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审计通过

ghlGHL 搜索

Agent Skill

ghl 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

7,987

周安装

320

GitHub Stars

公开资料未说明

下载量

2,586
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:ghl(GHL 搜索)
来源仓库:https://github.com/brianxmacdonald/ghl
安装命令:
openclaw skills install ghl
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 ghl

简介

通过 GoHighLevel CRM API v2 实现联系人、对话与任务的全读写管理。

  • 适合营销自动化、客户跟进与销售流程整合场景。
  • 支持短信、邮件、WhatsApp 等多渠道通信与工作流触发。
  • 安装命令:openclaw skills install ghl,适用于 OpenClaw。
  • 需提供有效的 GHL API 密钥,并确保网络可达其服务端点。

SKILL.md

name
ghl-crm-mastery
description
Full read/write access to GoHighLevel CRM via API v2. Contacts, conversations, notes, opportunities, calendars, tags, tasks, forms, workflows, payments, and invoices. Includes rate-limit retries, safety guardrails, and real-time conversation support.
version
1.3.0
author
SetupClaw.Tech
homepage
https://setupclaw.tech
metadata
{ "openclaw": { "requires": { "env": ["GHL_API_KEY", "GHL_LOCATION_ID"], "bins": ["python3"] }, "primaryEnv": "GHL_API_KEY", "homepage": "https://setupclaw.tech" } }

GHL CRM Mastery — GoHighLevel API v2 Skill

What This Does

Gives your agent full operational access to GoHighLevel — read, write, and real-time conversation management. Designed for CRM automation agents (appointment setting, lead qualification, pipeline management).

Contact Operations

  • contacts list — List contacts with pagination
  • contacts get — Full contact record by ID (name, email, phone, company, tags, custom fields)
  • contacts search — Find contact by email
  • contacts search-phone — Find contact by phone number
  • contacts update — Update any contact field (company, tags, custom fields, etc.)
  • contacts add-tags — Apply tags to a contact
  • contacts remove-tag — Remove a tag from a contact

Conversation Operations (Real-Time)

  • conversations list — List recent conversations
  • conversations get — Full conversation history for a contact (last 20 messages with direction, type, timestamp)
  • conversations send — Send SMS, email, or DM reply through GHL. This is how the agent responds to leads.

Notes

  • notes add — Add research notes, call summaries, or interaction logs to a contact record
  • notes list — Read existing notes for a contact

Pipeline & Opportunities

  • opportunities list — List pipeline items
  • opportunities get — Full opportunity details
  • opportunities update — Move opportunity to a different pipeline stage

Calendars

  • calendars list — List available calendars
  • calendars events — List events for a calendar

Tags, Forms, Workflows

  • tags list — List all tags in the location
  • forms list — List forms
  • forms submissions — Get submissions for a specific form
  • workflows list — List workflows (read-only)
  • workflows trigger — Trigger a workflow for a contact (NEVER create/edit/delete)

System

  • health — Test GHL API connection

Real-Time Conversation Pattern

The agent uses this skill for instant lead response. The pattern:

First touch (new lead, no prior research):

  1. contacts search-phone or contacts search — find the contact
  2. contacts get — pull full record
  3. notes list — check for existing research
  4. If no research notes → run identity verification (separate skill/process)
  5. conversations get — read conversation history
  6. Craft personalized response
  7. conversations send — reply via GHL
  8. notes add — log research findings + what was sent

Follow-up messages (contact already researched):

  1. contacts get — pull record (already has research in notes)
  2. conversations get — read latest messages
  3. Craft contextual reply (15-30 second target)
  4. conversations send — reply
  5. notes add — brief log of interaction

Key principle: Research happens ONCE per contact. After that, the agent reads its own notes and the conversation history, then replies fast. The goal is real-time chat feel — under 30 seconds for follow-ups.

Prerequisites

Required environment variables (must be set in your .env file):

GHL_API_KEY=your-private-integration-token
GHL_LOCATION_ID=your-location-id

Required runtime: python3 (ships with macOS; verify with python3 --version).

Getting Your GHL Credentials

  1. Log into GoHighLevel → Settings → Integrations → Private Integrations → Create New
  2. Name it appropriately for your deployment
  3. Enable all required scopes:

- contacts.readonly, contacts.write - conversations.readonly, conversations.write - conversations/message.readonly, conversations/message.write - opportunities.readonly, opportunities.write - calendars.readonly, calendars.write - calendars/events.readonly, calendars/events.write - locations/tags.readonly, locations/tags.write - locations/tasks.readonly, locations/tasks.write - forms.readonly, workflows.readonly - payments/transactions.readonly, locations.readonly - invoices.readonly, invoices.write, users.readonly

  1. Copy the Private Integration Token → GHL_API_KEY in .env
  2. Settings → Business Info → copy Location ID → GHL_LOCATION_ID in .env

Usage

All commands are run via the included Python CLI at {baseDir}/scripts/ghl_api.py:

export GHL_API_KEY=$(grep GHL_API_KEY ~/.openclaw/.env | cut -d= -f2)
export GHL_LOCATION_ID=$(grep GHL_LOCATION_ID ~/.openclaw/.env | cut -d= -f2)

# Test connection
python3 {baseDir}/scripts/ghl_api.py health

# Test contact lookup
python3 {baseDir}/scripts/ghl_api.py contacts list --limit 1

# Test conversation read
python3 {baseDir}/scripts/ghl_api.py conversations get --contact-id "YOUR_CONTACT_ID"

# Send a message
python3 {baseDir}/scripts/ghl_api.py conversations send --contact-id "CONTACT_ID" --message "Hello" --type sms

# Add a note
python3 {baseDir}/scripts/ghl_api.py notes add --contact-id "CONTACT_ID" --body "Research findings..."

Safety Guardrails (Non-Negotiable)

  1. Never create contacts — GHL creates contacts automatically when forms are submitted, SMS received, or DMs received. Creating contacts manually risks duplicates. If a contact doesn't exist, flag to the appropriate channel.
  2. Never delete contacts without explicit human confirmation in Slack
  3. Never send bulk SMS without human approval
  4. Never modify workflows — trigger only, never create/edit/delete
  5. Log every write operation — every conversations send and notes add prints a timestamped log line
  6. TCPA compliance — no SMS between 9PM and 8AM in the recipient's time zone (enforced by TCPA handler layer, not this skill)

Network Endpoints

This skill connects exclusively to the GoHighLevel API:

  • https://services.leadconnectorhq.com — GHL API v2 (all operations)

No other external endpoints are contacted. All credentials are read from local environment variables only.

Changelog

v1.3.0 (March 2026)

  • Added metadata.openclaw frontmatter declarations (requires.env, requires.bins, primaryEnv) for ClawHub security compliance
  • Added {baseDir} references for portable skill paths
  • Added explicit network endpoint documentation
  • Updated _meta.json with runtime and credential requirements
  • Generalized agent references for broader deployment compatibility

v1.2.0 (March 2026)

  • Added conversations send, notes list, contacts search-phone
  • Real-time conversation pattern documentation

v1.0.0 (March 2026)

  • Initial release: 24 endpoints covering contacts, conversations, notes, opportunities, calendars, tags, forms, workflows

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

83.66%
按下载量换算2,163

安全审计

VirusTotal

未展示

ClawScan

通过

Static analysis

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。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