Token导航 LogoToken导航TokenDH.com
研究检索需要联网clawhub未标认证来源可访问clear审计提醒

abm-outbound反导出站

Agent Skill

abm-outbound 用于处理浏览器自动化、网页检查和页面信息提取,适合在 OpenClaw 中需要让 Agent 打开页面、读取网页或验证前端流程时使用。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

108,619

周安装

4,481

GitHub Stars

2

下载量

35,490
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:abm-outbound(反导出站)
来源仓库:https://github.com/dru-ca/abm-outbound
安装命令:
openclaw skills install abm-outbound
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 abm-outbound

简介

多渠道 ABM 自动化,可将 LinkedIn URL 转变为协调一致的出站活动。抓取个人资料,利用 Apollo(电子邮件+电话)进行丰富,通过 Skip Trace 获取邮寄地址,然后通过 Scribeless 编排电子邮件序列、LinkedIn 触摸和手写信件。在拥挤的收件箱中脱颖而出的秘密武器。

SKILL.md

name
ABM Outbound
description
Multi-channel ABM automation that turns LinkedIn URLs into coordinated outbound campaigns. Scrapes profiles, enriches with Apollo (email + phone), gets mailing addresses via Skip Trace, then orchestrates email sequences, LinkedIn touches, and handwritten letters via Scribeless. The secret weapon for standing out in crowded inboxes.

ABM Outbound

Turn LinkedIn prospect lists into multi-channel outbound: email sequences, LinkedIn touches, and handwritten letters.

Prerequisites

ServicePurposeSign Up
ApifyLinkedIn scraping, Skip Traceapify.com
ApolloEmail & phone enrichmentapollo.io
ScribelessHandwritten lettersplatform.scribeless.co
Instantly *(optional)*Dedicated cold emailinstantly.ai
export APIFY_API_KEY="your_key"
export APOLLO_API_KEY="your_key"
export SCRIBELESS_API_KEY="your_key"

Pipeline

┌─────────────┐    ┌─────────────┐    ┌─────────────┐    ┌─────────────┐    ┌─────────────┐
│  1. INPUT   │───▶│  2. SCRAPE  │───▶│  3. ENRICH  │───▶│  4. ADDRESS │───▶│ 5. OUTREACH │
│  LinkedIn   │    │  Profiles   │    │ Email/Phone │    │ Skip Trace  │    │             │
│    URLs     │    │             │    │             │    │             │    │             │
└─────────────┘    └─────────────┘    └─────────────┘    └─────────────┘    └─────────────┘
   Your list          Apify             Apollo            Apify PFI        Email +
                                                                          LinkedIn +
                                                                          Scribeless

Step 1: Gather LinkedIn URLs

Provide a list of LinkedIn profile URLs from:

  • LinkedIn Sales Navigator exports
  • LinkedIn search scrapers
  • CRM exports
  • Manual prospecting
linkedin_url
https://linkedin.com/in/johndoe
https://linkedin.com/in/janesmith

Step 2: Scrape LinkedIn Profiles

curl -X POST "https://api.apify.com/v2/acts/harvestapi~linkedin-profile-scraper/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "profileUrls": [
      "https://linkedin.com/in/johndoe",
      "https://linkedin.com/in/janesmith"
    ]
  }'

Returns: First name, last name, company, title, location.

Step 3: Enrich with Apollo (Email & Phone)

curl -X POST "https://api.apollo.io/api/v1/people/bulk_match" \
  -H "X-Api-Key: $APOLLO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "reveal_personal_emails": true,
    "reveal_phone_number": true,
    "details": [{
      "first_name": "John",
      "last_name": "Doe",
      "organization_name": "Acme Corp",
      "linkedin_url": "https://linkedin.com/in/johndoe"
    }]
  }'

Returns: Work email, phone numbers.

