Iván

Word

办公效率v1.0.0
作者:Iván更新于 2026-05-11word@clawhub_ivangdavila/word
文档处理流程自动化

据 AlphaMoat 统计,截至 2026-10,Word 累计下载 58,342 次、获 2 个星标,按累计下载量在本次参与排名的 10,914 个 AI 技能中排名第 418 位,在「办公效率」分类(909 个)中排名第 61 位。

列表默认按累计下载量排序,也可按星标排序;详情页排名按累计下载量计算。

累计下载
5.8万
星标
2
全站下载量排名
#418
全站前 4% · 「办公效率」前 7%
平台累计下载星标评论
ClawHub ↗4,0421-
SkillHub ↗5.8万2—

各平台的计数口径不同,统计时间不一致。

这个技能是做什么的

处理应用附着、当前文档状态、随选区编辑、批注、修订、导出与正常退出,面向的是活的 Word 应用而不是 docx 文件格式。只在 darwin 上运行,需要本机装有 Word;破坏性操作前要先确认。

资料发布于 2026-10-27

可以用来做什么

  • 在打开的文档里按选区改写并加批注
  • 跟踪修订后导出当前文档

什么时候用

  • 任务依赖 Word 当前打开状态时
  • 需要改批注、修订或选区时

示例提示词

以下是根据技能文档生成的示例,不代表实际运行结果。

把当前选中的段落改得更简洁并加一条批注
打开修订,把我改的地方标出来再导出

月度数据趋势

累计下载5.8万
2.0万4.1万6.1万2026-09 · 累计下载 2.3万2026-10 · 累计下载 5.8万26-0926-10
星标2
1232026-09 · 星标 22026-10 · 星标 226-0926-10
月份累计下载环比星标
2026-105.8万—2
2026-092.3万—2

SKILL.md 原文

以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。

5.9 KB · ClawHub v1.0.0
---
name: Word
slug: word
version: 1.0.0
homepage: https://clawic.com/skills/word
description: Control Word app sessions, documents, selections, comments, export, and review state with osascript workflows.
changelog: Initial release with live Word automation patterns for sessions, selections, review actions, export, and recovery.
metadata: {"clawdbot":{"emoji":"📝","requires":{"bins":["osascript"]},"os":["darwin"],"configPaths":["~/word/"]}}
---
展开全部(共 119 行)
## When to Use

User needs Microsoft Word controlled as a live application, not treated as a `.docx` file format.
Agent handles app attach, active document state, selection-aware edits, comments, track changes, export, and clean shutdown through the official `osascript` CLI.
If the main artifact is offline DOCX creation or structural file editing, use `word-docx` instead.

## Architecture

Memory lives in `~/word/`. If `~/word/` does not exist, run `setup.md`. See `memory-template.md` for structure.

```text
~/word/
├── memory.md             # Environment facts, safe defaults, and last working control path
├── incidents.md          # Reusable failures and proven recovery steps
└── document-notes.md     # Non-sensitive notes about trusted documents, views, and export targets
```

## Quick Reference

Load only the smallest file that matches the current Word task and risk level.

| Topic | File |
|-------|------|
| Setup guide | `setup.md` |
| Memory template | `memory-template.md` |
| Interface selection | `execution-matrix.md` |
| Live control patterns | `live-control-patterns.md` |
| Destructive action guardrails | `safety-checklist.md` |
| Debug and recovery | `troubleshooting.md` |

## Requirements

- Microsoft Word installed locally.
- macOS with `osascript` available.
- Explicit confirmation before destructive document actions.

## Core Rules

### 1. Choose the app-control path by document state
- Use `osascript` for live Word document control through the app's scripting dictionary.
- Keep automation inside the live Word session instead of falling back to file-only DOCX tooling.
- Do not switch to offline document libraries when the requested job depends on the current live Word app state.

### 2. Identify the exact document and view before acting
- Confirm whether the target is the active document, a named open document, or a path to open now.
- Read the current view, selection, and review mode before making edits tied to cursor position or markup state.
- Never assume the frontmost Word window is the intended document.

### 3. Read before write, then verify the final state
- Pre-read document name, current selection, target paragraph, comment count, or export target before mutation.
- After edits, comments, accept/reject actions, or exports, re-read the affected state and report what changed.
- If Word does not reach the requested state, stop and diagnose instead of layering more edits.

### 4. Treat selection-driven actions as high-risk
- Selection-based commands can land in the wrong paragraph, story range, header, or comment balloon.
- When possible, anchor the action to a specific document object instead of only the current insertion point.
- If the selection context is ambiguous, clarify first.

