Wecomcli Sheet logo

Wecomcli Sheet

OrganizationPopular
Pinvou
wecomcli-sheet

何时用:仅当用户明确指向企业微信『在线表格』或提供 doc.weixin.qq.com/sheet/ 链接时使用;泛指做表格默认先按消歧确认,智能表格内容操作走 wecomcli-smartsheet,本地表格默认走本地工具。在线表格:新建、导入 CSV/Excel、读取信息与数据、修改内容、追加行、子表管理;文档公共操作走 wecomcli-doc-manage。

Overview

PublisherPinvou
Repositorypinvou-agent
Skill namewecomcli-sheet
Stars
2K
Forks
281
Bundled files
5
LicenseMIT
Links
Skill sourceRepositoryHomepage
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Pinvou on GitHub. Read the source before you install it.

Installation

Install the Wecomcli Sheet AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Pinvou/pinvou-agent.git /tmp/pinvou-agent
mkdir -p .claude/skills
cp -r /tmp/pinvou-agent/pinvou3-app/src-tauri/resources/common/bundle/wecom-skills/wecomcli-sheet .claude/skills/wecomcli-sheet
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wecomcli Sheet in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Wecomcli Sheet on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Wecomcli Sheet is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

企业微信在线表格管理

执行任何 wecom-cli 命令前，必须先读取并完成 wecomcli-shared 技能的公共前置检查。

资源型 skill，负责在线表格（sheet）的新建、导入与内容读写及子表管理。

适用范围

适用

  • 新建 / 导入企微在线表格
  • 读取 / 修改 / 追加在线表格内容
  • 添加 / 删除在线表格子表

不适用

  • 搜索文档 / 修改文档权限 / 重命名 / 加成员 → 改用 wecomcli-doc-manage
  • 用户给的链接是 https://doc.weixin.qq.com/smartsheet/... → 改用 wecomcli-smartsheet
  • 若遇到的 docid 以 s3 开头（形如 s3_xxxx）→ 改用 wecomcli-smartsheet
  • 用户泛指「做表格」、未明确在线表格还是智能表格 → 先用简洁自然语言消歧确认，不得默认本技能

接口路由表

硬规则：第二列是 references/xxx.md 链接的, 命中这一行后先用 read 读取对应 references 文件，再构造命令。

用户意图参考位置
新建在线表格见下方「新建在线表格」
导入本地 CSV / Excel 文件为企微在线表格见下方「导入在线表格」
读取在线表格基础信息与子表列表见下方「读取在线表格」
读取在线表格子表数据references/sheet-ranges-get.md
修改在线表格指定区域内容references/sheet-contents-update.md
在线表格末尾追加一行数据references/sheet-rows-append.md
添加在线表格子工作表references/sheet-subsheets-add.md
删除在线表格子工作表references/sheet-subsheets-delete.md

写操作确认

  • 删除子表（sheet-subsheets-delete）与 contents update 覆写前，必须向用户复述影响范围并获得明确确认。

接口详述

新建在线表格

从零新建一篇企微在线表格：空白，或带初始数据（二维表格数据）。本接口不接受任何文件路径参数——"用本地文件建/导入"走「导入在线表格」。

命令
bash
wecom-cli sheet create --json '<JSON 参数>'
参数
字段类型必填默认值语义
doc_namestring是—表格标题
grid_dataobject否—默认子表初始化数据；子结构见下方

grid_data 对象结构：

子字段类型必填默认值语义
start_row / start_columnint否0起始行 / 列号，从 0 起
rowsarray否—各行数据；每项 values 为单元格数组
rows[].values[].cell_valueobject否—单元格值，见下方「cell_value 类型选择」
rows[].values[].data_typestring否—枚举：TEXT / NUMBER / LINK / FORMULA
cell_value 类型选择

硬规则：选择 cell_value 形态后，必须同时把同级的 data_type 设置为下表对应值。

形态对应 data_type结构适用场景
textTEXT{"text": "<纯文本>"}纯文本内容（如姓名、说明、标签、编号字符串等）
numberNUMBER{"number": 123.45}数值，用于金额、数量、比率等需要参与公式计算或聚合的数据；值为 JSON 数字类型，不加引号
formulaFORMULA{"formula": "=SUM(A1,A2)"}任何以 = 开头的公式，包括 =SUM(...)、=A1+B1、=IF(...)、=VLOOKUP(...) 等
linkLINK{"link": {"url": "<URL>", "text": "<显示文本>"}}超链接
返回
字段类型说明
docidstring新建表格 ID
urlstring表格访问链接
使用规则
  • 何时走 import 而非本接口：用户提到具体文件路径、或明确说"导入 / 用这个文件建"，一律走「导入在线表格」。

导入在线表格

把本地文件（.csv / .xls / .xlsx）导入为企微在线表格。

命令
bash
wecom-cli sheet import --json '<JSON 参数>'
参数
字段类型必填默认值语义
file_namestring是—二进制文件名（含后缀），用于业务判断源文件类型
file_pathstring是—源文件的本地绝对路径
passwdstring否—Office 文件加密密码（若有）
返回
字段类型说明
docidstring导入完成后的表格 ID
urlstring导入完成后的访问链接
task_statusstring任务状态枚举，如 succ 成功

读取在线表格

根据 docid 读取在线表格的基础信息，包括工作表列表、文档名称与访问链接。所有后续 sheet * 接口的 sheet_id 都从本接口返回的 sheets[] 中取。

命令
bash
wecom-cli sheet get --json '<JSON 参数>'
参数
字段类型必填默认值语义
docidstring是—在线表格 ID
返回
字段类型说明
sheetsarray工作表列表；每项含 sheet_id / title / row_count / column_count / data_range 等基础信息
urlstring文档访问链接
namestring文档名称
使用规则
  • 拿到 sheet_id 后继续读取子表数据是另一个接口，命令字符串、参数名、是否分页等都没有在本节出现，必须先用 read 读 references/sheet-ranges-get.md，再据此构造命令。

跨技能依赖

依赖技能典型协作场景数据流向
wecomcli-doc-manage用户只给表格名称/关键词，需搜索获取 docid 后再读写表格；或需要文件级操作（改名、权限等）wecomcli-doc-manage 的「搜索文档」接口 → 返回 docid → 本 skill 的读取/修改/追加接口

必填参数缺失 / docid 多候选 / 新建 vs 导入等歧义场景，用简洁自然语言仅追问缺失或有歧义的信息；有候选项时在文字中列出供用户选择，不得自行猜测。

docid 使用规则

docid仅cli使用。 最终展示用户时，不应展示 docid，而是使用文档 URL：

[doc_name](doc_url)

docid 是文档的唯一标识符，调用任何文档内容操作技能时均需提供。禁止自造 docid，按以下优先级获取：

  1. 从文档链接提取（优先）：用户提供了企微文档 URL 时，直接从 URL 中解析。URL 格式为 https://doc.weixin.qq.com/<type>/<docid>?scode=...，取 /<type>/ 后、? 前的部分即为 docid。
  2. 通过文档搜索获取（备选）：用户仅提供文档名称或关键词、未给链接时，先调用 wecomcli-doc-manage 搜索文档，从返回结果中取 docid。
  3. 用户直接提供：用户明确给出了完整 docid，可直接使用，无需再提取或搜索。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Wecomcli Sheet AI skill do?

何时用:仅当用户明确指向企业微信『在线表格』或提供 doc.weixin.qq.com/sheet/ 链接时使用;泛指做表格默认先按消歧确认,智能表格内容操作走 wecomcli-smartsheet,本地表格默认走本地工具。在线表格:新建、导入 CSV/Excel、读取信息与数据、修改内容、追加行、子表管理;文档公共操作走 wecomcli-doc-manage。

Why use Wecomcli Sheet on TypingMind?

Because you install it once and use it with any model. Wecomcli Sheet is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Wecomcli Sheet in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Pinvou/pinvou-agent/tree/main/pinvou3-app/src-tauri/resources/common/bundle/wecom-skills/wecomcli-sheet. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Wecomcli Sheet?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Wecomcli Sheet?

As many as you like. As long as a model supports skills, you can use Wecomcli Sheet with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Wecomcli Sheet AI skill free?

Yes. It is published on GitHub by Pinvou under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
anthropics logo

Skill Development

anthropics
OrganizationPopular

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill…

23.8K
146.3K
1 files
View
DietrichGebert logo

Ponytail Help

DietrichGebert
CommunityPopular

Quick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".

7.6K
141.3K
Instructions
View
garrytan logo

Context Restore

garrytan
CommunityPopular

Restore working context saved earlier by /context-save. (gstack)

19.9K
133.5K
1 files
View
garrytan logo

Context Save

garrytan
CommunityPopular

Save working context. (gstack)

19.9K
133.5K
1 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