Step 4: Get Mailing Address (Skip Trace)

curl -X POST "https://api.apify.com/v2/acts/one-api~skip-trace/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": ["John Doe"]}'

Returns: Street address, city, state, postal code.

Important: Verify Skip Trace state matches LinkedIn location.

Step 5: Multi-Channel Outreach

5a: Email Sequence

Option 1: Apollo Sequences (Recommended)

curl -X POST "https://api.apollo.io/api/v1/emailer_campaigns/add_contact_ids" \
  -H "X-Api-Key: $APOLLO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "emailer_campaign_id": "YOUR_SEQUENCE_ID",
    "contact_ids": ["CONTACT_ID_1", "CONTACT_ID_2"],
    "send_email_from_email_account_id": "YOUR_EMAIL_ACCOUNT_ID"
  }'

Option 2: Instantly.ai

curl -X POST "https://api.instantly.ai/api/v1/lead/add" \
  -H "Authorization: Bearer $INSTANTLY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "campaign_id": "YOUR_CAMPAIGN_ID",
    "email": "john@acme.com",
    "first_name": "John",
    "last_name": "Doe",
    "company_name": "Acme Corp",
    "personalization": "Saw Acme just expanded to UK"
  }'

Option 3: CSV Upload

email,first_name,last_name,company,title,phone,personalization
john@acme.com,John,Doe,Acme Corp,VP Marketing,555-1234,Saw Acme just expanded to UK

5b: LinkedIn Sequence

  • Day 1: View profile
  • Day 2: Connection request with personalized note
  • Day 4: Follow-up message if connected
  • Day 7: Engage with their content

5c: Handwritten Letter (Scribeless)

Create campaign at platform.scribeless.co, then add recipients:

curl -X POST "https://platform.scribeless.co/api/recipients" \
  -H "X-API-Key: $SCRIBELESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "campaignId": "YOUR_CAMPAIGN_ID",
    "data": {
      "firstName": "John",
      "lastName": "Doe",
      "company": "Acme Corp",
      "address": {
        "address1": "123 Main St",
        "city": "San Francisco",
        "state": "CA",
        "postalCode": "94102",
        "country": "US"
      },
      "variables": {
        "custom1": "Saw Acme just expanded to the UK — congrats!"
      }
    }
  }'

See references/scribeless-api.md for full API details.

Coordinated Timing

DayEmailLinkedInLetter
1View profileLetter sent
3Connection request
5"Got my note?"Letter arrives
7Value emailMessage if connected
10Case study
14Break-upEngage content

The play: Letter lands → Email references it → LinkedIn reinforces.

Complete Workflow

# 1. Start with LinkedIn URLs
linkedin_urls = load_csv("prospects.csv")

# 2. Scrape profiles
profiles = apify_linkedin_scrape(linkedin_urls)

# 3. Enrich with Apollo
for profile in profiles:
    enriched = apollo_bulk_match(profile)
    profile['email'] = enriched['email']
    profile['phone'] = enriched['phone']

# 4. Get mailing addresses
for profile in profiles:
    address = skip_trace(profile['name'])
    if address['state'] == profile['linkedin_state']:
        profile['address'] = address
        profile['mailable'] = True

# 5. Push to channels
push_to_email_tool(profiles)
push_to_scribeless(profiles, campaign_id)
export_for_linkedin(profiles)

Output Format

first_name,last_name,email,phone,company,title,address1,city,state,postal,country,linkedin,mailable
John,Doe,john@acme.com,555-1234,Acme Corp,VP Marketing,123 Main St,San Francisco,CA,94102,US,linkedin.com/in/johndoe,TRUE

Best Practices

  1. Verify addresses — Skip Trace state should match LinkedIn location
  2. Personalize everything — Company news, job changes, shared connections
  3. Coordinate timing — Letter lands before "did you get my note?" email
  4. Start small — Test with 20-50 prospects before scaling
  5. Track by channel — Know which channel drives replies

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

72.39%
按下载量换算25,691

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

未展示

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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