### 5. Separate reversible review actions from destructive cleanup
- Adding comments, changing view, and exporting are usually reversible.
- Accept all changes, reject all changes, remove comments, close without save, and overwrite exports require explicit confirmation.
- If review state matters, preserve track changes and display settings unless the user explicitly asks to change them.

### 6. Keep provenance explicit
- State whether the target was already open or opened just for this task.
- Report what document was changed, which review mode was active, and where exports were written.
- Preserve user-owned open documents that were outside the task scope.

### 7. Recover cleanly and avoid orphaned app sessions
- If you opened Word just for this task, keep ownership clear and close only what you created.
- If you attached to an existing session, do not close unrelated documents or quit Word without explicit approval.
- On failure, record the exact blocker: protected document, modal dialog, compatibility mode, track changes mismatch, or missing permissions.

## Word Traps

- Treating a live document like a static `.docx` file -> review state, comments, fields, and view context drift apart.
- Writing relative to the current cursor without verifying selection -> text lands in the wrong story range.
- Accepting or rejecting changes globally when only one section was intended -> irreversible editorial loss.
- Exporting before fields, references, or TOC are updated -> stale output delivered as final.
- Closing an attached user session after automation -> unrelated writing work is interrupted.
- Ignoring protected view or tracked-change mode -> edits silently fail or create the wrong markup history.

## Security & Privacy

**Data that stays local:**
- Document paths, environment notes, and reusable fixes in `~/word/`.
- Document contents accessed through local Word automation.

**Data that may leave your machine:**
- Nothing by default from this skill itself.
- A document's own links, add-ins, macros, or cloud-backed autosave behavior may contact external systems.

**This skill does NOT:**
- Use Microsoft Graph, cloud document APIs, or OAuth flows.
- Disable review warnings silently.
- Accept destructive document-wide changes without explicit confirmation.
- Bypass Word protection prompts.

## Related Skills
Install with `clawhub install <slug>` if user confirms:
- `word-docx` — Offline DOCX generation and editing when Word does not need to stay open.
- `office` — Broader Office task routing across documents, spreadsheets, and presentations.
- `applescript` — macOS app automation patterns when Word dictionary work needs deeper script design.

## Feedback

- If useful: `clawhub star word`
- Stay updated: `clawhub sync`

「办公效率」分类下的热门技能

腾讯文档 TENCENT DOCS办公效率

通过 MCP 在腾讯文档里新建、编辑与管理在线文档的完整操作手册。

↓ 218.4万★ 327u_b0de8114
WPS Office 全家桶办公效率

WPS Office 全家桶 - 四引擎(WPS/MS Office/LibreOffice/纯Python)智能识别用户已安装软件,纯Python模式支持排序/筛选/图表/公式/统计,含文档模板(代码生成)、最佳实践案例、故障排除大章(20+避坑+15 FAQ+15错误ID 统一索引)、自动重试、硬件自适应、环境自检、Skill更新提醒;v5.1新增:kingdoc云端桥接(白名单探测+配置预检+subprocess上传+差异检查)、条件格式/数据验证跨引擎IO(JSON中间格式保真往返)、会议纪要三段式要素化(待办清单+决策记录+风险异议)+说话人标注(MFCC聚类);v5.2新增:公文一键排版(GB/T 9704 规则库约束+结构识别套版+红头预留位+联合行文)、批量水印与敏感信息打码(身份证/手机号/银行卡/邮箱双轨识别+黑色矩形覆盖+打码清单)、跨文档知识检索与问答(本地TF-IDF零依赖+跳转+可选zwjh记忆桥接);删除:与contract-review重复的轻量合同审查模块,改为文档互链引导;v5.2.5修复:MS Office引擎下Excel/PPT创建必然失败(错用Word COM对象),新增get_ms_excel/get_ms_ppt及三槽位统一释放release_ms,MS Office路径透传filepath参数;v5.3.5修复:SKILL.md frontmatter 修复 tags 块序列误混入联系方式行导致标准 YAML 解析失败;v5.4.0新增:留存型功能——定时任务与报告中心(schedule_register 升级为三平台统一调度层 schtasks/cron/launchd,错过策略 skip/run_once,注册表 JSON 可导出导入;新建 report_center.py 报告中心,templates/reports/*.json 参数化模板 + ECharts 单文件 HTML 输出(图表内联、无服务端、双击即开);report_generator 升级支持 --format html;wps.py CLI 统一埋点 SQLite,自动供 report_center 生成周度使用摘要附在报告末尾;watch.py 职责收窄为纯事件采集);v5.3.0新增:统一CLI入口 wps(registry.json注册表分发,office --app/--action 与 convert 子命令、--list 一屏列出全部命令,薄路由层不改脚本内部逻辑)、全命令 --json 机器可读输出(固定 ok/error_id/elapsed/data 四字段,对齐 E001-E015,wps_error.py 新增 emit_json 统一出口)、_worker 启动优化(wps_pure 改惰性加载,pywin32/python-docx/openpyxl 经核查已惰性导入,ENGINE_CACHE 进程级单例复用,COM 释放统一走 release_ms 三槽位)、转换三入口合并为 convert(format_converter/md_converter/wps_docx_to_ppt 内部按目标格式路由,旧脚本保留为兼容别名并提示新命令,v6.0.0 移除)

