MinerU zero-setup document extraction — convert PDFs, images, Word, and PowerPoint to Markdown instantly. No login, no token, no configuration. Just run and get results

MinerU fast extract — zero-setup, instant document extraction. Convert PDFs, images, Word (DOCX), and PowerPoint (PPTX) to Markdown with no login, no token,...

Security Scan

The skill's declared purpose (local, zero‑setup document extraction) and its requirements (just a CLI) are plausible, but the SKILL.md does not say whether processing is local or remote and the install step pulls an npm/go CLI that could phone home — you should verify the CLI's source before using it on sensitive documents.

Purpose & Capability

Name and description match the requested artifact: the skill only requires a single CLI binary (mineru-open-api) and its CLI commands in SKILL.md correspond to document extraction (PDF/Word/PPT/Image → Markdown). Requiring a mineru-open-api binary is coherent with the stated purpose.

Instruction Scope

Runtime instructions only tell the agent to invoke mineru-open-api flash-extract on local files or URLs. The SKILL.md does not disclose whether the CLI does all processing locally or uploads files to mineru.net or other remote services. The ability to pass remote URLs and the lack of any network/disclosure text is a scope concern because it affects confidentiality of documents the user provides.

Install Mechanism

Installers are npm (public registry) and go install from a GitHub module — these are common and traceable install routes. However, installing an npm package or a Go binary executes third‑party code on disk; that is expected but carries moderate risk. No direct downloads from unknown servers or URL shorteners were used.

Credentials

The skill declares no environment variables or credentials (which is consistent with 'no token' messaging). However, because the SKILL.md omits whether the CLI performs remote calls, there is an implicit risk that sensitive documents could be transmitted off‑device without requiring a token. The absence of any declared network endpoint or privacy statement is a proportionality/clarity concern.

Persistence & Privilege

The skill is not always: true, does not request persistent system configuration or other skills' configs, and only uses a single CLI tool — no elevated presence or special privileges are requested.

What to consider before installing

This skill appears to be a thin wrapper around a third‑party CLI (mineru-open-api). Before installing or using it on sensitive documents: 1) Inspect the mineru-open-api package and the referenced GitHub repo (check maintainers, recent commits, license, and whether processing is local). 2) Prefer running the CLI in a sandbox/container or on a throwaway VM for initial tests. 3) Test with non‑sensitive documents to observe network activity (e.g., monitor DNS/HTTP) to confirm whether files are uploaded. 4) If you need on‑device-only processing, verify the implementation explicitly states local processing or choose a well‑audited open‑source tool. If you cannot verify the binary's behavior, avoid using it with private or confidential documents.

Fast Document Extraction with mineru-open-api

Zero-setup, instant document parsing — no login, no token, no configuration needed. Supports tables and formulas (LaTeX).

Installation

npm install -g mineru-open-api

Or via Go (macOS/Linux):

go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest

Verify installation

mineru-open-api version

Quick start

mineru-open-api flash-extract report.pdf                     # PDF → Markdown (instant!)
mineru-open-api flash-extract report.pdf -o ./out/           # Save to file
mineru-open-api flash-extract resume.docx                    # Word → Markdown
mineru-open-api flash-extract slides.pptx                    # PowerPoint → Markdown
mineru-open-api flash-extract photo.png                      # Image → Markdown (OCR)
mineru-open-api flash-extract https://example.com/doc.pdf    # URL → Markdown

Supported input formats

Format	Supported
PDF (.pdf)	Yes
Images (.png, .jpg, .jpeg, .jp2, .webp, .gif, .bmp)	Yes
Word (.docx)	Yes
PowerPoint (.pptx)	Yes
URLs (remote files)	Yes

Command: flash-extract

mineru-open-api flash-extract <file-or-url> [flags]

Flags

Flag	Short	Default	Description
--output	-o	(stdout)	Output path (file or directory)
--language		ch	Document language
--pages		(all)	Page range, e.g. 1-10
--timeout		900	Timeout in seconds

Supported --language values

Values are organized by script/language family — each value covers all languages in its group.

