Token导航 LogoToken导航

Agent Skill · 研究检索

office-document-editor(办公室文档编辑器)

office-document-editor 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

office-document-editor 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 4,586。

总安装 31,236周安装 1,276GitHub Stars 1下载 10,004核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:office-document-editor(办公室文档编辑器)
来源仓库:https://github.com/tsukisama9292/office-document-editor
安装命令:
openclaw skills install office-document-editor
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install office-document-editor

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

专业 DOCX/PPTX 文档编辑,具有跟踪更改、格式保存、突出显示、删除线和 Git 版本控制。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install office-document-editor;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

office-document-editor 怎么安装?

在终端执行 openclaw skills install office-document-editor。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

office-document-editor 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

office-document-editor 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

office-document-editor 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

office-document-editor 用的人多吗?

公开数据是累计安装 31,236 次,近一周安装 1,276 次,下载 10,004 次,GitHub 1 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

office-document-editor 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
office-document-editor

办公室文档编辑器 · 本页

31,2361需要联网MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
office-document-editor
description
Professional DOCX/PPTX document editing with tracked changes, formatting preservation, highlights, strikethrough, and Git version control.
license
MIT
metadata
openclaw
requires
bins
install
kind
uv
path
.
bins
[docx_editor.py, pptx_editor.py, generate_diff.py]

Universal Office Document Editor

Professional document editing for any DOCX/PPTX file from any source.

Quick Reference

TaskApproach
Fetch file from uploadbash scripts/fetch_file.sh upload
Fetch file from URLbash scripts/fetch_file.sh https://example.com/file.docx
Fetch file from SFTPbash scripts/fetch_file.sh sftp://user@host:/path/file.docx
Edit DOCXuv run python scripts/docx_editor.py input.docx output.docx edits.json
Edit PPTXuv run python scripts/pptx_editor.py input.pptx output.pptx edits.json
Generate diffuv run python scripts/generate_diff.py old.docx new.docx diff.md
Interactive modebash scripts/interactive_edit.sh

File Sources

Uploaded Files (Chat Attachments)

# Get latest uploaded DOCX
bash scripts/fetch_file.sh upload output.docx

# Get latest uploaded PPTX
bash scripts/fetch_file.sh upload output.pptx

Location: ~/.openclaw/workspace/media/inbound/file_*.docx

Local Filesystem Paths

# Copy from local path
bash scripts/fetch_file.sh ~/Documents/report.docx output.docx

# Or direct path
bash scripts/fetch_file.sh /absolute/path/file.pptx output.pptx

Public URLs

# Download from URL
bash scripts/fetch_file.sh https://example.com/document.docx output.docx

SFTP/SSH Remote Files

# Fetch via SFTP
bash scripts/fetch_file.sh sftp://user@host:/path/file.docx output.docx

Creating Edit Rules

Create edits.json with your editing instructions:

{
  "description": "Edit description",
  "replacements": [
    {
      "search": "old text",
      "replace": "new text",
      "style": "highlight"
    }
  ],
  "additions": [
    {
      "after": "after this text",
      "text": "add this text",
      "style": "highlight"
    }
  ],
  "slides": [
    {
      "action": "rearrange",
      "order": [0, 2, 1, 3]
    }
  ]
}

Supported Styles

  • replace - Direct replacement
  • highlight - Yellow highlight
  • delete - Strikethrough
  • bold - Bold text
  • underline - Underline

Slide Actions (PPTX only)

  • rearrange - Change slide order
  • add - Add new slide
  • remove - Delete slide

Editing Documents

Edit DOCX

uv run python scripts/docx_editor.py input.docx output.docx edits.json

Features:

  • Paragraph text editing
  • Table cell editing
  • Format preservation
  • Multiple replacements
  • Text additions

Edit PPTX

uv run python scripts/pptx_editor.py input.pptx output.pptx edits.json

Features:

  • Slide text replacement
  • Slide rearrangement
  • Add/remove slides
  • Format preservation

Generate Diff Report

uv run python scripts/generate_diff.py input.docx output.docx diff-report.md

Output: Standard Unified Diff format in Markdown.


