agentleFS
156554395156554395/claude-code-skills/skills/dingtalk-shanji/SKILL.md

dingtalk-shanji

Skill1 starsChanged 10 days agoMITView on GitHub

从钉钉闪记提取听记数据,包括列表、转写文本、摘要、待办等。当用户提到"钉钉闪记"、"听记"、"会议录音"、"转写文本"、"shanji"、"dws minutes"时触发此技能。

  • Pipes a download into a shell
  • Installs packages

The file

Files
SKILL.md

钉钉闪记数据提取技能

使用官方 dws CLI 工具从钉钉闪记提取数据。

前置条件检查

在执行任何操作前,先检查 dws 是否已安装:

command -v dws && dws --version || echo "dws 未安装"

安装 dws

如果 dws 未安装,按以下顺序尝试安装:

方式1:npm 安装(优先)

npm install -g dingtalk-workspace-cli

方式2:sh 脚本安装(npm 失败时)

macOS / Linux:

curl -fsSL https://raw.githubusercontent.com/DingTalk-Real-AI/dingtalk-workspace-cli/main/scripts/install.sh | sh

Windows (PowerShell):

irm https://raw.githubusercontent.com/DingTalk-Real-AI/dingtalk-workspace-cli/main/scripts/install.ps1 | iex

安装后验证

dws --version
dws minutes --help

首次使用认证

首次使用需要登录认证:

dws login

按照提示完成 OAuth 设备流认证。


命令参考

列出听记

# 列出所有听记
dws minutes list all

# 列出我创建的听记
dws minutes list mine --max 20

# 列出分享给我的听记
dws minutes list shared

# 按关键词搜索
dws minutes list all --keyword "医美"

# 按时间范围筛选
dws minutes list all --start-time "2025-05-01" --end-time "2025-05-31"

# 输出JSON格式
dws minutes list all -f json

获取听记详情

# 获取基本信息(标题、时长、参与者)
dws minutes get info --id <taskUuid>

# 获取转写文本
dws minutes get transcription --id <taskUuid>

# 获取AI摘要
dws minutes get summary --id <taskUuid>

# 获取待办事项
dws minutes get todos --id <taskUuid>

# 获取关键词
dws minutes get keywords --id <taskUuid>

# 批量获取多个听记详情
dws minutes get batch --id <id1>,<id2>,<id3>

其他操作

# 更新标题
dws minutes update title --id <taskUuid> --title "新标题"

# 更新摘要
dws minutes update summary --id <taskUuid> --summary "新摘要"

# 替换转写文本中的错误
dws minutes replace-text --id <taskUuid> --find "错误文本" --replace "正确文本"

# 生成思维导图
dws minutes mind-graph create --id <taskUuid>

# 上传录音文件创建听记
dws minutes upload create --file "recording.mp3"

典型工作流程

1. 列出最近的听记

# 列出我创建的听记(JSON格式)
dws minutes list mine -f json

2. 获取特定听记的转写文本

# 先获取听记的taskUuid
dws minutes list mine --max 1 -f json | jq -r '.result.minutesDetails[0].taskUuid'

# 获取转写文本(使用 --id 参数)
dws minutes get transcription --id <taskUuid>

# 示例:
dws minutes get transcription --id 76327569643331323336383832345f3237323535323932305f32

3. 获取完整听记数据

# 获取详情(使用 --id 参数)
dws minutes get info --id <taskUuid> -f json

# 获取转写
dws minutes get transcription --id <taskUuid>

# 获取摘要
dws minutes get summary --id <taskUuid>

# 获取待办
dws minutes get todos --id <taskUuid>

# 示例:
TASK_UUID="76327569643331323336383832345f3237323535323932305f32"
dws minutes get info --id $TASK_UUID -f json
dws minutes get transcription --id $TASK_UUID
dws minutes get summary --id $TASK_UUID

输出格式

使用 -f json 参数获取JSON格式输出,便于程序处理:

dws minutes list all -f json

JSON输出示例:

[
  {
    "id": "76327569643331323336383832345f3237323535323932305f32",
    "title": "05-29 医美行业AI销售智能解决方案",
    "creator": "张三",
    "createTime": "2025-05-29T10:00:00Z",
    "duration": 7470,
    "participantCount": 5
  }
]

常用参数

参数说明
-f jsonJSON格式输出
-f table表格格式输出(默认)
-f raw原始格式输出
--help查看帮助
--verbose详细日志

注意事项

  1. 首次使用需登录:执行 dws login 完成认证
  2. 企业授权:需要企业管理员授权才能访问数据
  3. 权限控制:只能访问自己有权限的听记
  4. 命令行工具:比浏览器方案更轻量、更高效

与浏览器方案对比

特性dws CLI浏览器方案
安装简单(npm/sh)复杂(Playwright)
速度快慢
资源消耗低高
维护官方维护需自己维护
认证OAuth设备流Cookie注入
稳定性高低(页面变化会失效)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.