Firmographic Enrichment

What this does

Firmographic enrichment always looks like it worked, because the rows that filled are visible and the rows that did not are blank rather than flagged. This skill enriches, then measures coverage per field, so a qualification rule built on a field that is only forty percent populated is caught before it silently disqualifies half the list.

Requirements

Check these before you run the skill. Nothing outside this table is needed.

Requirement	Needed	Used for	What it costs you
Apify account and API token (APIFY_TOKEN)	Required	Runs the live data actors	A free Apify account works. Each run bills your own Apify account at the actor's Store price: company-firmographic-enricher 0.004 USD per company.
Node.js 18 or newer	Required	The MCP tool calls	Free. It starts the Mamba Labs MCP server with npx.

Missing a required item? Stop before the live steps and tell the user which item is missing and what it is for. Do not run the step without it and do not present an empty result as an answer. Keys are read from the environment at run time and are never written into a file, a prompt or the output.

When to use it

• enrich these companies
• add headcount and industry
• how complete is my company data
• company size for qualification
• firmographics

Inputs

• domains: the company list
• fields: which fields the downstream qualification actually needs

Shared context this skill reads

Before doing anything else, read whichever of these exist at the project root and use them instead of asking the user to repeat themselves:

• ICP.md

If none exist, do the work from what the user gives you, then offer to write the missing file so the next skill in the pack starts warmer.

Tool connection

Enrichment runs in batch across the domain list and returns per field values so coverage can be measured rather than assumed. industry is often null, and revenue_estimate is a heuristic band derived from headcount, not a reported figure.

This skill calls live data through the Mamba Labs MCP server, which runs the actors on Apify with your own Apify token (https://console.apify.com/account/integrations).

• Installed as a plugin: the server is already wired, and the plugin asks for the token once.
• Installed by hand: copy .mcp.json from this folder into your project root and set APIFY_TOKEN in your environment, or run:

claude mcp add mamba-gtm-suite -e APIFY_TOKEN=<your token> -- npx -y @mambalabsdev/mcp-gtm-suite@1.12.0

Actor	MCP tool	Used for	Store page
Company Firmographic Enricher	enrich_company_firmographics	headcount, industry, headquarters and revenue band by domain	https://apify.com/mambalabs/company-firmographic-enricher

Runnable example input, matched to the live tool schema:

enrich_company_firmographics:

{
  "domains": [
    "example.com",
    "example.net"
  ],
  "batchSize": 5
}

Cost line. Before any live call, state how many calls you plan and which actors they bill. After the run, report the calls made, the calls that failed, and the Apify usage where the tool reports it. Each actor bills the user's own Apify account at its Store price.

No token, no live data. If no Apify token is available, say so and stop the live steps. Never fill a live section from memory and present it as live.

Method

1. Name the fields the downstream rule needs before enriching, so coverage is measured against a requirement rather than reported in general.
2. Enrich in batch and keep the raw response, because a field can be present in the response and lost in extraction.
3. Measure coverage per field as a share of rows, and report it next to the requirement.
4. For any required field below the coverage the rule needs, either find a second source or change the rule. Running a rule on a sparse field is the failure mode.
5. Check the shape of what filled. Headcount as a band and headcount as a number are different fields and a rule written for one breaks on the other.
6. Spot check ten rows against the companies' own sites. Enrichment sources disagree with reality often enough that a sample is not optional.
7. Check the output with scripts/check-output.py before you return it.

Approval stop

This skill does not send email or write to a CRM. If the user asks it to, stop first: show what would be sent or written and wait for an explicit yes.

Output

The enriched table, a coverage table per field against the requirement, the fields that fell short with the recommendation, and the spot check result.

Check the output before you return it

Save the output to a file and run python3 scripts/check-output.py <file>. The contract it checks is scripts/output-contract.json.

• Exit 0, COMPLETE: return the output.
• Exit 2, INCOMPLETE: do not present the output as finished. Fill what you can, run the check again, and if parts stay missing, return the output under the heading Incomplete with every reason the check printed.

Quality bar

• Coverage is reported per field as a share of rows
• Required fields below the needed coverage are flagged with a recommendation
• Band and numeric shapes are distinguished
• A ten row hand check against source sites is included

Related skills

• company-identity-resolution
• icp-fit-scoring
• clay-build-gate

Ships in the clay-operator pack.