From gtm-skills
Designs enrichment columns that bridge research hypotheses to list enrichment, with segmentation and personalization modes. Walks users through interactive column design and outputs ready-to-run column_configs.
How this skill is triggered — by the user, by Claude, or both
Slash command
/gtm-skills:enrichment-designThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Bridge the gap between research hypotheses and table enrichment. Define WHAT to research about each company before running enrichment.
Bridge the gap between research hypotheses and table enrichment. Define WHAT to research about each company before running enrichment.
market-research has produced a hypothesis setlist-enrichment — this skill designs the columns, that skill runs themGoal: Design columns that score or confirm hypothesis fit per company.
Input: Hypothesis set (from market-research or context file)
Process:
column_configsExample: If hypothesis is "Database blind spot — 80-90% of targets invisible to standard tools":
Goal: Design columns that capture company-specific hooks for email personalization.
Input: Target list + what the user wants to personalize on
Process:
column_configsExample: For personalization hooks:
Do NOT just generate columns silently. Walk through this with the user:
Step 1: Present the framework
Show the user the two modes and ask which applies (or both).
Step 2: Propose initial columns
Based on hypotheses or user input, propose 3-5 columns. For each, show:
Column: [name]
Type: [output_format]
Agent: [research_pro | llm]
Prompt: [the actual prompt text]
Why: [what this tells us for segmentation/personalization]
Step 3: Refine together
Ask:
Step 4: Confirm column budget
Guidance:
Step 5: Output column_configs
Generate the final column configs as a JSON array ready for list-enrichment:
[
{
"kind": "agent",
"name": "Column Display Name",
"key": "column_key_snake_case",
"value": {
"agent_type": "research_pro",
"prompt": "Research prompt using {input} for domain...",
"output_format": "text"
}
}
]
| Data point type | Agent type | Why |
|---|---|---|
| Factual data from the web (funding, launches, news) | research_pro | Needs web research |
| Classification from company profile | llm | Profile data is enough |
| Nuanced judgment (maturity, fit score) | research_reasoning | Needs chain-of-thought |
| People/org structure | linkedin | LinkedIn-specific |
| Data point type | Format | When |
|---|---|---|
| Free-form research | text | Open-ended questions |
| Score/rating | grade | 1-5 scale assessments |
| Category | select | Mutually exclusive buckets |
| Multiple tags | multiselect | Non-exclusive tags |
| Structured data | json | Multiple related fields |
| Yes/no with evidence | json | {"match": bool, "evidence": str} |
{input} for the company domainselect/multiselect: list the labels in the prompt tooSee references/data-point-library.md for ~20 pre-built column configs organized by use case.
After column design is complete:
column_configs JSON to the userlist-enrichment. Run that skill with your table ID and these columns."list-enrichment workflownpx claudepluginhub extruct-ai/gtm-skills --plugin gtm-skillsAdd research-powered enrichment columns (funding, verticals, tech stack) to Extruct company tables. Useful for designing enrichment configs and monitoring progress.
Generates personalized sales outreach copy using Claygent AI research on enriched prospect data in Clay tables. For email openers, research prompts, and AI column configs.
Dispatches AI researchers to classify, score, forecast, and enrich datasets at scale. Use via Python SDK or MCP server for one-off or complex workflows.