Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计提醒

connectconnect 搜索

Agent Skill

connect 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 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

582

周安装

24

GitHub Stars

66

下载量

190
CodexClaudeCursorGemini CLI

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

unknown

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:connect(connect 搜索)
来源仓库:https://github.com/indranilbanerjee/digital-marketing-pro
仓库路径:skills/connect
安装命令:
npx skills add https://github.com/indranilbanerjee/digital-marketing-pro --skill connect
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 npx skills 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。

skills.shnpx skills
npx skills add https://github.com/indranilbanerjee/digital-marketing-pro --skill connect

简介

connect 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。

  • 适用于关键词搜索、任务场景匹配或来源线索梳理等研究检索场景。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装并使用该技能。
  • 安装前需确认权限范围、维护状态及是否涉及联网、命令执行或文件读写操作。
  • connect 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

/dm:connect

Purpose

Guide users through connecting a specific MCP integration to the Digital Marketing Pro plugin. Provides platform-specific setup instructions, credential requirements, configuration steps, and verification. This is the user-friendly entry point for adding integrations — it handles the common cases (known connectors with established setup paths) while /dm:add-integration handles custom or unknown MCP servers.

Input Required

The user must provide (or will be prompted for):

  • Connector name: The service to connect — e.g., "google-ads", "salesforce", "mailchimp", "twilio", "deepl". If the user provides a partial or informal name (e.g., "google analytics", "fb ads", "linkedin"), match it to the closest connector in the registry
  • Environment (optional): Whether they're using Claude Code (supports HTTP + npx) or Cowork (HTTP only). Defaults to auto-detect based on available context. If the requested connector is npx-only and the user is on Cowork, explain the limitation and suggest HTTP alternatives in the same category

Process

  1. Look up connector: Execute python3 scripts/connector-status.py --action setup-guide --name <connector> to get the detailed setup guide for the requested connector. If the name doesn't match exactly, search the registry for close matches and suggest the correct name.
  2. Check current status: Execute python3 scripts/connector-status.py --action check --name <connector> to determine if the connector is already configured. If already connected, report that and show which skills it powers — ask if the user wants to verify connectivity or reconfigure.
  3. Present setup instructions based on transport type: For HTTP connectors (Slack, Canva, Figma, HubSpot, Notion, Ahrefs, Similarweb, Klaviyo, Google Calendar, Gmail, Stripe, Asana, Webflow): For npx connectors (Google Ads, Meta, Salesforce, Twilio, etc.):

- Explain that the connector is already pre-configured in .mcp.json - No API keys or manual configuration needed - The user just needs to use a skill that requires it — Claude will prompt for OAuth authorization - Example: "Your Slack connector is already configured. Just run /dm:send-notification and you'll be prompted to authorize Slack access." - List the skills this connector enables - List the specific environment variables needed with clear descriptions - Provide platform-specific instructions for obtaining credentials: - Where to go in the platform's dashboard to create API keys - What permissions/scopes are needed - Any prerequisites (developer accounts, app creation, etc.) - Show the exact .mcp.json entry to add (from the setup guide) - Offer two setup paths: 1. Quick: "Set the environment variables and run /dm:add-integration <name> to configure automatically" 2. Manual: Show the JSON block to add to .mcp.json directly - Note that npx connectors work in Claude Code only, not Cowork

  1. Handle unknown connectors: If the connector name isn't in the registry:

- Search for close matches and suggest them - If no match found, explain that it's a custom integration and guide them to /dm:add-integration which handles npm package discovery and custom MCP server setup - List the categories of connectors available so they can explore alternatives

  1. Verify after setup (for npx connectors): After the user confirms they've set up credentials, offer to verify connectivity:

- Check that all required environment variables are set and non-empty - Suggest running a read-only test via the connector to confirm it works - Report success or diagnose failure with specific guidance

Output

A connector setup guide containing:

  • Connector info: Name, category, description, transport type (HTTP/npx), and current status (connected/not connected)
  • Skills unlocked: List of all skills this connector enables, with brief descriptions of what each skill does
  • Setup instructions: Step-by-step guide appropriate to the transport type — OAuth flow for HTTP, credential setup for npx
  • Credential requirements (npx only): Exact environment variable names, where to obtain them, and required permissions
  • Configuration entry (npx only): The exact JSON block to add to .mcp.json, ready to copy
  • Verification steps: How to confirm the connector is working after setup
  • Alternative connectors: Other connectors in the same category that the user might consider (e.g., "If you prefer Salesforce over HubSpot for CRM, run /dm:connect salesforce")
  • Next steps: "Run /dm:integrations to see your updated integration dashboard" and relevant skills to try

Agents Used

  • No specialized agent needed — this skill uses the connector-status.py script directly and provides platform-specific guidance based on the connector registry

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

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

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

Codex

38.55%
按下载量换算73

Claude

28.23%
按下载量换算54

Cursor

20.74%
按下载量换算39

Gemini CLI

9.88%
按下载量换算19

安全审计

Gen Agent Trust Hub

可疑

Socket

可疑

Snyk

通过

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