Add LinkedIn ABM Agent - Multi-Channel Outbound Automation

[Samir-atra]

Description

Implements a complete LinkedIn ABM (Account-Based Marketing) agent for multi-channel outreach automation. The agent orchestrates complex, multi-tool workflows spanning data enrichment, outreach automation, and offline touchpoints.

Features

• LinkedIn Prospecting: Scrape profiles from URLs, validate against target criteria
• Data Enrichment: Enrich prospects with Apollo.io (email, phone) and Skip Trace (mailing addresses)
• Message Generation: Create personalized messages for email, LinkedIn, and direct mail
• Human-in-the-Loop: Review and approval workflow before sending
• Multi-Channel Outreach: Execute coordinated outreach across email (Day 1), LinkedIn (Day 3), direct mail (Day 7)
• Campaign Tracking: Log outcomes, export reports, track conversions

Agent Flow

intake -> prospect -> enrich -> message -> review -> outreach -> tracking
                      ^                                      |
                      +---------- feedback loop <---+

Type of Change

• New feature (non-breaking change that adds functionality)

Related Issues

Resolves #4419

Changes Made

Agent Template (examples/templates/linkedin_abm_agent/)

• Complete 7-node pipeline agent with intake, prospecting, enrichment, messaging, review, outreach, and tracking nodes
• 8 edges connecting all nodes with feedback loops
• Configuration, runtime, and test files
• README documentation

MCP Tools (New)

• linkedin_tool: Profile scraping, connection requests, URL validation
• scribeless_tool: Handwritten letter sending, status tracking, balance checking
• skiptrace_tool: Mailing address lookup, batch processing, CSV parsing

Credential Specs

• LinkedIn session cookie spec
• Scribeless API key spec
• Skip Trace API key spec

Unit Tests

• Node definition validation
• Agent structure validation
• Edge configuration validation
• Goal definition validation

Testing

• Unit tests pass (cd core && pytest tests/)
• Lint passes (cd core && ruff check .)
• Manual testing performed (agent structure validated)

Checklist

• My code follows the project's style guidelines
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-under areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes

[github-actions]

PR Requirements Warning

This PR does not meet the contribution requirements.
If the issue is not fixed within ~24 hours, it may be automatically closed.

PR Author: @Samir-atra
Found issues: #4419 (assignees: none)
Problem: The PR author must be assigned to the linked issue.

To fix:

1. Assign yourself (@Samir-atra) to one of the linked issues
2. Re-open this PR

Exception: To bypass this requirement, you can:

• Add the micro-fix label or include micro-fix in your PR title for trivial fixes
• Add the documentation label or include doc/docs in your PR title for documentation changes

Micro-fix requirements (must meet ALL):

Qualifies	Disqualifies
< 20 lines changed	Any functional bug fix
Typos & Documentation & Linting	Refactoring for "clean code"
No logic/API/DB changes	New features (even tiny ones)

Why is this required? See #472 for details.