Abm Outbound logo

Abm Outbound

Organization
sundial-org
abm-outbound

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.

Overview

Publishersundial-org
Repositoryawesome-openclaw-skills
Skill nameabm-outbound
Stars
664
Forks
97
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by sundial-org on GitHub. Read the source before you install it.

Installation

Install the Abm Outbound AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/sundial-org/awesome-openclaw-skills/tree/main/skills/abm-outbound
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/sundial-org/awesome-openclaw-skills.git /tmp/awesome-openclaw-skills
mkdir -p .claude/skills
cp -r /tmp/awesome-openclaw-skills/skills/abm-outbound .claude/skills/abm-outbound
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Abm Outbound in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Abm Outbound on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Abm Outbound is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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
bash
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
csv
linkedin_url
https://linkedin.com/in/johndoe
https://linkedin.com/in/janesmith

Step 2: Scrape LinkedIn Profiles

bash
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)

bash
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)

bash
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)

bash
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

bash
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

csv
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:

bash
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
1—View profileLetter sent
3—Connection 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

python
# 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

csv
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

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Abm Outbound AI skill do?

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.

Why use Abm Outbound on TypingMind?

Because you install it once and use it with any model. Abm Outbound is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Abm Outbound in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sundial-org/awesome-openclaw-skills/tree/main/skills/abm-outbound. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Abm Outbound?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Abm Outbound?

As many as you like. As long as a model supports skills, you can use Abm Outbound with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Abm Outbound AI skill free?

It is published on GitHub by sundial-org. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