情况
Phase 2: 设计美化方案
根据分析结果，制定具体美化计划。向用户简要展示方案并确认后再执行。
方案应包含：
- 结构调整计划 — 哪些内容需要提升/降低标题层级，哪里需要增加分隔
- 强调元素计划 — 哪些内容用高亮块、哪些用分栏（严格控制数量，参照"颜色克制总原则"）
- 配色方案选择 — 从预设方案中选择 1 个主色系（见 reference/color-schemes.md），全文统一使用该色系，不混用多个方案
- 颜色使用预算 — 明确列出：高亮块 X 个、分栏 X 处、行内高亮约 X 处，确保总量克制
- 预计操作数量 — 让用户对改动范围有预期
Phase 3: 执行美化
执行前必须刷新大纲： 每次写入前调用 get_note_outline 获取最新 block_id。
优先使用 batch_edit 批量执行，减少调用次数。执行顺序固定为：delete → replace → update_attrs → insert。
分批执行时，每批完成后重新获取大纲再继续。
Phase 4: 验证结果
- 调用
read_note检查最终效果 - 确认层级结构正确、颜色一致、无格式错乱
- 向用户汇报完成情况
结构层级设计规则
标题层级规范
| 层级 | 用途 | 说明 |
|---|---|---|
<h1> |
文档主标题 | 全文仅一个，位于开头 |
<h2> |
一级章节 | 文档的主要板块划分 |
<h3> |
二级章节 | 板块内的子主题 |
<h4> |
三级章节 | 细分内容，按需使用 |
<h5>/<h6> |
极少使用 | 仅在层级确实需要时 |
结构调整策略
扁平化文档（全是段落无标题）：
- 识别语义分界点（话题转换处）
- 将领头段落提升为
<h2>或<h3> - 为无标题章节生成概括性标题
层级跳跃修复（如 h1 直接到 h4）：
- 补齐中间层级，或将深层标题上提
过深层级扁平化（超过 4 级）：
- 将
<h5>/<h6>内容合并到上级或转为加粗段落
高亮块使用规则
适用场景与配色
| 场景 | 背景色 | 边框色 | 推荐 emoji |
|---|---|---|---|
| 核心结论/要点 | #E8F5E9 |
#4CAF50 |
✅ 或 💡 |
| 重要提示/注意 | #FFF3E0 |
#FF9800 |
⚠️ 或 📌 |
| 警告/风险 | #FFEBEE |
#F44336 |
❗ 或 🚨 |
| 引用/摘要 | #E3F2FD |
#2196F3 |
📖 或 💬 |
| 定义/术语 | #F3E5F5 |
#9C27B0 |
📝 或 🔍 |
| 最佳实践 | #E0F7FA |
#00BCD4 |
⭐ 或 🎯 |
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.
- 1mo ago First seen · 254 lines · 232 tokens per session scan A 031092729d1b
wpsnote-beautifier is a skill published in the GitHub repository wpsnote/wpsnote-skills (183 stars, last pushed yesterday), licensed MIT. It adds 232 tokens to every session and 3,128 once invoked, about $0.0009 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
research-hub
Use research-hub to operate Zotero, Obsidian, and NotebookLM research workflows through CLI, MCP, REST, and dashboard. Trigger when the user asks to find papers, ingest sources, organize a literature review, build Obsidian research notes, upload sources to NotebookLM, inspect clusters, generate AI briefs, or maintain…
write-docs-cn
A guide to writing project documentation, especially README files. It explains how tutorials differ from reference material and where each kind of information belongs.
write-tech-cn
A writing guide for Chinese technical documents such as READMEs, tutorials, blogs, and technical explanations. It focuses on direct conclusions, clear actions, natural Chinese, and consistent technical terms.
pdf-image-text-extractor
A tool for reading text from images and PDF files, including scanned documents. OCR means recognizing printed or handwritten characters in an image and turning them into editable text.
youtube-digest
A transcript extractor for YouTube videos. It reads available subtitles or automatically generated captions, can translate non-Chinese captions into Chinese, and can export the text to Excel, a spreadsheet application.
hyalo-okf
Maintain Open Knowledge Format vaults with Hyalo's OKF index, log, and conformance commands.