Agent Skills
› vixues/LeAgent
› document-processor
document-processor
GitHub指导处理文档、提取内容及转换结构化信息。适用于解析PDF、Word或表格，执行文本/表格提取、字段抽取及格式互转，并包含质量验证与错误处理规范。
Trigger Scenarios
用户请求处理文档内容
需要解析或提取PDF/Word/Excel文件
要求将文档转换为其他格式
Install
npx skills add vixues/LeAgent --skill document-processor -g -y
SKILL.md
Frontmatter
{
"name": "document-processor",
"license": "Apache-2.0",
"metadata": {
"tags": [
"document",
"processing",
"parsing",
"extraction",
"conversion"
],
"version": "1.0.0",
"category": "document"
},
"description": "Guidance for processing documents, extracting content, and transforming structured information. Use when the user asks to process, parse, extract, or transform document content such as PDFs, Word files, or spreadsheets.",
"allowed-tools": "document_parser pdf_extractor docx_extractor excel_extractor table_extractor"
}
Document Processing
You are assisting with document processing tasks. Follow these guidelines.
Document Analysis Workflow
- Identify the document type: PDF, DOCX, XLSX, TXT, Markdown, HTML.
- Assess document structure: headers, sections, tables, images, metadata.
- Extract relevant content based on the user's request.
- Transform extracted content to the requested format.
- Validate accuracy, structure, and completeness.
Common Operations
Text Extraction
- Preserve document structure (headers, paragraphs, lists).
- Keep formatting where semantically meaningful (bold terms, emphasis).
- Extract metadata (author, creation date, document properties) when relevant.
Table Extraction
- Identify table boundaries and column headers.
- Preserve row/column relationships when exporting to CSV or JSON.
- Handle merged cells, nested tables, and multi-page tables carefully.
Information Extraction
- Extract specific fields (names, dates, amounts, addresses) with high precision.
- Use structured output (JSON, YAML) when returning multiple fields.
- Report confidence when extraction is ambiguous.
Format Conversion
- PDF ↔ Text/Markdown
- DOCX ↔ Markdown/HTML
- XLSX ↔ CSV/JSON
- HTML ↔ Markdown
Quality Guidelines
- Verify that extracted content matches the source.
- Preserve line breaks and paragraph structure unless asked to flatten.
- Flag OCR artifacts or illegible sections explicitly.
- For multi-page documents, maintain page references where useful.
Error Handling
- Document any parts that could not be processed (e.g., encrypted pages, images).
- Provide clear error messages for unsupported formats.
- Suggest alternative approaches when the primary method fails.
Version History
- a3dbf81 Current 2026-07-06 00:03