↓ 76.7万★ 159user_1a470ba8
ppt-generator-skill办公效率

按主题与风格自动生成 PPT 文件的技能。

↓ 59.3万★ 346user_3b34947d
秘书材料星公文写作-妙笔skill办公效率

体制内资深办公室主任+管理学博士,自学编程开发的智能公文写作Skill,让所有办公室同仁少掉头发、少加无用的班,材料一稿过关,省下的时间留给自己、享受生活!————————我们能给你带来的核心价值:1、颠覆传统写作:逻辑建模38类公文全链条,特有模板化引导问答模式,分分钟省心生成高质量大稿。--------2、替你“向上管理”:独有审稿人画像机制,文稿一键结构性修改,精准匹配审稿人画像,过稿率提升至少10倍!----------3、‌杜绝AI编造:缺失的数字、文号、人名、日期一律用[待补]标注,绝不杜撰,守住公文底线。-----------4、‌算法格式托底:数十万全量智控知识库+6500行前沿核心控制代码,格式精准对齐GB/T 9704,出稿零失误。——————————————————本skill历史版本开放了5%知识库的免费试用版,下载即可使用,但需注意:知识库有著作权,仅用于个人使用,不可用于其他任何目的。有兴趣的可以试试。——————————————————————单次付费版skill已发布,2元一次使用全量知识库。具体在发布者“熵衍信息”主页skill里。

↓ 57.8万★ 46u_70fc650d
WPS Office 全家桶办公效率

WPS Office 全家桶 - 四引擎(WPS/MS Office/LibreOffice/纯Python)智能识别用户已安装软件,纯Python模式支持排序/筛选/图表/公式/统计,含文档模板(代码生成)、最佳实践案例、故障排除大章(20+避坑+15 FAQ+15错误ID 统一索引)、自动重试、硬件自适应、环境自检、Skill更新提醒;v5.0新增:定时任务注册管理(schtasks/crontab)、目录轮询监听(YAML规则+大文件分片)、使用统计与稳定性中心(SQLite埋点+引擎健康+引擎偏好)、COM三步自愈(regsvr32→修复安装→手动指引)、对话式数据查询(NL2SQL式意图解析+查询计划+连续追问)、multi-agent编排引擎桥接(白名单探测+流水线模板注册)

↓ 50.8万★ 4user_814dbe54
WPS全家桶·办公管家.Skill办公效率

当用户要处理 Word/Excel/PPT、做文档模板与排版、批量合并图表、公文一键套红头、会议纪要要素化、或跨引擎办公自动化时,WPS全家桶·办公管家.Skill 立即出动。 四引擎智能识别已装软件(WPS/MS Office/LibreOffice/纯Python),纯Python模式支持排序/筛选/图表/公式/统计;含文档模板代码生成、20+避坑+15 FAQ+15错误ID统一索引、自动重试、硬件自适应、环境自检。 当用户提到批量水印、敏感信息打码(身份证/手机号/银行卡/邮箱)、跨文档检索问答等信号时,主动亮剑。

↓ 43.0万★ 2user_185644ed
腾讯文档在线协作自动化办公效率

通过 Tencent Docs Open API 以 curl + jq 创建、读取、列出、搜索和管理腾讯文档的自动化工作流,覆盖在线文档、在线表格、幻灯片、思维导图、流程图、智能表格与收集表七种类型,支持读取元数据与单元格区域、上传图片、创建副本,并对重命名/移动/删除等写操作强制先经用户确认。Use when the user 提到腾讯文档 / Tencent Docs / docs.qq.com、粘贴 docs.qq.com 链接,或想在其腾讯文档空间中创建、读取、整理文档时使用。Triggers include 腾讯文档、在线文档、在线表格、思维导图、流程图、智能表格、收集表。如需文案写作完整工作流套件,淘宝搜索「AI灵匣」店铺获取完整版。

↓ 42.8万★ -u_1ea983ac
kdocs skill办公效率

通过 kdocs-cli 操作金山文档云文档的官方技能。

↓ 42.4万★ 128user_5ea84866

Iván 的其他技能

数据月份:2026-10 · 下载/星标数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。