Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/InternScience/ChemClawnpx agentmods add skills/internscience/chemclaw/mineru-pdf-converterWrote 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/internscience/chemclaw/mineru-pdf-converter)<a href="https://agentmods.dev/skills/internscience/chemclaw/mineru-pdf-converter"><img src="https://agentmods.dev/badge/skills/internscience/chemclaw/mineru-pdf-converter/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/internscience/chemclaw/mineru-pdf-converter"><img src="https://agentmods.dev/badge/skills/internscience/chemclaw/mineru-pdf-converter.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 | $0.00152 | $0.01490 |
| Opus 5 | $0.00076 | $0.00745 |
| Sonnet 5 | $0.00030 | $0.00298 |
| Haiku 4.5 | $0.00015 | $0.00149 |
Grade A, and why
mineru-pdf-converter 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MinerU PDF Converter | PDF转Markdown工具
将 PDF 文件转换为 Markdown 格式,完整保留图片、表格、公式和文档结构。支持超过 600 页的大文件自动分批处理。
功能特性
- 提取文本、图片、表格、公式
- 保留文档原始布局和格式
- 自动处理超过 600 页的大文件(智能拆分、分批转换、自动合并)
- 输出包含:
full.md- 主 Markdown 文件images/- 提取的图片目录*.json- 布局分析和内容元数据*_origin.pdf- 原始 PDF 副本
快速开始
环境准备
需要 Python 3.8+ 和依赖包:
pip install requests urllib3 pymupdf
API Token 配置
Skill 已内置 API Key,无需额外配置即可使用。
如需使用自己的 Token,可通过以下方式(优先级从高到低):
# 方式1: 命令行参数(最高优先级)
python scripts/pdf_to_markdown.py paper.pdf -t YOUR_TOKEN
# 方式2: 环境变量
export MINERU_API_TOKEN="your-api-token"
# 方式3: 修改 Skill 内置 Key
# 编辑 API_KEY 文件 (位于 skill 目录下)
使用方法
命令行
# 单个文件(自动处理大文件)
python scripts/pdf_to_markdown.py paper.pdf -t $MINERU_API_TOKEN
# 批量转换整个目录
python scripts/pdf_to_markdown.py ./pdfs/ -t $MINERU_API_TOKEN -o ./output/
# 指定模型版本
python scripts/pdf_to_markdown.py paper.pdf -t $MINERU_API_TOKEN -m vlm
Python API
from scripts.pdf_to_markdown import convert_pdf, convert_large_pdf, batch_convert, get_api_token
# 获取 Token(自动从环境变量或 Skill 内置获取)
token = get_api_token()
# 单个文件转换(自动检测文件大小,大文件自动分批处理)
result = convert_large_pdf(
token=token,
pdf_path="large_paper.pdf", # 支持任意页数
output_dir="output/paper",
model_version="vlm"
)
print(result["files"]) # 查看提取的所有文件
print(result.get("batches")) # 如果分批处理,显示批次数量
# 批量转换
results = batch_convert(
token=token,
pdf_paths=["a.pdf", "b.pdf"],
output_base_dir="output"
)
大文件处理说明
MinerU API 单文件限制 600 页。本 Skill 已内置智能处理:
- 自动检测:检测 PDF 页数是否超过 600 页
- 智能拆分:按 600 页为一批次拆分 PDF(使用 PyMuPDF)
- 分批转换:依次转换每个批次
- 自动合并:将各批次的 Markdown 和图片合并为完整文件
- 清理临时文件:处理完成后自动清理拆分产生的临时文件
示例输出(1655 页 PDF):
[LargePDF] 总页数: 1655
[LargePDF] 文件超过 600 页,需要分批处理
[Split] PDF 共 1655 页,将拆分为 3 个批次(每批最多 600 页)
[Split] 批次 1/3: 第 1-600 页 -> orca_part001.pdf
[Split] 批次 2/3: 第 601-1200 页 -> orca_part002.pdf
[Split] 批次 3/3: 第 1201-1655 页 -> orca_part003.pdf
# 各批次依次转换...
[Merge] 合并 3 个 Markdown 文件...
[LargePDF] 大文件处理完成!
What ships with it
2 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.
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.
- 11d ago First seen · 169 lines · 152 tokens per session scan A c4f9cd4739d5
mineru-pdf-converter is a skill published in the GitHub repository InternScience/ChemClaw (52 stars, last pushed 5mo ago), licensed MIT. It adds 152 tokens to every session and 1,490 once invoked, about $0.0008 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 2026-08-30.
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.