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 malue-ai/dazee-small --skill deep-doc-readergit clone --depth 1 https://github.com/malue-ai/dazee-smallWrote 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/malue-ai/dazee-small/deep-doc-reader)<a href="https://agentmods.dev/skills/malue-ai/dazee-small/deep-doc-reader"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/deep-doc-reader/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/malue-ai/dazee-small/deep-doc-reader"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/deep-doc-reader.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 | $0.00042 | $0.01052 |
| Opus 5.5 | $0.00017 | $0.00421 |
| Sonnet 5.5 | $0.00008 | $0.00210 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
deep-doc-reader 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.
What it actually says
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
## 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)
## 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
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 · 125 lines · 42 tokens per session scan A 56630ffe42e9
deep-doc-reader is a skill published in the GitHub repository malue-ai/dazee-small (36 stars, last pushed 7mo ago), licensed MIT. It adds 42 tokens to every session and 1,052 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
meta-web-to-pdf-briefing
Render a topic into a distributable PDF briefing in three steps: web search → bullet summary → styled PDF. Trigger when the user asks for a PDF briefing on a single topic.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
paper-reader
A reading assistant for computer-vision and deep-learning research papers. It can work with PDF files, arXiv papers, and papers stored in Zotero, a reference-management app.