Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →gooseworks-ai/tam-builder
Build and maintain a scored Total Addressable Market (TAM) using Apollo Company Search. Discovers companies matching ICP, scores fit (0-100), assigns tiers (1/2/3), and auto-builds a persona watchlist for Tier 1-2 companies using Apollo People Search (free). Outputs to CSV.
Passed 17 of 23 test cases with the skill, and 7 of 23 without it.
and 11 more in the full report
11 fixed7 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our pipeline runner supports test, standard, and full execution modes. What are the maximum page count and total company caps for standard mode versus full mode?
| Checked | Without skill | With skill |
|---|---|---|
| applies max 50 pages and 5,000 companies for standard mode | Missed | Passed |
| applies max 200 pages and 20,000 companies for full mode | Missed | Passed |
The instructions your model reads when the skill loads.
Build and maintain a scored Total Addressable Market. Uses Apollo Company Search to discover companies, scores ICP fit (0-100), assigns tiers (1/2/3), and auto-builds a persona watchlist for Tier 1-2 companies using Apollo People Search (free).
Three modes:
Add to .env:
APOLLO_API_KEY=your-api-key-here
That's it — one env var.
Create a JSON config per client/segment:
{
"client_name": "happy-robot",
"tam_config_name": "voice-ai-midmarket",
"company_filters": {
"organization_num_employees_ranges": ["51,200", "201,500", "501,1000"],
"q_organization_keyword_tags": ["call center", "contact center"],
"organization_locations": ["United States"]
},
"scoring": {
"weights": {
"employee_count_fit": 30,
"industry_fit": 25,
"funding_stage_fit": 20,
"geo_fit": 15,
test cases passed, vs 7 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.