Complete Workflow

Step 1: Fetch File

# From upload
bash scripts/fetch_file.sh upload input.docx

# From URL
bash scripts/fetch_file.sh https://example.com/file.docx input.docx

# From local path
bash scripts/fetch_file.sh ~/Documents/file.docx input.docx

Step 2: Create Edit Rules

{
  "description": "IRB Review Response",
  "replacements": [
    {
      "search": "2026 年 2 月 28 日",
      "replace": "2026 年 8 月 31 日",
      "style": "highlight"
    }
  ]
}

Step 3: Execute Edit

uv run python scripts/docx_editor.py input.docx output.docx edits.json

Step 4: Generate Reports

# Unified Diff
uv run python scripts/generate_diff.py input.docx output.docx diff.md

# Convert to Markdown
uv run markitdown output.docx > output.md

Step 5: Version Control

git add *.docx *.md diff.md
git commit -m "Edit: Description of changes"

Interactive Mode

For guided editing:

bash scripts/interactive_edit.sh

This will prompt you through:

  1. File source selection
  2. Edit type selection
  3. Details collection
  4. Output location

Examples

Example 1: Text Replacement with Highlight

{
  "replacements": [
    {
      "search": "February 28, 2026",
      "replace": "August 31, 2026",
      "style": "highlight"
    }
  ]
}

Example 2: Add Text After Question

{
  "additions": [
    {
      "after": "What is the research topic?",
      "text": "[ANSWER] Data Structures and Algorithms",
      "style": "highlight"
    }
  ]
}

Example 3: Rearrange Slides

{
  "slides": [
    {
      "action": "rearrange",
      "order": [0, 2, 1, 3, 4]
    }
  ]
}

Notes

Format Preservation

  • ✅ Text, paragraphs, tables: Fully preserved
  • ✅ Highlights, strikethrough, bold: Supported
  • ⚠️ Complex styles (custom themes): May be lost
  • ❌ Images, charts: Manual handling required

Table Text Replacement

python-docx requires exact match (including spaces, punctuation, newlines) for table text.

Solutions:

  1. Use shorter search strings
  2. Use markitdown to preview table content first
  3. Use exact match in JSON

Git Best Practices

  • Use local Git repo (do not upload to GitHub)
  • Add sensitive files to .gitignore
  • Backup to secure location regularly

Dependencies

  • uv: Package management and virtual environment
  • python-docx: DOCX editing
  • python-pptx: PPTX editing
  • mammoth: DOCX to Markdown conversion
  • markitdown: Universal document conversion
  • curl: URL downloads
  • sftp: SFTP file transfers (optional)

Installation

cd ~/.openclaw/workspace/skills/office-document-editor
uv sync

Troubleshooting

"No replacements made"

Cause: Text doesn't match exactly

Solution:

# Preview content
uv run markitdown input.docx

# Use exact text from preview

"Virtual environment not found"

Solution:

cd ~/.openclaw/workspace/skills/office-document-editor
uv sync

"File not found"

Solutions:

  • Check file path is correct
  • Try uploading the file again
  • Verify URL is accessible
  • Check SFTP credentials

Scripts Reference

fetch_file.sh

Universal file fetcher for all source types.

bash scripts/fetch_file.sh <source> [output_filename]

Sources:

  • upload - Latest uploaded file
  • /path/to/file - Local path
  • https://... - Public URL
  • sftp://... - SFTP remote

docx_editor.py

Edit Word documents with formatting.

uv run python scripts/docx_editor.py input.docx output.docx edits.json

pptx_editor.py

Edit PowerPoint presentations.

uv run python scripts/pptx_editor.py input.pptx output.pptx edits.json

generate_diff.py

Generate Unified Diff reports.

uv run python scripts/generate_diff.py old.docx new.docx diff.md

interactive_edit.sh

Interactive guided editing.

bash scripts/interactive_edit.sh

workflow_complete.sh

Complete automated workflow.

bash scripts/workflow_complete.sh input.docx edits.json

平台分布

OpenClaw

90.45%
按下载量换算9,049

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

未展示

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills