科研 Skill

Word 文档处理

docx

读写编辑复杂 Word 文档

官方收录发布者 kdense-claude-scientific-skills安全审核通过v0.1.4更新于 2026-11-11

Skill 说明

完整 Word 文档读写编辑(目录 / 表 / 页眉页脚 / 图片 / 追踪修改 / 模板套用),并在遇到公式/OMML/MathType/LaTeX 场景时路由到 docx-equation-processor | 输入:.docx 文件 | 输出:改后的 .docx(保留公式结构 / 目录 / 表 / 页眉页脚 / 图片 / 追踪修改 / 模板套用)

SKILL.md

DOCX creation, editing, and analysis

Overview

A .docx file is a ZIP archive containing XML files.

Existing-document revision takes precedence

When the user asks to revise an existing Word document, the current saved DOCX is the source of truth for both content and formatting. Read it again each turn; chat history, earlier uploads, Markdown, JSON and LaTeX intermediates are not a substitute. If several files could be the current manuscript, locate the intended one before writing. If Word has unsaved edits, ask the user to save them; do not close Word, delete lock files or force replacement.

For a selected passage/section, change only that scope. Preserve other text, styles, title levels, numbering, TOC fields, bookmarks, references and package parts. Do not rebuild an existing manuscript with build_article_docx.py, Pandoc, or an old intermediate unless the user explicitly requests a full rebuild or reformat. New-document style defaults below do not apply to existing manuscripts.

For replacing a whole section body (including new inline/display equations), use scripts/office/replace_section.py inspect once, write a JSON content spec, then call replace_section.py replace. This bundled path snapshots, builds native OMML through the installed equation converter, validates, saves and registers undo in one operation. Do not write task-local OOXML builders or equivalent verifiers for supported inputs, repeatedly dump raw XML, or deliver with cp instead of commit. Read the linked workflow for the input schema and unsupported cases.

Before editing an existing file, read the scoped editing workflow. It provides edit_guard.py snapshots, current-document inventory, bounded edits, verification, guarded commit and exact restore. A schema-valid DOCX does not prove that unrelated content or formatting was preserved. Never claim “only section X changed” without comparing the original DOCX and the final candidate.

A request to discuss/propose wording does not itself authorize saving it when the user has requested chat-only suggestions. A request to undo means restore the preceding edit's snapshot, not rewrite the text again or renumber the manuscript.

Equation-aware Routing

Word equations are stored as OMML, usually in <m:oMath> or <m:oMathPara> nodes. For any task involving formulas, equations, inline math, display math, LaTeX, MathML, OMML, MathType, equation numbering, equation references, or academic papers with existing Word formula objects, use the docx-equation-processor skill together with this skill.

Before editing a formula-bearing document, inspect word/document.xml for <m:oMath> / <m:oMathPara>. If formulas are present:

  • Treat each OMML subtree as an atomic object unless the user explicitly asks to edit that formula.
  • Do not rewrite formula paragraphs as plain text.
  • Do not rely on python-docx for formula-heavy edits; it can corrupt OMML structures.
  • Prefer ZIP-level XML edits for preserving or inserting formulas.
  • Count OMML nodes before and after edits when formulas should be preserved.

If docx-equation-processor is not installed or available locally, stop before editing formulas or formula-bearing paragraphs and tell the user to install/add that skill. Continue only for clearly unrelated document regions where formulas cannot be affected.

Quick Reference

TaskApproach
Read/analyze contentpandoc or unpack for raw XML
Create new documentUse docx-js - see Creating New Documents below
Edit existing documentUnpack → edit XML → repack - see Editing Existing Documents below

Converting .doc to .docx

Legacy .doc files must be converted before editing:

python scripts/office/soffice.py --headless --convert-to docx document.doc

Reading Content

# Text extraction with tracked changes
pandoc --track-changes=all document.docx -o output.md

# Raw XML access
python scripts/office/unpack.py document.docx unpacked/ --merge-runs false

Converting to Images

python scripts/office/soffice.py --headless --convert-to pdf document.docx
pdftoppm -jpeg -r 150 document.pdf page

Accepting Tracked Changes

To produce a clean document with all tracked changes accepted (requires LibreOffice):

python scripts/accept_changes.py input.docx output.docx

Creating New Documents

Generate .docx files with JavaScript, then validate. Install: npm install -g docx

For a text-first article that will later receive native Word formulas, use scripts/office/build_article_docx.py with declarative JSON content. It creates a safe base DOCX without hand-written package XML; then run the equation skill's formula_inserter.py batch-convert for $...$ and $$...$$ markers. Do not copy or recreate DOC_TEMPLATE, STYLES_XML, RELS_XML, or other raw DOCX package templates in task-local scripts.

The builder explicitly styles Heading 1, Heading 2, and Heading 3 as black, bold, left-aligned Chinese headings; do not use Word's unmodified blue heading theme for article chapters or subchapters.

For this formula-article workflow, the required sequence is:

python -m json.tool content.json
python scripts/office/build_article_docx.py content.json article.docx
python <equation-skill>/scripts/formula_inserter.py batch-convert article.docx --backup
python scripts/office/validate.py article.docx

Stop and report the validation failure. Do not replace the last command with a task-local verify_docx() function and do not claim the file opens in Word until this full validator passes.

JSON Content Safety

Treat content.json as strict JSON, not as a prose file. Before building, run python -m json.tool content.json and fix every parse error. In a JSON string, write a literal ASCII double quote as \"; alternatively use “…” for Chinese quotation marks. Never run a global replacement of double quotes after writing the file, because JSON field delimiters are also double quotes. If JSON parsing fails, fix the content at the reported line and column before generating DOCX.

Setup

const { Document, Packer, Paragraph, TextRun, Table, TableRow, TableCell, ImageRun,
        Header, Footer, AlignmentType, PageOrientation, LevelFormat, ExternalHyperlink,
        InternalHyperlink, Bookmark, FootnoteReferenceRun, PositionalTab,
        PositionalTabAlignment, PositionalTabRelativeTo, PositionalTabLeader,
        TabStopType, TabStopPosition, Column, SectionType,
        TableOfContents, HeadingLevel, BorderStyle, WidthType, ShadingType,
        VerticalAlign, PageNumber, PageBreak } = require('docx');

const doc = new Document({ sections: [{ children: [/* content */] }] });
Packer.toBuffer(doc).then(buffer => fs.writeFileSync("doc.docx", buffer));

Validation

After creating the file, validate it. If validation fails, unpack, fix the XML, and repack.

python scripts/office/validate.py doc.docx

Page Size

// CRITICAL: docx-js defaults to A4, not US Letter
// Always set page size explicitly for consistent results
sections: [{
  properties: {
    page: {
      size: {
        width: 12240,   // 8.5 inches in DXA
        height: 15840   // 11 inches in DXA
      },
      margin: { top: 1440, right: 1440, bottom: 1440, left: 1440 } // 1 inch margins
    }
  },
  children: [/* content */]
}]

Common page sizes (DXA units, 1440 DXA = 1 inch):

PaperWidthHeightContent Width (1" margins)
US Letter12,24015,8409,360
A4 (default)11,90616,8389,026

Landscape orientation: docx-js swaps width/height internally, so pass portrait dimensions and let it handle the swap:

size: {
  width: 12240,   // Pass SHORT edge as width
  height: 15840,  // Pass LONG edge as height
  orientation: PageOrientation.LANDSCAPE  // docx-js swaps them in the XML
},
// Content width = 15840 - left margin - right margin (uses the long edge)

Styles (Override Built-in Headings)

Use Arial as the default font (universally supported). Keep titles black for readability.

const doc = new Document({
  styles: {
    default: { document: { run: { font: "Arial", size: 24 } } }, // 12pt default
    paragraphStyles: [
      // IMPORTANT: Use exact IDs to override built-in styles
      { id: "Heading1", name: "Heading 1", basedOn: "Normal", next: "Normal", quickFormat: true,
        run: { size: 32, bold: true, font: "Arial" },
        paragraph: { spacing: { before: 240, after: 240 }, outlineLevel: 0 } }, // outlineLevel required for TOC
      { id: "Heading2", name: "Heading 2", basedOn: "Normal", next: "Normal", quickFormat: true,
        run: { size: 28, bold: true, font: "Arial" },
        paragraph: { spacing: { before: 180, after: 180 }, outlineLevel: 1 } },
    ]
  },
  sections: [{
    children: [
      new Paragraph({ heading: HeadingLevel.HEADING_1, children: [new TextRun("Title")] }),
    ]
  }]
});

