Use the Moltsheet CLI to manage spreadsheet-style data for AI workflows. Prefer the CLI over raw HTTP. Authenticate once, prefer `--json`, and use files or s...
数据来源:ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一:命令行安装(推荐)
推荐(无需提前安装 clawhub)
npx clawhub@latest --dir ~/.claude/skills install moltsheet或使用 clawhub CLI(需提前安装)
clawhub --dir ~/.claude/skills install moltsheet⚠️ 需要 Node.js 18+,没有 Node?请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二:手动下载安装(无需 Node)
下载 ZIP,解压后将文件夹放到以下路径,重启 Agent 即可:
安装路径
~/.claude/skills/moltsheet/💡解压后将文件夹放到上方路径,重启 Agent 即可生效
--- name: moltsheet description: Interact with a web-based Excel-like spreadsheet API for AI agents. Use when you need to create, manipulate, or query spreadsheet data programmatically, or when the user asks to work with Excel-like data. Authenticate using API key in Authorization header. allowed-tools: Bash(curl *) ---
A web-based Excel-like API for AI agents to create, manipulate, and query spreadsheet data programmatically. Supports bulk operations for large datasets.
https://www.moltsheet.com/api/v1
Authorization: Bearer .example fields showing correct formatsuccess, error, message, and contextual helpRegister once to obtain an API key. Required fields: displayName and slug.
- ✅ Valid: my.agent, bot123, agent.v2 - ❌ Invalid: .agent, agent., My.Agent (uppercase not allowed)
agent.one conflicts with AGENT.ONE)curl -X POST https://www.moltsheet.com/api/v1/agents/register \
-H "Content-Type: application/json" \
-d '{
"displayName": "Data Processor Agent",
"slug": "data.processor",
"description": "Processes spreadsheet data"
}'
Response:
{
"success": true,
"agent": {
"api_key": "uuid-here",
"displayName": "Data Processor Agent",
"slug": "data.processor",
"created_at": "2026-02-03T10:00:00Z"
},
"message": "Agent registered successfully. Save your API key - it cannot be retrieved later.",
"usage": "Include in all requests: Authorization: Bearer uuid-here",
"privacy": "Your API key is private and will never be exposed to other agents"
}
Save your api_key securely—it is required for all API requests.
Slug Availability Check: If slug is already taken (case-insensitive):
{
"success": false,
"error": "Slug already taken",
"message": "The slug \"data.processor\" is already in use (case-insensitive check)",
"available": false,
"suggestion": "Try a different slug or add numbers/dots to make it unique"
}
Validation Error Example:
{
"success": false,
"error": "Slug cannot start or end with a dot",
"message": "Slug must be 3-30 characters, lowercase letters, digits, and dots (not at start/end)",
"example": {
"displayName": "Data Processor Agent",
"slug": "data.processor",
"description": "Processes spreadsheet data"
},
"rules": {
"length": "3-30 characters",
"allowed": "lowercase letters (a-z), digits (0-9), dots (.)",
"dotPosition": "dots only in the middle (not at start or end)",
"examples": ["my.agent", "bot123", "agent.v2"]
}
}
All requests must include your API key in the Authorization header:
-H "Authorization: Bearer YOUR_API_KEY"
Security Notes:
https://www.moltsheet.comPrivacy Guarantee:
slug and displayName onlycurl -X POST https://www.moltsheet.com/api/v1/sheets \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"name": "MySheet", "description": "A test sheet", "schema": [{"name": "Column A", "type": "string"}, {"name": "Column B", "type": "number"}]}'
Response:
{
"success": true,
"id": "sheet-uuid",
"message": "Sheet \"MySheet\" created successfully"
}
Error Examples:
{
"success": false,
"error": "Invalid \"schema\" property",
"example": {
"name": "My Sheet",
"schema": [
{ "name": "Name", "type": "string" },
{ "name": "Age", "type": "number" }
]
},
"supported_types": ["string", "number", "boolean", "date", "url"]
}
{"name": string, "type": string}. Types: string, number, boolean, date, url.Lists all sheets you own and sheets shared with you as a collaborator.
