What is content-digest?

A skill for turning supplied material into structured knowledge notes and saving them to WPS Notes, a note-taking service.

Summarizing and extracting notes from webpages, documents, PDFs, images, and other provided content when the user intends to save the result.

It organizes information from sources such as links, files, images, and pasted text so it can be kept as notes.

content-digest — Skill for Claude Code by wpsnote/wpsnote-skills

Install

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.

Any agent

npx skills add wpsnote/wpsnote-skills --skill content-digest

Clone the repo

git clone --depth 1 https://github.com/wpsnote/wpsnote-skills

Made for: Claude Code.

Or install content-skills, the plugin that ships this one along with the rest of its 10 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/content-digest/github.svg)](https://agentmods.dev/skills/wpsnote/wpsnote-skills/content-digest)

Your own site

<a href="https://agentmods.dev/skills/wpsnote/wpsnote-skills/content-digest"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/content-digest/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/wpsnote/wpsnote-skills/content-digest"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/content-digest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 254 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,541 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00254	$0.03541
Opus 5.5	$0.00102	$0.01416
Sonnet 5.5	$0.00051	$0.00708
Haiku 4.5	$0.00025	$0.00354

Measured 1mo ago against content hash 3dde73edb436, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

content-digest 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/pdf_to_images.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/content-digest/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Digest — 万能内容提炼

将任意来源的内容转化为结构化知识笔记，自动保存到 WPS 笔记。

工作流

第一步：识别输入类型并获取内容

输入类型	获取方式	图片解读路径
URL / 网页 / 公众号链接	`WebFetch(url)` 提取正文；若被拦截 → 笔记写「访问受限，如需提炼请手动复制原文到 AI 工具处理」	正文中如有图片 URL → 提取后走「网络图片」流程
本地文件（文本类 PDF/Word）	`Read(绝对路径)`；若提取文字 < 50 字 → 执行「图片类 PDF 转换流程」	转 PNG 后逐页 `Read` 视觉解读
本地图片（jpg/png/gif/webp）	`Read(图片路径)` → AI 视觉分析（不尝试插入，MCP 不支持本地路径）	直接 `Read`
网络图片 URL	`insert_image(url)` 插入笔记 → `read_image(note_id, block_id)` 取 base64 → AI 视觉解读	`read_image` ← WPS 笔记原生识图能力
笔记内已有图片	`get_note_outline` 定位 image block → `read_image(note_id, block_id)` 取 base64 → AI 视觉解读	`read_image` ← WPS 笔记原生识图能力
直接粘贴文本 / 邮件	无需获取，直接进入第二步；判断依据：消息中无 URL 也无文件路径	—
多篇内容	全部提炼后合并，标题用「内容提炼合集 · YYYY-MM-DD」	每类图片按对应路径处理

支持的完整文件格式见 references/supported-formats.md 图片处理细节：本地图片 → Read 直接视觉分析；网络图片 → insert_image 插入笔记再 read_image 取 base64 解读；网页内嵌图片 → 从正文提取 URL 后走网络图片流程；笔记内已有图片 → get_note_outline 定位后 read_image 解读；PDF/PPT 图片页 → 见下方处理流程。

第二步：提炼内容

文字类：

一句话概括：不超过 50 字，动词开头，忠实原文
核心观点：用自己的语言转述，不直接复制原文句子
金句摘录：必须是原文原句，逐字引用，不改动
我的思考：用户未提供则留 [待补充]，不编造

图片类（所有来源统一使用以下模块）：

📌 一句话概括：图片的核心内容，10 字以内
🔍 内容解读：分点描述图片内容（文字/界面/人物/图表/图形设计等）；有文字则逐字提取；有数据则标明数值
💡 核心信息：图片传达的主要观点或信息
💬 我的思考：图片适用场景、设计亮点或可借鉴之处

图片解读不能跳过：笔记的核心价值是把「看过就忘」的图片变成可检索的文字。哪怕图片模糊或内容抽象，也必须描述所能观察到的一切——否则笔记等于空白。

行动清单（可选模块）：

行动清单只在内容包含明确可执行建议时生成，不是每篇都需要：

✅ 适合生成：教程/指南类（「三步完成 X」）、方法论文章（「你应该做 Y」）、含待办事项的邮件、任务型文档
❌ 不适合生成：纯观点/叙述类文章、数据分析报告、故事类内容、图片笔记

有疑问时默认不生成，比强行生成空洞的行动清单更好。

输出 XML 模板（含配色）见 references/output-templates.md
来源标识与原文附录规则见 references/source-rules.md

排版规范（写入时强制执行）

区域	排版方式	颜色
来源元信息	`<blockquote>`	无
一句话概括	`<h2>📌 一句话概括</h2>` + `<p>`	无
核心观点	`<h2>💡 核心观点</h2>` + `<columns><column columnBackgroundColor="#EBF2FF">`	浅蓝（`highlightBlock` 颜色不生效，改用 columns）
金句摘录	`<h2>⭐ 金句摘录</h2>` + `<columns><column columnBackgroundColor="#FFF5EB">`	浅橙（同上）
我的思考	`<h2>💬 我的思考</h2>` + `<p>`	无
行动清单	`<h2>✅ 行动清单</h2>` + `<p listType="todo" checked="0">`	无

Read the full file on GitHub · 182 lines

Files

What ships with it

4 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.

Changes

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 · 182 lines · 254 tokens per session scan A 3dde73edb436

Subscribe to this mod's changes

content-digest is a skill published in the GitHub repository wpsnote/wpsnote-skills (183 stars, last pushed today), licensed MIT. It adds 254 tokens to every session and 3,541 once invoked, about $0.0010 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.

Productivity Writing and docs cli deepseek-harness dsh knowledge-management mcp wpsnote

dsh-onboarding

Guidance for helping someone use DeepSeek Harness, a local runtime for coding agents, for the first time. It explains the runtime, profiles, workspace, permissions, and how extensions are discovered.

pingfanfan/hello-dsh · 60 tokens

query

Answer questions about the wiki by searching, reading, and synthesizing relevant scraps with [[Title]] citations. Use this when the user wants to query the wiki, ask what they have written about a topic, compare scraps, find related notes, or pull a synthesized overview from existing scraps.

boykush/scraps · 61 tokens

content-digest