Lists (NEVER use unicode bullets)

// ❌ WRONG - never manually insert bullet characters
new Paragraph({ children: [new TextRun("• Item")] })  // BAD
new Paragraph({ children: [new TextRun("\u2022 Item")] })  // BAD

// ✅ CORRECT - use numbering config with LevelFormat.BULLET
const doc = new Document({
  numbering: {
    config: [
      { reference: "bullets",
        levels: [{ level: 0, format: LevelFormat.BULLET, text: "•", alignment: AlignmentType.LEFT,
          style: { paragraph: { indent: { left: 720, hanging: 360 } } } }] },
      { reference: "numbers",
        levels: [{ level: 0, format: LevelFormat.DECIMAL, text: "%1.", alignment: AlignmentType.LEFT,
          style: { paragraph: { indent: { left: 720, hanging: 360 } } } }] },
    ]
  },
  sections: [{
    children: [
      new Paragraph({ numbering: { reference: "bullets", level: 0 },
        children: [new TextRun("Bullet item")] }),
      new Paragraph({ numbering: { reference: "numbers", level: 0 },
        children: [new TextRun("Numbered item")] }),
    ]
  }]
});

// ⚠️ Each reference creates INDEPENDENT numbering
// Same reference = continues (1,2,3 then 4,5,6)
// Different reference = restarts (1,2,3 then 1,2,3)

Tables

CRITICAL: Tables need dual widths - set both columnWidths on the table AND width on each cell. Without both, tables render incorrectly on some platforms.

// CRITICAL: Always set table width for consistent rendering
// CRITICAL: Use ShadingType.CLEAR (not SOLID) to prevent black backgrounds
const border = { style: BorderStyle.SINGLE, size: 1, color: "CCCCCC" };
const borders = { top: border, bottom: border, left: border, right: border };

new Table({
  width: { size: 9360, type: WidthType.DXA }, // Always use DXA (percentages break in Google Docs)
  columnWidths: [4680, 4680], // Must sum to table width (DXA: 1440 = 1 inch)
  rows: [
    new TableRow({
      children: [
        new TableCell({
          borders,
          width: { size: 4680, type: WidthType.DXA }, // Also set on each cell
          shading: { fill: "D5E8F0", type: ShadingType.CLEAR }, // CLEAR not SOLID
          margins: { top: 80, bottom: 80, left: 120, right: 120 }, // Cell padding (internal, not added to width)
          children: [new Paragraph({ children: [new TextRun("Cell")] })]
        })
      ]
    })
  ]
})

Table width calculation:

Always use WidthType.DXA — WidthType.PERCENTAGE breaks in Google Docs.

// Table width = sum of columnWidths = content width
// US Letter with 1" margins: 12240 - 2880 = 9360 DXA
width: { size: 9360, type: WidthType.DXA },
columnWidths: [7000, 2360]  // Must sum to table width

Width rules:

  • Always use WidthType.DXA — never WidthType.PERCENTAGE (incompatible with Google Docs)
  • Table width must equal the sum of columnWidths
  • Cell width must match corresponding columnWidth
  • Cell margins are internal padding - they reduce content area, not add to cell width
  • For full-width tables: use content width (page width minus left and right margins)

Images

// CRITICAL: type parameter is REQUIRED
new Paragraph({
  children: [new ImageRun({
    type: "png", // Required: png, jpg, jpeg, gif, bmp, svg
    data: fs.readFileSync("image.png"),
    transformation: { width: 200, height: 150 },
    altText: { title: "Title", description: "Desc", name: "Name" } // All three required
  })]
})

Page Breaks

// CRITICAL: PageBreak must be inside a Paragraph
new Paragraph({ children: [new PageBreak()] })

// Or use pageBreakBefore
new Paragraph({ pageBreakBefore: true, children: [new TextRun("New page")] })

Hyperlinks

// External link
new Paragraph({
  children: [new ExternalHyperlink({
    children: [new TextRun({ text: "Click here", style: "Hyperlink" })],
    link: "https://example.com",
  })]
})

