← Back to Skills Marketplace
yinin2005

knowledge-digest

by yinin2005 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
209
Downloads
1
Stars
2
Active Installs
1
Versions
Install in OpenClaw
/install knowledge-digest
Description
将学习资料（PDF/教材/话题）转换为个性化、多模态的学习材料：手写笔记PDF、极简交互测验HTML、幻灯片PDF+PPTX、思维导图、音频课程。触发词：知识消化、学习材料、笔记生成、测验、幻灯片、思维导图、音频课程、课件、教材转换
README (SKILL.md)

知识消化助手

Overview

将教材、PDF 或话题转换为个性化、多模态的学习材料。根据年级水平（小学/初中/高中/大学/专业）自动调整内容深度和表达方式。

支持的输出格式

格式 关键词 说明
notes 笔记/手写笔记 手写风格笔记 PDF
quiz 测验/测试 极简 HTML 交互测验
slides 幻灯片/PPT PDF + PPTX 双版本
mindmap 思维导图 PNG + Mermaid 文本
audio 音频课程 师生对话 mp3，约15分钟
all 全部 生成所有格式

默认：mindmap + slides(PDF) + quiz

Workflow

阶段1：获取用户输入

  • 用户上传 PDF/教材（可选）
  • 或指定话题/方向
  • 年级水平（小学/初中/高中/大学/专业）
  • 期望输出格式

无资料时：询问用户选择"上传资料"或"帮我搜索并生成"。

阶段2：内容解析

提取章节结构、核心概念、关键术语、学习目标、知识点依赖关系，输出 JSON 结构供后续生成使用。

阶段3：按格式生成（见各格式指南）

阶段4：统一交付

\x3Cdeliver_assets>
\x3Citem>\x3Cpath>文件路径\x3C/path>\x3C/item>
\x3C/deliver_assets>

规则：只返回文件路径，禁止在对话中内嵌展示任何文件。

年级适配

年级 语言风格 内容深度
小学 活泼、故事化、鼓励性 生活化、简单
初中 引导式提问、基础术语 日常场景、适中难度
高中 逻辑推理、学术性 专业术语、高难度
大学/专业 研讨式、批判性思维 学术语言、专业深度

格式1：手写风格笔记（notes）

类型A（原文PDF → 叠加手写标注）：

  1. 逐页分析 PDF 内容，识别章节/概念/公式/问题
  2. 规划每页3-8处标注（蓝色：结构标注/概念解释；粉色：重点提问/解决方案）
  3. 生成带手写标注的页面图像
  4. 编译为 PDF（150 DPI，90%质量）

类型B（从零生成手写笔记）：

  1. 整理内容为层级结构（标题→章节→核心概念→要点→示例）
  2. 设计手写风格版式（标题大、正文手写要点、有图解和标注）
  3. 逐页生成手写风格图像
  4. 编译为 PDF

颜色规则：全 PDF 统一不超过2种颜色（默认蓝+粉）

格式2：交互测验（quiz）

  • 每节至少5道题：选择题2-3道、判断题1-2道、填空题1-2道
  • 难度：40%简单、40%中等、20%困难
  • 每题含正确答案+有教学价值的解析
  • 生成单个 HTML 文件，视觉极简（纯白背景、无装饰）
  • 交互：点击选项→选中→提交→即时反馈对错+解析→显示总分

格式3：幻灯片（slides）

  1. 创建 content_script.md：每张幻灯片用50-80字描述信息内容，专注信息架构，不描述视觉细节
  2. 逐张生成图像：第一张用 gen_images，后续用 edit_images 以上一张为 base
  3. 编译：生成 PDF（150 DPI）+ PPTX

视觉原则：

  • 图表/插图是信息的主要载体，不是装饰背景
  • 拒绝"大面积留白+居中文字"的低效模式
  • 信息密度匹配专业信息图

格式4：思维导图（mindmap）

  • 层级不超过4层，根节点=主题，一级=核心概念，二级=细节要点
  • 每节点不超过10字
  • 输出 PNG + Mermaid 文本

格式5：音频课程（audio）

  • 师生对话形式，约15分钟，约150-180字/分钟
  • 所有例子从用户兴趣领域取材
  • 老师声音温和专业，学生声音好奇活泼
  • 输出 mp3

通用约束

  • 内容必须基于原教材，不添加未经验证的信息
  • 测验HTML保持极简：不使用 UI 框架、渐变、阴影
  • 笔记全 PDF 严格限制不超过2种颜色
  • 禁止在对话中预览/内嵌展示任何生成文件
  • 音频文件禁止自动播放