curl https://www.moltsheet.com/api/v1/sheets \
-H "Authorization: Bearer YOUR_API_KEY"
Response:
{
"success": true,
"sheets": [
{
"id": "sheet-uuid-1",
"name": "My Own Sheet",
"description": "A sheet I own",
"role": "owner",
"schema": [{"name": "Name", "type": "string"}],
"rowCount": 2
},
{
"id": "sheet-uuid-2",
"name": "Shared Sheet",
"description": "A sheet shared with me",
"role": "collaborator",
"access_level": "write",
"schema": [{"name": "Name", "type": "string"}],
"rowCount": 5
}
],
"summary": {
"owned": 1,
"shared": 1,
"total": 2
}
}
Sheet Roles:
"role": "owner" - You created this sheet and have full control"role": "collaborator" - Shared with you by another agent - "access_level": "read" - View only - "access_level": "write" - View and modify
curl https://www.moltsheet.com/api/v1/sheets/SHEET_ID/rows \
-H "Authorization: Bearer YOUR_API_KEY"
Response:
{
"success": true,
"rows": [
{"id": "row-1", "Name": "John", "Role": "CEO"},
{"id": "row-2", "Name": "Jane", "Role": "CTO"}
]
}
curl -X PUT https://www.moltsheet.com/api/v1/sheets/SHEET_ID \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"name": "New Name", "description": "Updated desc", "schema": [...] }'
Response: {"success": true, "sheet": {...}}
⚠️ Data Loss Protection: When updating schema, if columns are removed that contain data, you must add ?confirmDataLoss=true to the URL:
curl -X PUT "https://www.moltsheet.com/api/v1/sheets/SHEET_ID?confirmDataLoss=true" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"schema": [{"name": "NewColumn", "type": "string"}]}'
Without Confirmation (Error Response):
{
"success": false,
"error": "Data loss protection",
"message": "Schema update would delete 1 column(s) containing data. To proceed, add ?confirmDataLoss=true to the URL.",
"columns_to_delete": [{"name": "CEO", "type": "string"}],
"data_warning": "All data in these columns will be permanently deleted",
"alternatives": {
"rename_column": "POST /api/v1/sheets/SHEET_ID/columns/{index}/rename",
"example": "To rename instead of delete, use: POST /api/v1/sheets/SHEET_ID/columns/0/rename with body: { \"newName\": \"NewColumnName\" }"
}
}
Best Practice: Use the rename endpoint (below) instead of schema updates when renaming columns to preserve data automatically.
curl -X DELETE https://www.moltsheet.com/api/v1/sheets/SHEET_ID \
-H "Authorization: Bearer YOUR_API_KEY"
Response: {"success": true} Response: {"success": true}
...
安装 Moltsheet - Spreadsheets for AI agents 后,可以对 AI 说这些话来触发它
Help me get started with Moltsheet - Spreadsheets for AI agents
Explains what Moltsheet - Spreadsheets for AI agents does, walks through the setup, and runs a quick demo based on your current project
Use Moltsheet - Spreadsheets for AI agents to use the Moltsheet CLI to manage spreadsheet-style data for AI workf...
Invokes Moltsheet - Spreadsheets for AI agents with the right parameters and returns the result directly in the conversation
What can I do with Moltsheet - Spreadsheets for AI agents in my documents & notes workflow?
将技能文件夹放到 ~/.claude/skills/moltsheet/ 目录(个人级,所有项目可用),或 .claude/skills/moltsheet/(项目级)。重启 AI 客户端后,用 /moltsheet 主动调用,或让 AI 根据上下文自动发现并使用。
Moltsheet - Spreadsheets for AI agents 支持 Claude、Cursor、OpenClaw,可与这些 AI 平台无缝集成,扩展其能力。
Moltsheet - Spreadsheets for AI agents 可免费安装使用。请查阅仓库了解许可证信息。
Use the Moltsheet CLI to manage spreadsheet-style data for AI workflows. Prefer the CLI over raw HTTP. Authenticate once, prefer `--json`, and use files or s...
Lists the top use cases for Moltsheet - Spreadsheets for AI agents, with example commands for each scenario
Automate my documents & notes tasks using Moltsheet - Spreadsheets for AI agents
Identifies repetitive steps in your workflow and sets up Moltsheet - Spreadsheets for AI agents to handle them automatically
Moltsheet - Spreadsheets for AI agents 属于「Documents & Notes」分类,该分类的技能帮助 AI 智能体在此领域执行专业任务。