// Internal link (bookmark + reference)
// 1. Create bookmark at destination
new Paragraph({ heading: HeadingLevel.HEADING_1, children: [
  new Bookmark({ id: "chapter1", children: [new TextRun("Chapter 1")] }),
]})
// 2. Link to it
new Paragraph({ children: [new InternalHyperlink({
  children: [new TextRun({ text: "See Chapter 1", style: "Hyperlink" })],
  anchor: "chapter1",
})]})

Footnotes

const doc = new Document({
  footnotes: {
    1: { children: [new Paragraph("Source: Annual Report 2024")] },
    2: { children: [new Paragraph("See appendix for methodology")] },
  },
  sections: [{
    children: [new Paragraph({
      children: [
        new TextRun("Revenue grew 15%"),
        new FootnoteReferenceRun(1),
        new TextRun(" using adjusted metrics"),
        new FootnoteReferenceRun(2),
      ],
    })]
  }]
});

Tab Stops

// Right-align text on same line (e.g., date opposite a title)
new Paragraph({
  children: [
    new TextRun("Company Name"),
    new TextRun("\tJanuary 2025"),
  ],
  tabStops: [{ type: TabStopType.RIGHT, position: TabStopPosition.MAX }],
})

// Dot leader (e.g., TOC-style)
new Paragraph({
  children: [
    new TextRun("Introduction"),
    new TextRun({ children: [
      new PositionalTab({
        alignment: PositionalTabAlignment.RIGHT,
        relativeTo: PositionalTabRelativeTo.MARGIN,
        leader: PositionalTabLeader.DOT,
      }),
      "3",
    ]}),
  ],
})

Multi-Column Layouts

// Equal-width columns
sections: [{
  properties: {
    column: {
      count: 2,          // number of columns
      space: 720,        // gap between columns in DXA (720 = 0.5 inch)
      equalWidth: true,
      separate: true,    // vertical line between columns
    },
  },
  children: [/* content flows naturally across columns */]
}]

// Custom-width columns (equalWidth must be false)
sections: [{
  properties: {
    column: {
      equalWidth: false,
      children: [
        new Column({ width: 5400, space: 720 }),
        new Column({ width: 3240 }),
      ],
    },
  },
  children: [/* content */]
}]

Force a column break with a new section using type: SectionType.NEXT_COLUMN.

Table of Contents

// CRITICAL: Headings must use HeadingLevel ONLY - no custom styles
new TableOfContents("Table of Contents", { hyperlink: true, headingStyleRange: "1-3" })

Headers/Footers

sections: [{
  properties: {
    page: { margin: { top: 1440, right: 1440, bottom: 1440, left: 1440 } } // 1440 = 1 inch
  },
  headers: {
    default: new Header({ children: [new Paragraph({ children: [new TextRun("Header")] })] })
  },
  footers: {
    default: new Footer({ children: [new Paragraph({
      children: [new TextRun("Page "), new TextRun({ children: [PageNumber.CURRENT] })]
    })] })
  },
  children: [/* content */]
}]

Critical Rules for docx-js

  • Set page size explicitly - docx-js defaults to A4; use US Letter (12240 x 15840 DXA) for US documents
  • Landscape: pass portrait dimensions - docx-js swaps width/height internally; pass short edge as width, long edge as height, and set orientation: PageOrientation.LANDSCAPE
  • Never use \n - use separate Paragraph elements
  • Never use unicode bullets - use LevelFormat.BULLET with numbering config
  • PageBreak must be in Paragraph - standalone creates invalid XML
  • ImageRun requires type - always specify png/jpg/etc
  • Always set table width with DXA - never use WidthType.PERCENTAGE (breaks in Google Docs)
  • Tables need dual widths - columnWidths array AND cell width, both must match
  • Table width = sum of columnWidths - for DXA, ensure they add up exactly
  • Always add cell margins - use margins: { top: 80, bottom: 80, left: 120, right: 120 } for readable padding
  • Use ShadingType.CLEAR - never SOLID for table shading
  • Never use tables as dividers/rules - cells have minimum height and render as empty boxes (including in headers/footers); use border: { bottom: { style: BorderStyle.SINGLE, size: 6, color: "2E75B6", space: 1 } } on a Paragraph instead. For two-column footers, use tab stops (see Tab Stops section), not tables
  • TOC requires HeadingLevel only - no custom styles on heading paragraphs
  • Override built-in styles - use exact IDs: "Heading1", "Heading2", etc.
  • Include outlineLevel - required for TOC (0 for H1, 1 for H2, etc.)

