Token导航 LogoToken导航TokenDH.com
研究检索敏感数据clawhub未标认证来源可访问clear审计提醒

makexmakex 搜索

Agent Skill

makex 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。

总安装

17,734

周安装

754

GitHub Stars

公开资料未说明

下载量

6,213
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

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:makex(makex 搜索)
来源仓库:https://github.com/tkejr/makex
安装命令:
openclaw skills install makex
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 makex

简介

使用具有组织级身份验证和统一端点的 OpenClaw API 通过 MakeX 集成并执行来自第三方服务的操作。

SKILL.md

OpenClaw Integrations API

OpenClaw is a skill-based integration system that allows apps built on MakeX to discover and execute actions from third-party services (Gmail, Slack, GitHub, etc.) via Composio.

Authentication

All endpoints require the X-Org-Token header containing an organization service token. This token is validated against the organization database. User session cookies are not used — these endpoints are designed for server-to-server communication.

X-Org-Token: <org-service-token>

Don't have an org token?

  1. Go to https://www.makex.app/ and sign up for an account.
  2. Navigate to Settings in your dashboard.
  3. Copy your API key from the settings page — this is your X-Org-Token.

Base URL

POST /api/openclaw/integrations/<endpoint>

All endpoints support CORS via a preflight OPTIONS handler.

Endpoints

1. Search Actions

POST /api/openclaw/integrations/search-actions

Discover available actions/tools across one or more integrations.

Request Body:

{
  "integrations": ["gmail", "slack", "github"],
  "toolkit": "gmail",
  "search": "send"
}
  • integrations (required): Array of integration slugs to search across.
  • toolkit (optional): If provided, overrides integrations and searches only this toolkit.
  • search (optional): Filter actions by keyword.

Response (200):

{
  "total": 12,
  "actions": {
    "gmail": [
      { "slug": "GMAIL_SEND_EMAIL", "name": "Send Email" },
      { "slug": "GMAIL_CREATE_DRAFT", "name": "Create Draft" }
    ],
    "slack": [
      { "slug": "SLACK_SEND_MESSAGE", "name": "Send Message" }
    ]
  }
}

2. Connected Account

POST /api/openclaw/integrations/connected-account

Check if a specific integration is connected for the organization and retrieve account details.

Request Body:

{
  "integration": "gmail"
}
  • integration (required): The integration slug to check.

Response (200):

{
  "accountId": "conn_abc123",
  "userId": "org_xyz",
  "integration": "gmail",
  "status": "ACTIVE"
}

Response (404) — not connected:

{
  "error": "No active connected account found for integration gmail",
  "availableIntegrations": ["slack", "github"]
}

3. Action Details

POST /api/openclaw/integrations/action-details

Get the full specification of a specific action, including its input and output parameters.

Request Body:

{
  "action_slug": "GMAIL_SEND_EMAIL"
}
  • action_slug (required): The slug of the action to retrieve.

Response (200):

{
  "name": "Send Email",
  "slug": "GMAIL_SEND_EMAIL",
  "description": "Send an email via Gmail",
  "inputParameters": {
    "to": { "type": "string", "description": "Recipient email", "required": true },
    "subject": { "type": "string", "description": "Email subject" },
    "body": { "type": "string", "description": "Email body" }
  },
  "outputParameters": {
    "messageId": { "type": "string" },
    "threadId": { "type": "string" }
  }
}

4. Run Action

POST /api/openclaw/integrations/run-action

Execute a specific action on a connected account.

Request Body:

{
  "toolName": "GMAIL_SEND_EMAIL",
  "accountId": "conn_abc123",
  "arguments": {
    "to": "user@example.com",
    "subject": "Hello",
    "body": "Hi there"
  }
}
  • toolName (required): The action slug to execute.
  • accountId (required): The connected account ID (from the connected-account endpoint).
  • arguments (optional): Structured key-value arguments for the action.
  • text (optional): Natural language text input (used if arguments is not provided).
  • version (optional): API version override.
  • custom_auth_params (optional): Custom authentication parameters.
  • custom_connection_data (optional): Custom connection data.
  • allow_tracing (optional): Enable tracing for the execution.

Response (200): The raw Composio execution response (varies by action).


5. Output Structure

POST /api/openclaw/integrations/output-structure

Execute an action and return its output structure. Useful for determining the shape of an action's response.

Request Body:

{
  "action_slug": "GMAIL_SEND_EMAIL",
  "accountId": "conn_abc123",
  "arguments": {
    "to": "test@example.com",
    "subject": "Test",
    "body": "Test body"
  }
}
  • action_slug (required): The action slug to execute.
  • accountId (required): The connected account ID.
  • arguments (optional): Arguments to pass to the action.

Response (200):

{
  "successful": true,
  "data": { ... }
}

Error Responses

All endpoints return errors in a consistent format:

{ "error": "Description of what went wrong" }
StatusMeaning
400Missing required parameters
401Missing or invalid X-Org-Token
404Resource not found (e.g., no connected account)
500Server error or missing COMPOSIO_API_KEY

Typical Workflow

  1. Search actions to discover what's available for connected integrations.
  2. Get connected account to retrieve the accountId for a specific integration.
  3. Get action details to understand input/output parameters for a chosen action.
  4. Run action to execute the action with the required arguments.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

87.93%
按下载量换算5,463

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

未展示

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills