List Segmentation

Overview

Take an enriched Extruct table and a hypothesis set, then segment companies by hypothesis fit and assign tiers based on data richness and signal strength. Outputs a tiered, segmented list ready for email generation.

When to Use

Trigger this skill when you need to:

Segment companies by hypothesis fit
Tier companies for prioritization
Prioritize your list for outreach
Determine which companies get personalized emails
Decide messaging order and depth

Trigger phrases: “segment”, “tier”, “segment companies”, “tier companies”, “prioritize list”, “segment and tier”, “tiering”, “which companies first”

Inputs

enriched_table

string

required

Extruct table ID from the list-enrichment skill containing company data with enrichment columns

hypothesis_set

string

required

Path to hypothesis set file: claude-code-gtm/context/{vertical-slug}/hypothesis_set.md

context_file

string

Company context file: claude-code-gtm/context/{company}_context.md (recommended for better segmentation)

Environment Setup

Verify API Token

The skill checks for EXTRUCT_API_TOKEN environment variable. If missing, you’ll be prompted to provide your Extruct API token.

export EXTRUCT_API_TOKEN=<your-token>

API Configuration

Base URL: https://api.extruct.ai/v1Authentication uses Bearer token in headers.

Workflow

Load Data

Fetch enriched table data via GET /tables/{table_id}/data and parse all rows with their enrichment column values.Read the hypothesis set file and parse each hypothesis into:

Number and short name
Description with data points
Best-fit company type

Match Companies to Hypotheses

For each company row, evaluate which hypothesis fits best by considering:

Enrichment data alignment — Do the enrichment column values match the hypothesis’s “best fit” description?
Signal strength — How many enrichment columns have useful data (not N/A)?
Specificity — Does the company’s profile match the hypothesis narrowly or broadly?

Assign each company ONE primary hypothesis. If multiple fit, pick the strongest signal.

Decision Framework

For each company:
  1. Read all enrichment values
  2. For each hypothesis:
     - Does the company's vertical/industry match the "best fit"?
     - Do enrichment values confirm the hypothesis pain point?
     - Is there a specific data point that makes this hypothesis resonate?
  3. Pick the hypothesis with the strongest evidence
  4. If no hypothesis fits well, mark as "Unmatched"

Assign Tiers

Three tiers based on fit strength and data richness:

Tier	Criteria	Action
Tier 1	Strong hypothesis fit + data-rich (3+ enrichment fields populated) + clear hook signal	Personalized email via `email-response-simulation` review
Tier 2	Medium hypothesis fit OR data-rich but no clear hook	Standard templated email via `email-generation`
Tier 3	Weak fit OR missing data (2+ fields N/A) OR unmatched hypothesis	Hold for re-enrichment or different campaign

Tier 1 Signals (any of these)

CEO/leadership made a public statement related to the hypothesis
Recent news directly relevant to the pain point
Hiring for roles that signal the hypothesis pain
High hypothesis fit score from enrichment (grade 4-5)

Tier 3 Signals (any of these)

Most enrichment fields returned N/A
No hypothesis match above threshold
Company profile too generic to confidently segment

Generate Output

Output a segmented list in two formats:Markdown table (for review):

## Segmented List: [Campaign Name]

### Tier 1 — [N] companies (personalized outreach)

| Company | Domain | Hypothesis | Tier Rationale | Hook Signal |
|---------|--------|-----------|----------------|-------------|
| [name] | [domain] | #[N] [name] | [why this tier] | [specific hook] |

### Tier 2 — [N] companies (templated outreach)
...

### Tier 3 — [N] companies (hold/re-enrich)
...

CSV (for email-generation):Saved to claude-code-gtm/csv/input/{campaign-slug}/segmented_list.csv with columns:

company_name, domain, tier, hypothesis_number, hypothesis_name, tier_rationale, hook_signal

Review with User

Present summary stats:

Total companies: N
Tier 1: N (X%)
Tier 2: N (X%)
Tier 3: N (X%)
Unmatched: N

Review questions:

“Does the tier distribution look right? (Typical: 10-20% Tier 1, 50-60% Tier 2, 20-30% Tier 3)”
“Any companies that should move tiers?”
“Ready to proceed to email-generation?”