Editing Existing Documents

First follow the scoped editing workflow above. The low-level steps below apply to a candidate copied from the snapshot, never directly to the only original. Use the guard to check the candidate before committing it.

Step 1: Unpack

python scripts/office/unpack.py document.docx unpacked/ --merge-runs false

Extracts XML, pretty-prints, merges adjacent runs, and converts smart quotes to XML entities (&#x201C; etc.) so they survive editing. Use --merge-runs false to skip run merging.

Step 2: Edit XML

Edit files in unpacked/word/. See XML Reference below for patterns.

Use "Claude" as the author for tracked changes and comments, unless the user explicitly requests use of a different name.

Use edit_guard.py replace-text for a unique match within one text node. For rich edits, use namespace-aware XML editing on a snapshot copy and preserve unselected nodes. Do not flatten paragraphs through .text assignment. Check the resulting candidate with the guard; whole-package unpack/repack tools may normalize protected parts and can therefore fail its preservation checks.

CRITICAL: Use smart quotes for new content. When adding text with apostrophes or quotes, use XML entities to produce smart quotes:

<!-- Use these entities for professional typography -->
<w:t>Here&#x2019;s a quote: &#x201C;Hello&#x201D;</w:t>
EntityCharacter
&#x2018;‘ (left single)
&#x2019;’ (right single / apostrophe)
&#x201C;“ (left double)
&#x201D;” (right double)

Adding comments: Use comment.py to handle boilerplate across multiple XML files (text must be pre-escaped XML):

python scripts/comment.py unpacked/ 0 "Comment text with &amp; and &#x2019;"
python scripts/comment.py unpacked/ 1 "Reply text" --parent 0  # reply to comment 0
python scripts/comment.py unpacked/ 0 "Text" --author "Custom Author"  # custom author name

Then add markers to document.xml (see Comments in XML Reference).

Step 3: Pack

python scripts/office/pack.py unpacked/ output.docx --original document.docx

Validates with auto-repair, condenses XML, and creates DOCX. Use --validate false to skip.

Auto-repair will fix:

  • durableId >= 0x7FFFFFFF (regenerates valid ID)
  • Missing xml:space="preserve" on <w:t> with whitespace

Auto-repair won't fix:

  • Malformed XML, invalid element nesting, missing relationships, schema violations

Common Pitfalls

  • Replace entire <w:r> elements: When adding tracked changes, replace the whole <w:r>...</w:r> block with <w:del>...<w:ins>... as siblings. Don't inject tracked change tags inside a run.
  • Preserve <w:rPr> formatting: Copy the original run's <w:rPr> block into your tracked change runs to maintain bold, font size, etc.

XML Reference

Schema Compliance

  • Element order in <w:pPr>: <w:pStyle>, <w:numPr>, <w:spacing>, <w:ind>, <w:jc>, <w:rPr> last
  • Whitespace: Add xml:space="preserve" to <w:t> with leading/trailing spaces
  • RSIDs: Must be 8-digit hex (e.g., 00AB1234)

Tracked Changes

Insertion:

<w:ins w:id="1" w:author="Claude" w:date="2025-01-01T00:00:00Z">
  <w:r><w:t>inserted text</w:t></w:r>
</w:ins>

Deletion:

<w:del w:id="2" w:author="Claude" w:date="2025-01-01T00:00:00Z">
  <w:r><w:delText>deleted text</w:delText></w:r>
</w:del>

Inside <w:del>: Use <w:delText> instead of <w:t>, and <w:delInstrText> instead of <w:instrText>.

Minimal edits - only mark what changes:

<!-- Change "30 days" to "60 days" -->
<w:r><w:t>The term is </w:t></w:r>
<w:del w:id="1" w:author="Claude" w:date="...">
  <w:r><w:delText>30</w:delText></w:r>
</w:del>
<w:ins w:id="2" w:author="Claude" w:date="...">
  <w:r><w:t>60</w:t></w:r>
</w:ins>
<w:r><w:t> days.</w:t></w:r>

Deleting entire paragraphs/list items - when removing ALL content from a paragraph, also mark the paragraph mark as deleted so it merges with the next paragraph. Add <w:del/> inside <w:pPr><w:rPr>:

<w:p>
  <w:pPr>
    <w:numPr>...</w:numPr>  <!-- list numbering if present -->
    <w:rPr>
      <w:del w:id="1" w:author="Claude" w:date="2025-01-01T00:00:00Z"/>
    </w:rPr>
  </w:pPr>
  <w:del w:id="2" w:author="Claude" w:date="2025-01-01T00:00:00Z">
    <w:r><w:delText>Entire paragraph content being deleted...</w:delText></w:r>
  </w:del>
</w:p>

Without the <w:del/> in <w:pPr><w:rPr>, accepting changes leaves an empty paragraph/list item.

