메뉴
Use when extracting PDFs, scanned documents, images, Office files, URLs, or web pages with MinerU, especially when OCR, table recognition, formula recognition, Markdown, HTML, LaTeX, DOCX, or JSON output is needed.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when producing, editing, or reviewing Traditional Chinese technical writing, including comments, documentation, explanations, and Chinese answers that must avoid translationese, casual phrasing, template language, and weak logic.
Audit NixOS impermanence state — find files still on the current filesystem device. Use when the user wants to check for untracked files, audit impermanence, or runs /impermanence-audit.
去除文字中的 AI 生成痕跡。適用於編輯或審閱文字，使其聽起來更自然、更像人類書寫。 基於維基百科的「AI 寫作特徵」綜合指南。偵測並修復以下模式：誇大的象徵意義、 宣傳性語言、以 -ing 結尾的膚淺分析、模糊的歸因、破折號過度使用、三段式法則、 AI 詞彙、否定式排比、過多的連接性短語。
Universal coding standards, best practices, and patterns. Use when developing in any language — triggers on TypeScript, JavaScript, React, Node.js, Python, Nix, ruff, pyright, pytest, uv, flake.nix, justfile, just, recipes, and general code quality topics.
Use when writing git commit messages, reviewing commits, or setting up commit conventions. Triggers on commit, git commit, commit message, changelog, semantic versioning.
A formal evaluation framework for Claude Code sessions, implementing eval-driven development (EDD) principles.
| name | mineru-pdf-extract |
| description | Use when extracting PDFs, scanned documents, images, Office files, URLs, or web pages with MinerU, especially when OCR, table recognition, formula recognition, Markdown, HTML, LaTeX, DOCX, or JSON output is needed. |
MinerU is a powerful document extraction tool. Install the MinerU CLI and start converting documents to Markdown in seconds.
npm install -g mineru-open-api
Or via Go (macOS/Linux):
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest
Verify: mineru-open-api version
MinerU flash-extract | MinerU extract | |
|---|---|---|
| Token required | No | Yes (mineru-open-api auth) |
| Speed | Fast | Normal |
| Table recognition | Yes | Yes |
| Formula recognition | Yes | Yes |
| OCR | Yes | Yes |
| Output formats | Markdown only | md, html, latex, docx, json |
| Batch mode | No | Yes |
| Model selection | pipeline | vlm, pipeline, MinerU-HTML |
| File size limit | 10 MB | Much higher |
| Page limit | 20 pages | Much higher |
mineru-open-api flash-extract <file> for quick Markdown conversionmineru-open-api auth, then use mineru-open-api extract for multi-format output, VLM model, and batch processingmineru-open-api crawl <url> to convert web content-o directoryOnly required for MinerU extract and crawl. Not needed for MinerU flash-extract.
mineru-open-api auth # Interactive token setup
export MINERU_TOKEN="your-token" # Or set via environment variable
Token resolution order: --token flag > MINERU_TOKEN env > ~/.mineru/config.yaml.
MinerU accepts a wide range of document formats:
| Format | MinerU flash-extract | MinerU extract |
|---|---|---|
PDF (.pdf) | Yes | Yes |
Images (.png, .jpg, .jpeg, .jp2, .webp, .gif, .bmp) | Yes | Yes |
Word (.docx) | Yes | Yes |
Word (.doc) | No | Yes |
PowerPoint (.pptx) | Yes | Yes |
PowerPoint (.ppt) | No | Yes |
Excel (.xlsx) | Yes | Yes |
Excel (.xls) | No | Yes |
HTML (.html) | No | Yes |
| URLs (remote files) | Yes | Yes |
MinerU crawl accepts any HTTP/HTTPS URL and extracts web page content to Markdown.
Fast, token-free MinerU document extraction. Outputs Markdown only. Limited to 10 MB / 20 pages per file.
mineru-open-api flash-extract report.pdf # MinerU Markdown to stdout
mineru-open-api flash-extract report.pdf -o ./out/ # Save to file
mineru-open-api flash-extract https://example.com/doc.pdf # URL mode
mineru-open-api flash-extract report.pdf --language en # Specify language
mineru-open-api flash-extract report.pdf --pages 1-10 # Page range
Flags: --output/-o (output path), --language (default ch), --pages (page range), --timeout (default 900s).
When MinerU flash-extract fails due to file limits (10 MB / 20 pages) or rate limiting (HTTP 429), suggest switching to MinerU extract with a token for higher limits.
Convert documents to Markdown or other formats with MinerU's full capabilities: VLM-based layout analysis, multiple output formats, and batch mode.
mineru-open-api extract report.pdf # MinerU Markdown to stdout
mineru-open-api extract report.pdf -f html # MinerU HTML output
mineru-open-api extract report.pdf -o ./out/ -f md,docx # Multiple formats
mineru-open-api extract *.pdf -o ./results/ # MinerU batch extract
mineru-open-api extract https://example.com/doc.pdf # Extract from URL
Flags: --output/-o, --format/-f (md/json/html/latex/docx), --model (vlm/pipeline/html), --ocr, --formula, --table, --language, --pages, --timeout, --list, --concurrency.
MinerU vlm | MinerU pipeline | |
|---|---|---|
| Parsing accuracy | Higher — better at complex layouts | Standard |
| Hallucination risk | May produce hallucinated text in rare cases | No hallucination |
Use MinerU --model vlm for complex formatting. Use MinerU --model pipeline for no-hallucination reliability.
mineru-open-api crawl https://example.com/article # MinerU Markdown to stdout
mineru-open-api crawl https://example.com/article -o ./out/ # Save to file
mineru-open-api crawl url1 url2 -o ./pages/ # MinerU batch crawl
Flags: --output/-o, --format/-f (md/json/html), --timeout, --list, --concurrency.
mineru-open-api auth # Interactive MinerU token setup
mineru-open-api auth --verify # Verify current token
mineru-open-api auth --show # Show token source
Without -o: MinerU result → stdout, progress → stderr. With -o: saved to file/directory. Batch mode and binary formats (docx) require -o.
mineru-open-api extract "report 01.pdf"flash-extract when: no token configured, simple extraction, file under 10 MB / 20 pagesextract when: user needs non-Markdown formats, VLM model, batch processing, or file exceeds flash-extract limits-o, generate output directory: ~/MinerU-Skill/<name>_<hash>/ where <hash> = first 6 chars of MD5 of the source pathflash-extract success, append a brief hint about MinerU extract upgrade path (once per session)npm install -g mineru-open-apiFor full CLI reference and troubleshooting, see: https://github.com/opendatalab/MinerU-Ecosystem/tree/main/cli
--language valuesThe --language flag accepts the following values (default: ch). Used by both MinerU flash-extract and extract.
| 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 |
| 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 |