Office hours: Build your self-driving GTM engine·Oct 29, 9:00am PT, onlineRegister→
Cargo
  • PrimitivesData ModelsYour companies, contacts and deals, merged from every sourceContextWhat your team knows, as files every agent readsTerritoriesWho sells where, defined onceMailboxesMailboxes in your reps' names, warmed up and kept under limitsToolsThe actions your agents, plays and reps callAgentsAI that researches, decides and writes, reading your contextPlaysWorkflows that run on a trigger or a schedule, with retriesAppsInternal apps for your reps, hosted on Cargo
    Add-onsChrome ExtensionSell faster, right in your browserButtonTrigger AI agents inside your CRMFormTurn any tool into an embeddable formSlackTag Cargo in Slack. It does the GTM workGitHubPlan on every pull request, deploy on merge
    MoreProjectsDefine your entire GTM in codeCLIUse Cargo from your terminalMCPUse Cargo from Claude and ChatGPTDeveloper resourcesCargo API docs, OpenAPI spec, auth docs, webhooks, MCP serverAPI ReferenceExplore the Cargo APIDocumentationLearn how to use CargoIntegrationsConnected to your entire GTM stack
  • VeriffHow Veriff replaced MuleSoft with Cargo under NetSuite, Stripe and SalesforceAugmentHow Augment Code routes developer sign-ups to reps in under an hourWeights & BiasesHow Weights & Biases ships a new purchase signal in 2 days on CargoSee all
  • Pricing
  • Cookbooks
  • Blog
Sign in
Skills
SLDecide who is worth the time · One-off

Score leads

Score a list of companies against your ideal customer profile and rank them — every row gets a number, the reason behind it, and a tier, so the bottom of the list can be dropped before anyone spends time on it.

Installation
Install score-leads and follow its SKILL.md, starting from https://api.getcargo.io/INSTALL.md
Paste it into Claude Code, Cursor, Codex, Gemini CLI, Devin or Replicas.
$npx skills add getcargohq/gtm-skills/score-leads
Run it in your project. Adds the skill for your coding agent.

No account needed to install. A new Cargo account starts with 100 free credits, no card.

Say this to your agent

Score the 20 companies in `webinar-accounts.csv` against our ICP: 50–500 employees, B2B software, US or UK, competitors out.

Illustrative output #

Fictional records, to show the shape of what comes back.

domainscoretierreasonmissing
northwind.example92A240 staff, B2B software, US
tailspin.example61BB2B software, UK; 85 staff is small but inside range
globex.example0—disqualified: competitor
umbrella.exampleunrankedheadcount, industry

20 enriched for 5 credits (20 × 0.25): 4 tier A, 8 tier B, 5 tier C, 1 disqualified, 2 unranked for missing data.

What it costs #

ActionCredits
companyEnrich.enrichByDomain0.25

Never run this across a full list on the first attempt. Sample 10–20 rows, report the observed cost and the score distribution, then get the user to approve the full run — quoting the record count and the credit estimate. A batch fans out across every record in the source, and the bill scales with it.

Show the distribution with the sample, not just the cost. If every row lands in one tier the criteria are not discriminating, and that is worth finding out at 20 rows rather than at 2,000.

Worth knowing #

  • enrichByDomain needs a domain, not a company name. A list carrying only names has to be resolved first, and that is a different job: say so rather than sending names and reporting the misses as bad fits.
  • Scoring is deterministic and free. Keep it that way: an LLM asked to “rate fit” produces a number nobody can reproduce or argue with.
  • Re-scoring after the criteria change costs nothing, because the enrichment is already stored. Say so, because users assume otherwise and under-ask as a result.
  • Richer firmographics exist at a higher tier if a criterion genuinely needs them. Reach for one only when a stated criterion cannot be answered from the fields above, never by default.
Version1.0.4
LicenseMIT
Source
For
  • RevOps
  • Sales development
Integrations
  • CompanyEnrich
Content
  • Say this to your agent
  • Illustrative output
  • What it costs
  • Worth knowing
Decide who is worth the time
  • Research account

Build the self-driving GTM engine

Your coding agents build it on Cargo.Or our team builds, operates and improves it with you.

Start building
Cargo
Backed byY CombinatorSOC 2 Type IICertified
LinkedinX

Product

Data ModelsContextTerritoriesMailboxesToolsAI AgentsPlaysAppsIntegrationsPricing

Add-ons

Chrome extensionButtonFormSlackGitHub

Build

DocsDeveloper resourcesCargo API docsCargo OpenAPI specCargo auth docsCargo webhooksCargo MCP serverProjectsClaude CodeCodexCursorAll coding agents

Resources

ReportsBlogCustomer storiesCookbooksEnrichmentRoutingSignalsScoringCRM hygieneAd audiencesGTM skillsGTM EngineeringGlossaryCompareCargo x ClayCargo x WorkatoCargo x n8nCargo x DeeplineCargo x DefaultCargo x LeanDataCargo x UnifyCargo x ValleyCargo x GojiberryCargo x PhantomBusterCargo x ZapierCargo x ApolloCargo x Chili PiperCargo x Common RoomCargo x MakeCargo x Tray.io

Company

ManifestoCommunityEventsJobsPartners DirectoryPartner Program

Legal

SecurityTerms of servicePrivacy PolicyRefundsDPASupport
© 2026 Cargo
 ////////    ///////    ////////     ////////    ///////
///         ///   ///   ///   ///   ///         ///   ///
///         ///   ///   ///   ///   ///         ///   ///
///         /////////   ////////    ///  ////   ///   ///
///         ///   ///   /// ///     ///   ///   ///   ///
///         ///   ///   ///  ///    ///   ///   ///   ///
 ////////   ///   ///   ///   ///    ///////     ///////

$ npm install -g @cargo-ai/cli