メニュー
Document parsing skill for extracting content from PDFs and other academic documents using MinerU and local parsers
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/QiZishi/PaperAgent --skill parse-skillコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Citation network and reference management skill for tracking citations, formatting references, and building citation graphs
Academic literature search skill for finding papers from arXiv, Semantic Scholar, and HuggingFace
Academic writing skill for generating summaries, reports, literature reviews, and other research documents
SKILL.md を表示中
SOC 職業分類に基づく
| name | parse_skill |
| description | Document parsing skill for extracting content from PDFs and other academic documents using MinerU and local parsers |
| version | 1.0.0 |
| author | PaperAgent Team |
This skill enables you to parse and extract content from academic documents, particularly PDFs. Use this skill when you need to extract text, figures, tables, and structured content from research papers.
You have access to the following parsing tools (registered in the Toolkit):
parse_pdf_with_mineruParse a PDF document using MinerU API for high-quality extraction.
Parameters:
pdf_url (str, required): URL to the PDF fileextract_figures (bool, optional): Whether to extract figures (default: True)model_version (str, optional): "vlm" (vision-language model) or "basic"Returns: Parsed content including:
Example:
parse_pdf_with_mineru(pdf_url="https://arxiv.org/pdf/2301.12345.pdf", extract_figures=True, model_version="vlm")
Note: MinerU API requires authentication. Ensure the API token is configured.
parse_pdf_localParse a PDF document locally using pypdf (faster but less accurate).
Parameters:
file_path (str, required): Local path to the PDF fileReturns: Extracted text content with page markers and metadata.
Example:
parse_pdf_local(file_path="/path/to/paper.pdf")
extract_text_from_fileExtract text from various file types.
Parameters:
file_path (str, required): Path to the file (supports txt, md, pdf, docx)Returns: Plain text content.
Example:
extract_text_from_file(file_path="/path/to/document.docx")
extract_sectionsExtract structured sections from a parsed document.
Parameters:
content (str, required): Document content in markdown formatsection_patterns (list[str], optional): Custom section heading patternsReturns: List of sections with:
Example:
extract_sections(content=markdown_content, section_patterns=["Abstract", "Introduction", "Methods", "Results", "Conclusion"])
extract_figuresExtract figure information from parsed content.
Parameters:
content (str, required): Document contentinclude_images (bool, optional): Whether to include image data (default: False)Returns: List of figures with captions and positions.
Example:
extract_figures(content=parsed_content, include_images=True)
extract_referencesExtract and parse reference list from document.
Parameters:
content (str, required): Document contentformat (str, optional): Expected citation format for parsing hintsReturns: List of parsed references with structured fields.
Example:
extract_references(content=paper_content)
https://arxiv.org/pdf/xxxx.xxxxx.pdf)parse_pdf_with_mineru with model_version="vlm" for best resultsmodel_version="basic"parse_pdf_local for quick extractionextract_figures=True with MinerUChoose the right parser:
Handle large documents:
Validate extraction:
Process structured content:
extract_sections to navigate large documentsextract_references for citation analysisParsed content is returned in markdown format:
#, ##, ### or [Figure N: caption]