Tiering Framework

Scoring Formula

Optional numeric scoring for systematic tier assignment:

tier_score = (hypothesis_fit * 0.4) + (data_richness * 0.3) + (hook_available * 0.3)

Where:
- hypothesis_fit: 0-5 (from grade column or manual assessment)
- data_richness: 0-5 (count of populated fields / total fields * 5)
- hook_available: 0 (no hook), 3 (generic hook), 5 (specific hook)

Tier 1: score >= 3.5
Tier 2: score >= 2.0
Tier 3: score < 2.0

Tier Decision Matrix

Signal	Tier 1	Tier 2	Tier 3
Hypothesis fit score	4-5	2-3	1 or N/A
Enrichment fields populated	4+ of 5	2-3 of 5	0-1 of 5
Hook signal available	Yes (specific)	Generic only	None
Company profile depth	Rich description + recent data	Basic description	Minimal or stale
Vertical match	Exact	Adjacent	No match

Output Actions by Tier

Tier 1: Full Personalization Pipeline

Expected volume: 10-20% of list (20-50 companies)Email quality: Highly personalized P1 with specific hookProcess:

Run through email-generation with hypothesis + hook signal
Review each email via email-response-simulation (persona research)
Iterate until satisfied
Upload to sequencer in a separate, high-touch campaign

Tier 2: Templated with Hypothesis Variation

Expected volume: 50-60% of list (100-300 companies)Email quality: Hypothesis-personalized but not individually researchedProcess:

Run through email-generation with hypothesis only (no individual hooks)
Group by hypothesis — each group gets a slightly different P1
Spot-check 5-10 emails for quality
Upload to sequencer in main campaign

Tier 3: Hold or Re-Process

Expected volume: 20-30% of listEmail quality: Do not email until upgraded to Tier 2+Options:

Re-enrich: Run additional enrichment columns to fill gaps
Different campaign: Save for a broader, less-targeted campaign
Drop: If the company truly doesn’t fit any hypothesis

Troubleshooting Tier Distribution

Issue	Fix
80%+ in Tier 3	Hypotheses don’t match the list — re-run `market-research` or rebuild the list
50%+ in Tier 1	Tiering too lenient — tighten the hook signal requirement
0% in Tier 1	No personalization columns — run `enrichment-design` in personalization mode
Even split across all 3	Usually correct — proceed

API Reference

Fetch Table Data

GET /tables/{table_id}/data
Authorization: Bearer {EXTRUCT_API_TOKEN}

Response:

{
  "rows": [
    {
      "id": "row-uuid",
      "cells": {
        "company_name": "Acme Corp",
        "domain": "acme.com",
        "enrichment_column_1": "value",
        "enrichment_column_2": "value"
      }
    }
  ]
}

Next Steps

After segmentation is complete:

Tier 1 companies → people-search → email-search → email-generation → email-response-simulation
Tier 2 companies → people-search → email-search → email-generation
Tier 3 companies → Hold or re-run list-enrichment

Get Started

Core Concepts

Skills Reference

Guides

API Integration

Overview

When to Use

Inputs

Environment Setup

Workflow

Tiering Framework

Scoring Formula

Tier Decision Matrix

Output Actions by Tier

Troubleshooting Tier Distribution

API Reference

Fetch Table Data

Next Steps

Build docs developers (and LLMs) love

Get Started

Core Concepts

Skills Reference

Guides

API Integration

​Overview

​When to Use

​Inputs

​Environment Setup

​Workflow

​Tiering Framework

​Scoring Formula

​Tier Decision Matrix

​Output Actions by Tier

​Troubleshooting Tier Distribution

​API Reference

​Fetch Table Data

​Next Steps

Build docs developers (and LLMs) love

Overview

When to Use

Inputs

Environment Setup

Workflow

Tiering Framework

Scoring Formula

Tier Decision Matrix

Output Actions by Tier

Troubleshooting Tier Distribution

API Reference

Fetch Table Data

Next Steps