Common Mistakes

  1. 内容偏离原教材，自行发挥
  2. 忽略年级适配，语言深度不当
  3. 笔记颜色过多
  4. 测验HTML过度设计
  5. 幻灯片文字主导、视觉无信息价值
  6. 幻灯片使用蓝色/紫色作为主题色（除非用户指定）
  7. 预览/内嵌展示生成文件
  8. 思维导图层级过深

文件命名与交付

格式 文件名
笔记 {topic}_notes.pdf
测验 {topic}_quiz.html
幻灯片 {topic}_slides.pdf + {topic}_slides.pptx
思维导图 {topic}_mindmap.png
音频 {topic}_audio.mp3

交付统一用 \x3Cdeliver_assets> 标签。

Usage Guidance
Before installing: 1) Confirm the host platform provides the toolchain the skill implicitly needs (image generation/editing, TTS for MP3, PDF→PPTX compilation) or whether you'll need to supply API keys/binaries. 2) Ask the skill author to clarify what gen_images/edit_images calls map to and how PPTX/mp3 are produced (local binaries vs external APIs). 3) Consider privacy: if you ask the skill to "search and generate", it may fetch external web content — avoid uploading sensitive student materials unless you know where outputs and source files are stored. 4) Request example output files (a sample notes PDF, quiz HTML, and one slide deck) to validate formatting constraints (colors, interactivity, no inline previews). 5) If you require offline or on-prem generation for compliance, verify the runtime environment can perform image/audio/PPTX generation without sending data to third-party services.
Capability Analysis
Type: OpenClaw Skill Name: knowledge-digest Version: 1.0.0 The 'knowledge-digest' skill is a legitimate educational tool designed to convert learning materials into various formats such as handwritten-style PDFs, interactive HTML quizzes, and audio courses. The SKILL.md file outlines a clear, task-oriented workflow with specific constraints on content depth and delivery methods (using the <deliver_assets> tag). There are no indicators of data exfiltration, malicious command execution, or prompt injection attacks.
Capability Assessment
✓ Purpose & Capability
The skill's name/description align with the instructions: it processes uploaded PDFs or a user-provided topic and produces notes, quizzes, slides, mindmaps and audio. It does not request unrelated credentials or config paths. One minor gap: the SKILL.md assumes the ability to generate and compile images, MP3 and PPTX but does not declare required binaries or services (e.g., image model, TTS, PDF/PPTX generator). This is plausibly platform-provided but is underspecified.
ℹ Instruction Scope
Instructions remain within the claimed scope (parse content, extract structure, generate specified artifacts). However the document references functions/tools by name (gen_images, edit_images) and compilation steps (compile to PDF/PPTX, produce MP3) without specifying how these should be executed or what external endpoints/APIs/binaries are used. Also the ‘help me search and generate’ fallback allows the agent to fetch web content — expected for the task, but it broadens the attack surface and privacy considerations.
✓ Install Mechanism
There is no install spec and no code files — instruction-only skills have minimal disk footprint and no automatic downloads. This is low risk from an install point of view.
✓ Credentials
The skill requests no environment variables, credentials, or config paths, which is proportionate for the declared functionality. Note that generating audio, PPTX or invoking external image models might normally require service keys or binaries; none are requested here, so confirm where generation will run and whether keys are needed at runtime.
✓ Persistence & Privilege
The skill is not always-included and does not request elevated persistence or modifications to other skills. Autonomous invocation is allowed (platform default) but that is not combined with other privileged or broad credential access.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install knowledge-digest
  3. After installation, invoke the skill by name or use /knowledge-digest
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
knowledge-digest 1.0.0 – 首次发布 - 全新推出多模态知识消化助手，支持输入教材/PDF/话题并自动适配年级 - 一键生成多种学习材料：手写风格笔记、极简交互测验、专业幻灯片、可视化思维导图、音频课程 - 各格式严格遵循内容深度、适龄表达与视觉规范 - 提供统一文件命名和交付流程，保障交互专业与合规 - 默认输出思维导图、PDF幻灯片和测验，支持自定义需求
Metadata
Slug knowledge-digest
Version 1.0.0
License MIT-0
All-time Installs 3
Active Installs 2
Total Versions 1
Frequently Asked Questions

What is knowledge-digest?

将学习资料（PDF/教材/话题）转换为个性化、多模态的学习材料：手写笔记PDF、极简交互测验HTML、幻灯片PDF+PPTX、思维导图、音频课程。触发词：知识消化、学习材料、笔记生成、测验、幻灯片、思维导图、音频课程、课件、教材转换. It is an AI Agent Skill for Claude Code / OpenClaw, with 209 downloads so far.

How do I install knowledge-digest?

Run "/install knowledge-digest" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is knowledge-digest free?

Yes, knowledge-digest is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does knowledge-digest support?

knowledge-digest is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created knowledge-digest?

It is built and maintained by yinin2005 (@yinin2005); the current version is v1.0.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments