deep-doc-reader
Deep analysis and Q&A for long documents (PDF reports, contracts, papers, manuals).
Skill by malue-ai
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/malue-ai-deep-doc-reader
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/deep-doc-reader
What's inside
- Skill name
deep-doc-reader- Description
- Deep analysis and Q&A for long documents (PDF reports, contracts, papers, manuals). Uses PageIndex MCP to build hierarchical tree indexes and reason over document structure for precise section-level retrieval.
- License
- MIT
- Instructions
- 114 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# 长文档深度阅读与问答
对长 PDF(年报、合同、论文、手册)进行结构化理解和精准问答。通过 PageIndex MCP 将文档构建为层级树索引,实现章节级定位和推理检索。
## 使用场景
- 用户说「帮我分析这份年报里 Q3 的营收数据」
- 用户说「这份合同的违约条款在哪?具体怎么写的?」
- 用户说「这篇 80 页的论文,实验方法部分说了什么?」
- 用户说「帮我找这份手册里关于安装步骤的部分」
- 用户需要反复询问同一份长文档的不同内容
## 何时使用此 Skill(而非其他工具)
```
判断逻辑:
文档相关请求
├── 文件在哪?找某个文件 → 用 local-search
├── 简单摘要/概述 → 用 summarize
├── 编辑 PDF 内容 → 用 PDF 读取类 Skill
├── 创建 Word/Excel → 用 word-processor / excel-analyzer
└── 长文档深度问答(以下场景)→ 用 deep-doc-reader ✅
├── PDF 超过 20 页
├── 需要精确定位到具体章节/页码
├── 需要反复查询同一文档的不同部分
└── 需要理解文档的层级结构
```
## 工作流程
### 第一步:上传文档建立索引
用户提供 PDF 文件后,通过 PageIndex MCP 工具上传并建立树索引:
```
用户提供 PDF 路径或 URL
↓
调用 PageIndex MCP 上传文档
↓
PageIndex 自动构建层级树索引(目录 → 章节 → 子章节)
↓
返回文档 ID,后续查询使用此 ID
```
**注意**:
- 首次上传需要等待索引构建(大文档约 1-3 分钟)
- 索引构建完成后,后续查询都是即时的
- 免费额度:1000 页
### 第二步:基于树索引进行问答
```
用户提问:「Q3 营收数据是多少?」
↓
PageIndex 通过树结构推理导航:
文档根节点 → 财务数据章节 → Q3 季度报告 → 营收数据
↓
返回精确内容 + 页码引用
↓
整理回答,附上来源页码
```
### 第三步:多轮追问
同一文档支持多轮追问,无需重新上传:
```
用户:「Q3 营收多少?」 → 回答 + 页码
用户:「跟 Q2 对比呢?」 → 自动导航到 Q2 部分
用户:「管理层怎么解释这个变化?」 → 定位 MD&A 章节
```
## 输出格式
### 标准回答格式
```markdown
## 回答
[具体回答内容]
### 来源
- 📄 第 87 页 - 第三季度财务摘要
- 📄 第 92-93 页 - 营收明细表
```
### 结构概览格式(用户要求了解文档结构时)
```markdown
## 文档结构
📑 XXX 年度报告(共 156 页)
├── 第一章:公司概况(p.1-15)
├── 第二章:经营情况讨论(p.16-45)
│ ├── 2.1 行业形势(p.16-22)
│ ├── 2.2 经营成果(p.23-38)
│ └── 2.3 现金流分析(p.39-45)
├── 第三章:财务报表(p.46-120)
│ ├── 3.1 资产负债表(p.46-52)
│ ├── 3.2 利润表(p.53-60)
│ └── ...
└── 附录(p.121-156)
```
## 输出规范
- 回答必须附上页码引用(用户可验证)
- 数据类回答直接引用原文数字,不做推算
- 长回答分段落,每段标注来源章节
- 如果文档中找不到相关内容,明确告知用户From malue-ai/dazee-small, MIT.
More from malue-ai/dazee-small
- 0.496score
deep-research
malue-ai
Conduct multi-step autonomous research on any topic.
SkillDFreshness: D★ 37Claude Code +9 - 0.496score
excel-fixer
malue-ai
Auto-detect and fix common Excel formatting issues like merged cells, inconsistent types, duplicate headers, and encoding problems.
SkillDFreshness: D★ 37Claude Code +9 - 0.496score
code-sandbox
malue-ai
Secure sandboxed code execution for AI-generated scripts.
SkillDFreshness: D★ 37Claude Code +9 - 0.496score
cross-app-workflow
malue-ai
Chain multiple local apps and skills into complex multi-step workflows.
SkillDFreshness: D★ 37Claude Code +9 - 0.496score
elegant-reports
malue-ai
Generate beautifully designed PDF reports with Nordic-style typography, charts, tables, and multi-page layouts using reportlab or fpdf2.
SkillDFreshness: D★ 37Claude Code +9 - 0.496score
excel-analyzer
malue-ai
Analyze and process Excel/CSV files using pandas and openpyxl.
SkillDFreshness: D★ 37Claude Code +9 - 0.496score
app-scanner
malue-ai
Discover installed applications on macOS and recommend the best app for user tasks.
SkillDFreshness: D★ 37Claude Code +9 - 0.496score
batch-file-converter
malue-ai
Batch convert files between formats - images (HEIC/PNG/JPG/WebP), documents (Markdown/HTML), and more using Python and system tools.
SkillDFreshness: D★ 37Claude Code +9 - 0.496score
competitive-intel
malue-ai
Monitor competitor websites, products, and social media for updates.
SkillDFreshness: D★ 37Claude Code +9 - 0.496score
content-reformatter
malue-ai
Reformat content for different platforms (WeChat, Zhihu, Xiaohongshu, Twitter, email).
SkillDFreshness: D★ 37Claude Code +9 - 0.496score
draw-io
malue-ai
Generate professional diagrams in draw.io XML format including flowcharts, org charts, UML diagrams, and network topology diagrams.
SkillDFreshness: D★ 37Claude Code +9 - 0.496score
feishu
malue-ai
Feishu (Lark) full integration — messages, documents, calendars, tasks, approvals, and meeting minutes via lark-oapi SDK.
SkillDFreshness: D★ 37Claude Code +9
Signals
- Stars
- 37
- Forks
- 2
- Open issues
- 3
- Last commit (this folder)
- Mar 6, 2026 (7 months ago)
- Last release
- Feb 26, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/malue-ai/dazee-small
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from malue-ai
- 0.496score
code-sandbox
malue-ai
Secure sandboxed code execution for AI-generated scripts.
SkillDFreshness: D★ 37Claude Code +9 - 0.496score
content-reformatter
malue-ai
Reformat content for different platforms (WeChat, Zhihu, Xiaohongshu, Twitter, email).
SkillDFreshness: D★ 37Claude Code +9 - 0.496score
app-scanner
malue-ai
Discover installed applications on macOS and recommend the best app for user tasks.
SkillDFreshness: D★ 37Claude Code +9 - 0.496score
batch-file-converter
malue-ai
Batch convert files between formats - images (HEIC/PNG/JPG/WebP), documents (Markdown/HTML), and more using Python and system tools.
SkillDFreshness: D★ 37Claude Code +9 - 0.496score
competitive-intel
malue-ai
Monitor competitor websites, products, and social media for updates.
SkillDFreshness: D★ 37Claude Code +9 - 0.496score
cross-app-workflow
malue-ai
Chain multiple local apps and skills into complex multi-step workflows.
SkillDFreshness: D★ 37Claude Code +9
Cite this page
deep-doc-reader skill. Agent Mart. https://agentmart.dev/skills/malue-ai-deep-doc-reader (last updated 2026-10-24)