Standalone language packs

Value	Included languages	说明
ch	Chinese, English, Chinese Traditional	中英文（默认值）
ch_server	Chinese, English, Chinese Traditional, Japanese	繁体、手写体
en	English	纯英文
japan	Chinese, English, Chinese Traditional, Japanese	日文为主
korean	Korean, English	韩文
chinese_cht	Chinese, English, Chinese Traditional, Japanese	繁体中文为主
ta	Tamil, English	泰米尔文
te	Telugu, English	泰卢固文
ka	Kannada	卡纳达文
el	Greek, English	希腊文
th	Thai, English	泰文

Language family packs

Value	Script/Family	Included languages
latin	Latin script (拉丁语系)	French, German, Afrikaans, Italian, Spanish, Bosnian, Portuguese, Czech, Welsh, Danish, Estonian, Irish, Croatian, Uzbek, Hungarian, Serbian (Latin), Indonesian, Occitan, Icelandic, Lithuanian, Maori, Malay, Dutch, Norwegian, Polish, Slovak, Slovenian, Albanian, Swedish, Swahili, Tagalog, Turkish, Latin, Azerbaijani, Kurdish, Latvian, Maltese, Pali, Romanian, Vietnamese, Finnish, Basque, Galician, Luxembourgish, Romansh, Catalan, Quechua
arabic	Arabic script (阿拉伯语系)	Arabic, Persian, Uyghur, Urdu, Pashto, Kurdish, Sindhi, Balochi, English
cyrillic	Cyrillic script (西里尔语系)	Russian, Belarusian, Ukrainian, Serbian (Cyrillic), Bulgarian, Mongolian, Abkhazian, Adyghe, Kabardian, Avar, Dargin, Ingush, Chechen, Lak, Lezgin, Tabasaran, Kazakh, Kyrgyz, Tajik, Macedonian, Tatar, Chuvash, Bashkir, Malian, Moldovan, Udmurt, Komi, Ossetian, Buryat, Kalmyk, Tuvan, Sakha, Karakalpak, English
east_slavic	East Slavic (东斯拉夫语系)	Russian, Belarusian, Ukrainian, English
devanagari	Devanagari script (天城文语系)	Hindi, Marathi, Nepali, Bihari, Maithili, Angika, Bhojpuri, Magahi, Santali, Newari, Konkani, Sanskrit, Haryanvi, English

Examples

mineru-open-api flash-extract report.pdf
mineru-open-api flash-extract report.pdf -o ./out/
mineru-open-api flash-extract report.pdf --language en
mineru-open-api flash-extract report.pdf --language latin
mineru-open-api flash-extract report.pdf --pages "1-5"
mineru-open-api flash-extract contract.docx -o ./out/
mineru-open-api flash-extract presentation.pptx -o ./out/
mineru-open-api flash-extract scan.jpg --language ch

Output behavior

• No -o flag: result goes to stdout; status/progress messages go to stderr
• With -o flag: result saved to file/directory; progress messages on stderr
• Markdown output includes extracted images saved alongside the .md file
• Tables are converted to Markdown tables
• Formulas are converted to LaTeX format (inline $...$ and block $$...$$)

Agent guidelines

When using this skill on behalf of the user:

• Always use flash-extract for any input — whether it's a local file or a URL (e.g. https://cdn-mineru.openxlab.org.cn/demo/example.pdf). Do NOT assume a URL means "web page". flash-extract handles URLs to document files directly.
• Quote file paths that contain spaces or special characters with double quotes. Example: mineru-open-api flash-extract "report 01.pdf".
• Don't run commands blindly on errors — explain the exit code and troubleshooting steps instead of re-running the command.
• Installation questions ("mineru 怎么安装") should be answered with the install instructions above.

Default output directory

When the user does NOT specify -o, generate a default output directory:

~/MinerU-Skill/<name>_<hash>/

• <name>: derived from the source, then sanitized (replace spaces and shell-unsafe characters with _, collapse consecutive _).
  • For URLs: last path segment (e.g. https://arxiv.org/pdf/2509.22186 → 2509.22186)
  • For local files: filename without extension (e.g. report.pdf → report)
• <hash>: first 6 characters of MD5 hash of the full original source.

echo -n "source" | md5sum | cut -c1-6   # Linux
echo -n "source" | md5 | cut -c1-6      # macOS

When the user specifies -o: use the user's path as-is.

Skill upgrade = CLI upgrade

When the user asks to upgrade this skill, re-install the CLI first:

npm install -g mineru-open-api@latest

Exit codes

Code	Meaning	Recovery
0	Success	—
1	General API or unknown error	Check network; retry; use --verbose
2	Invalid parameters / usage error	Check command syntax and flag values
4	File too large or page limit exceeded	Try a smaller file or fewer pages
5	Extraction failed	Document may be corrupted or unsupported
6	Timeout	Increase with --timeout

Troubleshooting

• Timeout on large files: Increase with --timeout 1600
• Extraction quality is poor: Try specifying --language to match the document language
• HTTP 429: Rate limit hit. Wait a few minutes and retry.