Monitor buying signals
Watch a list of target accounts for the public events that mean someone is in market — hiring for the role you sell into, saying something new, or turning up in a detection feed, each with a date and a link.
Install monitor-buying-signals and follow its SKILL.md, starting from https://api.getcargo.io/INSTALL.md$npx skills add getcargohq/gtm-skills/monitor-buying-signalsNo account needed to install. A new Cargo account starts with 100 free credits, no card.
Say this to your agent
Watch our 20 open-opportunity accounts and tell me which started hiring RevOps in the last 30 days.
Illustrative output #
Fictional records, to show the shape of what comes back.
| account | signal | date | source | so_what |
|---|---|---|---|---|
| Northwind | Posted “Head of Revenue Operations” | 2026-09-21 | jobs.northwind.example/revops-head | The owner of our deal’s process is about to change |
| Fabrikam | CEO post on consolidating GTM tools | 2026-09-15 | x.com/fabrikam_example/status/1 | Budget is being cut elsewhere; lead with consolidation |
| Tailspin | Posted “RevOps Analyst” | 2026-09-08 | jobs.tailspin.example/revops-analyst | A team is being built under our champion |
3 of 20 accounts fired and the other 17 are not listed; 2.1 credits (sillage free on all 20, 4 job posts × 0.5, 5 X lookups × 0.02).
What it costs #
| Action | Credits |
|---|---|
sillage.searchLeads | 0 |
theirStack.searchJobs | 0.5 per job returned |
x.getUserPosts | 0.02 |
Never run this across a full list on the first attempt. Sample 10–20 accounts, report the observed cost and how many actually fired, then get the user to approve the full run — quoting the account count and the credit estimate. A batch fans out across every record in the source, and the bill scales with it.
The fire rate from the sample is the number that matters more than the cost. If two accounts in twenty fired, a weekly run over 500 accounts is worth it. If none did, the triggers from step 1 are wrong and running wider will not fix that.
Worth knowing #
- The free rung is not optional.
sillage.searchLeadscosts 0, so running it first is a pure saving. It needs amodelUuid, which is a setup step rather than a retry if detections are not being delivered yet. theirStack.searchJobstakes domains ascompanyFields.company_domain_orand titles asfields.job_title_or(job_title_pattern_orfor partial matches). Keys outside its schema (company_domains,job_titles, a top-leveldomain) are refused before the run starts (Unknown field: …); inside a workflow node they are dropped silently instead, so the search returns an unfiltered page and bills 0.5 for every job in it.- Confirm an X handle from the company’s own site. Squatted and parody handles resolve fine and return confident nonsense.
- Engagement lists (followers, likers, retweeters) are not part of this skill. People who engaged with a post did not ask to hear from you, and building a send list from them is the thing the basis test above exists to stop.
- Re-running on a schedule is where the cost lives. Gate on accounts whose last check is older than the interval, or every run re-bills accounts that did nothing.