MinerU-Ecosystem
opendatalab/MinerU-Ecosystem
The MinerU-Ecosystem skill integrates the MinerU open-source document parsing engine to convert complex PDFs, office documents, images, and web pages into clean Markdown or multi-format output. It supports two modes: a token-free flash extraction for quick tasks and a precision extraction mode with OCR, layout analysis, and batch processing.
192 14Apache-2.0Updated 2026-05-11
80
GreatOverview
This skill provides a seamless interface for AI agents and developers to interact with the MinerU document extraction API via the `mineru-open-api` CLI tool. It handles a wide variety of formats including PDF, Word, Excel, PowerPoint, images, and HTML, transforming unstructured files into clean, parseable text structures like Markdown, LaTeX, and JSON. It excels at preserving complex layouts, recovering tables, and parsing math formulas, making it ideal for retrieval-augmented generation (RAG) pipelines, research paper ingestion, and general document automation.
Capabilities
- ▸PDF, Office file, and image document conversion
- ▸Token-free quick flash extraction for lightweight tasks
- ▸Precision extraction with VLM-based layout analysis and OCR
- ▸Mathematical formula recognition into LaTeX
- ▸Table structure recovery into HTML
- ▸Web page crawling and extraction to Markdown
- ▸Multi-language support spanning over 80 languages
Best for
Converting academic research papers with complex tables and formulas into Markdown, Extracting clean text and layout from scanned PDFs and images using OCR, Batch processing hundreds of enterprise documents or web pages for RAG ingestion, Transforming Word, Excel, and PowerPoint documents into structured LLM-ready formats
Works with
Claude CodeCursorGitHub CopilotChatGPTGemini CLI
Evoa Score breakdown= Σ (score × weight)
80Task usefulness20%100 → +20.0
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%70 → +10.5
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%44 → +5.3
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%80 → +12.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%85 → +8.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%59 → +4.7
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%100 → +5.0
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total79.5 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Document contents are transmitted to the external MinerU API (mineru.net) for remote processing. Avoid sending sensitive, confidential, or proprietary data unless compliance allows external API routing.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.