Rejecting another author's insertion - nest deletion inside their insertion:

<w:ins w:author="Jane" w:id="5">
  <w:del w:author="Claude" w:id="10">
    <w:r><w:delText>their inserted text</w:delText></w:r>
  </w:del>
</w:ins>

Restoring another author's deletion - add insertion after (don't modify their deletion):

<w:del w:author="Jane" w:id="5">
  <w:r><w:delText>deleted text</w:delText></w:r>
</w:del>
<w:ins w:author="Claude" w:id="10">
  <w:r><w:t>deleted text</w:t></w:r>
</w:ins>

Comments

After running comment.py (see Step 2), add markers to document.xml. For replies, use --parent flag and nest markers inside the parent's.

CRITICAL: <w:commentRangeStart> and <w:commentRangeEnd> are siblings of <w:r>, never inside <w:r>.

<!-- Comment markers are direct children of w:p, never inside w:r -->
<w:commentRangeStart w:id="0"/>
<w:del w:id="1" w:author="Claude" w:date="2025-01-01T00:00:00Z">
  <w:r><w:delText>deleted</w:delText></w:r>
</w:del>
<w:r><w:t> more text</w:t></w:r>
<w:commentRangeEnd w:id="0"/>
<w:r><w:rPr><w:rStyle w:val="CommentReference"/></w:rPr><w:commentReference w:id="0"/></w:r>

<!-- Comment 0 with reply 1 nested inside -->
<w:commentRangeStart w:id="0"/>
  <w:commentRangeStart w:id="1"/>
  <w:r><w:t>text</w:t></w:r>
  <w:commentRangeEnd w:id="1"/>
<w:commentRangeEnd w:id="0"/>
<w:r><w:rPr><w:rStyle w:val="CommentReference"/></w:rPr><w:commentReference w:id="0"/></w:r>
<w:r><w:rPr><w:rStyle w:val="CommentReference"/></w:rPr><w:commentReference w:id="1"/></w:r>

Images

  1. Add image file to word/media/
  2. Add relationship to word/_rels/document.xml.rels:
<Relationship Id="rId5" Type=".../image" Target="media/image1.png"/>
  1. Add content type to [Content_Types].xml:
<Default Extension="png" ContentType="image/png"/>
  1. Reference in document.xml:
<w:drawing>
  <wp:inline>
    <wp:extent cx="914400" cy="914400"/>  <!-- EMUs: 914400 = 1 inch -->
    <a:graphic>
      <a:graphicData uri=".../picture">
        <pic:pic>
          <pic:blipFill><a:blip r:embed="rId5"/></pic:blipFill>
        </pic:pic>
      </a:graphicData>
    </a:graphic>
  </wp:inline>
</w:drawing>

Dependencies

  • pandoc: Text extraction
  • docx: npm install -g docx (new documents)
  • LibreOffice: PDF conversion (auto-configured for sandboxed environments via scripts/office/soffice.py)
  • Poppler: pdftoppm for images
  • Python validator dependencies: lxml and defusedxml

常见问题

Word 文档处理能做什么?

完整 Word 文档读写编辑(目录 / 表 / 页眉页脚 / 图片 / 追踪修改 / 模板套用),并在遇到公式/OMML/MathType/LaTeX 场景时路由到 docx-equation-processor | 输入:.docx 文件 | 输出:改后的 .docx(保留公式结构 / 目录 / 表 / 页眉页脚 / 图片 / 追踪修改 / 模板套用)。

如何安装Word 文档处理?

在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「Word 文档处理」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。

Word 文档处理需要哪些权限?

该科研 Skill声明需要:本地文件。安装前会再次列出,由你确认后才会生效。

Word 文档处理经过官方审核吗?

是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。