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 mineru-pdfgit 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/mineru-pdf)<a href="https://agentmods.dev/skills/malue-ai/dazee-small/mineru-pdf"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/mineru-pdf/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/mineru-pdf"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/mineru-pdf.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 | $0.00024 | $0.00629 |
| Opus 5 | $0.00012 | $0.00315 |
| Sonnet 5 | $0.00005 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
mineru-pdf 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 10d 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
MinerU PDF 解析
本地解析 PDF 文档为结构化 Markdown 或 JSON，保留标题层级、表格、列表等结构。CPU 运行，数据不出本机。
使用场景
- 用户说「帮我把这个 PDF 转成 Markdown」「提取这个 PDF 的内容」
- 需要从 PDF 中提取结构化文本用于后续分析
- 扫描件 PDF 需要 OCR 提取文字（配合 OCR 类 Skill）
- 批量处理多个 PDF 文件
与其他 PDF 处理 Skill 的区别
| 工具 | 擅长 | 局限 |
|---|---|---|
| nano-pdf | 简单文本提取、PDF 元数据 | 不保留结构 |
| pdf-toolkit | 合并/拆分/加密/水印 | 不做内容解析 |
| mineru-pdf | 结构化解析（标题/表格/列表） | 安装包较大 |
优先使用 mineru-pdf 做内容提取，pdf-toolkit 做文件操作。
执行方式
安装
pip install magic-pdf
基本用法
magic-pdf -p /path/to/document.pdf -o /path/to/output/ -m auto
参数说明：
-p：输入 PDF 路径-o：输出目录-m：模式选择auto：自动判断（推荐）txt：纯文本 PDFocr：扫描件 PDF
Python API
from magic_pdf.data.data_reader_writer import FileBasedDataWriter, FileBasedDataReader
from magic_pdf.pipe.UNIPipe import UNIPipe
reader = FileBasedDataReader("")
writer = FileBasedDataWriter(output_dir)
pdf_bytes = reader.read(pdf_path)
pipe = UNIPipe(pdf_bytes, model_list=[], image_writer=writer)
pipe.pipe_classify()
pipe.pipe_analyze()
pipe.pipe_parse()
md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
输出内容
解析后在输出目录生成：
*.md：Markdown 格式的结构化内容images/：提取的图片*.json：结构化元数据
输出规范
- 保留原文档的标题层级（H1-H6）
- 表格转换为 Markdown 表格
- 图片提取并以
引用 - 页码标注在章节末尾
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.
- 10d ago First seen · 86 lines · 24 tokens per session scan A 295ed4badf7a
mineru-pdf is a skill published in the GitHub repository malue-ai/dazee-small (36 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 629 once invoked, about $0.0001 per session on Opus 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
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
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.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.