Convert a Markdown file to Word (.docx) with formatting.

Applies Chinese government document formatting (公文格式规范) by default:

• Headings: 黑体 (H1 三号16pt, H2 小三15pt, H3 四号14pt) bold, left-aligned

• Body: 仿宋_GB2312 四号14pt, justified, 2-char first-line indent

• Tables: 仿宋_GB2312 五号10.5pt, center-aligned

• Line spacing: fixed 28pt for body/headings, single for tables

Args: input_path: Absolute path to the input Markdown file. output_path: Output .docx path. Defaults to /.docx. format_spec: Path to a format description markdown file (like 格式要求.md). Overrides the default format. The file defines fonts, sizes, spacing, and alignment per Word style (H1/H2/H3/正文/表格). reference_docx: Path to a .docx template whose styles overlay on top of the format spec. Useful for matching an existing document's styles. extract_media: Directory to extract media files to. skip_format: If True, bypass ALL formatting (pure pandoc output). no_cache_template: If True, force regeneration of the cached reference template (needed when format spec changes). auto_suggest: If True, automatically generate a modification suggestions report (xx-修改建议.md) after conversion. The report covers heading hierarchy, required sections, format issues, content problems, list continuity, and Chinese punctuation.

Returns: Summary string with input path, output path, file size, and optionally the modification suggestions report path and issue count.

Convert Markdown tables to an Excel (.xlsx) file.

Extracts every HTML and Markdown pipe table from the document (in document order) and writes each to its own worksheet. Preserves colspan/rowspan merged cells, inline bold, and text-align alignment.

Styling:

• Font: 微软雅黑 (11pt body), thin borders on all cells

• Header cells (HTML or the first row of a pipe table): bold + light gray fill

• All cells: vertical center, wrap text

• Column widths and row heights estimated from content

Args: input_path: Absolute path to the input Markdown file. output_path: Output .xlsx path. Defaults to /.xlsx. font_name: Optional font name override (default 微软雅黑). body_size: Optional body font size override (default 11).

Returns: Summary string with input path, output path, file size, and sheet count.

Analyze a Markdown document and generate modification suggestions.

Performs semantic analysis across six categories:

1. Heading hierarchy — skipped levels, missing/multiple H1, long titles

2. Required 公文 sections — expected elements in Chinese government docs

3. Format issues — broken image references, HTML table problems

4. Content issues — empty sections, placeholder text, duplicates, long paragraphs

5. Numbered list continuity — gaps and restarts in ordered lists

6. Chinese punctuation — half-width marks, missing sentence endings

Generates a structured report at /-修改建议.md with findings organized by category, each showing line numbers, severity, and specific suggestions.

Args: input_path: Absolute path to the input Markdown file.

Returns: Summary string with input path, suggestions file path, and issue count.