Clay to Cargo
Rebuild a Clay table on Cargo — map every Clay enrichment column to its provider action, price the run before it happens, and keep the result as version-controlled code instead of a spreadsheet.
Install clay-to-cargo and follow its SKILL.md, starting from https://api.getcargo.io/INSTALL.md$npx skills add getcargohq/gtm-skills/clay-to-cargoNo account needed to install. A new Cargo account starts with 100 free credits, no card.
Say this to your agent
Rebuild our "Inbound enrichment" Clay table on Cargo — here's the ClayMate JSON export.
Illustrative output #
Fictional records, to show the shape of what comes back.
| Clay column | Cargo action | Clay fill | Cargo fill | Agreement |
|---|---|---|---|---|
| Work Email | prospeo.findEmail → FullEnrich.findEmail | 14 / 20 | 16 / 20 | 13 of 14 |
| Email Valid? | waterfall.verifyEmail | 14 / 14 | 16 / 16 | 13 of 14 |
| Company Industry | companyEnrich.enrichByDomain | 20 / 20 | 19 / 20 | 18 of 19 |
20 sample rows, 6 of them rows Clay left empty, for 23.6 credits end to end (20 × 0.5 + 7 × 1 + 16 × 0.1 + 20 × 0.25); whether that parity is enough to switch is the user’s call.
What it costs #
| Action | Credits |
|---|---|
prospeo.findEmail | 0.5 |
FullEnrich.findEmail | 1 |
waterfall.verifyEmail | 0.1 |
companyEnrich.enrichByDomain | 0.25 |
prospeo.enrichLinkedin | 0.5 |
Never run this across a full list on the first attempt. Sample 10–20 rows from the export, report the observed cost and per-column fill rate, then get the user to approve the full run — quoting the row count and the credit estimate. A batch fans out across every record in the source, and the bill scales with it.
Worth knowing #
- Run the cheap rung across everything, then escalate only the misses — never run both on the full list.
prospeo.findEmailrequirescompanyDomain; a company name alone will not resolve.FullEnrich.findEmailtakesdomainName, notcompanyDomain. The two rungs disagree on the field name, and a copy-paste between them silently resolves nothing.- Clay’s per-row credit and Cargo’s credit are different units. Never compare the two numbers directly — compare what one sample of rows cost end to end on each.