cargo-gtm Skill for Claude Code: B2B Lead Lists, Enrichment and Outreach Prep

Makes Claude build B2B lead lists, enrich and verify contacts through Cargo, score leads and draft outreach, with a sample and cost check first.

Installs: 10.6K; on skills.sh
Stars: 21; on GitHub
Files: 60+; besides SKILL.md
Updated: Oct 2026; last repo commit

When you state a go-to-market goal, Claude opens the matching one of 19 recipes (prospecting, TAM lists, job-change and funding monitoring, tech-intent, outreach activation, ad audiences and more), runs a 10 to 20 record sample, and shows the credit cost before any full run. Costs come from credits-based data providers that Cargo calls, and SKILL.md leads with seven of them.

It never sends messages. Outreach recipes stop at send-ready copy for your own sequencer. SKILL.md says it refuses bulk unsolicited messaging, purchased or scraped lists, consumer targeting and filter evasion, and requires a consent basis and a suppression check before outreach.

Good for

Sales and RevOps teams building prospect lists and verified contacts
Growth marketers sizing a market or pushing audiences to ad platforms
Founders running outbound research without a data team
GTM engineers who want repeatable plays instead of spreadsheets

Install cargo-gtm

Claude Code

Copy this prompt.

Install the cargo-gtm skill in Claude Code. Run this command:

/plugin marketplace add getcargohq/cargo-skills
/plugin install cargo@cargo-skills

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Every Cargo skill drives the cargo-ai CLI, so install it and sign in first. A new account starts with 100 free credits and no card (README). Pick one channel, not two: the plugin and skills add both register the skills, so using both duplicates them. The whole bundle is the route the README documents; this skill's own files point to files in sibling skills such as ../cargo/references/prerequisites.md. The plugin needs Claude Code 2.1.154 or newer and adds hooks and two subagents; see the safety section.

From the project README. Source.

What's in the skill

When it loads

Do business-to-business go-to-market work on Cargo — research accounts and buying committees, enrich and verify B2B contact records from licensed data providers, score and qualify leads, draft permission-based outreach for the user's own sequencer, sync to CRM, and monitor buying signals. Consent basis, suppression lists, and volume limits gate every step that touches a person (`references/acceptable-use.md`); bulk unsolicited messaging, purchased or scraped lists, and consumer targeting are refused. Triggers: "build me a list of", "find 50 <title> at <segment>", "who works at", "find work emails for these accounts", "enrich this CSV", "verify these emails", "build a TAM", "who fits our ICP", "who actually buys from us", "what data points should we collect on accounts", "our outbound is reaching the wrong people", "score these leads", "write a first-touch email", "push these to my CRM", "who changed jobs", "who just raised funding", "companies using <tech>", "who is hiring <role>", "find the buying committee", "portfolio companies of <investor>", "upload this audience to Google/Meta/LinkedIn ads". Providers: aiArk, anthropic, apolloio, bounceban, bouncer, brightData, builtwith, cargoSignals, cleon1, companyEnrich, contactOut, datagma, dropcontact, enrichCrm, enrichley, enrowio, exa, explorium, findyMail, firecrawl, forager, FullEnrich, g2, gemini, hunter, icypeas, kitt, leadMagic, linkedin, linkup, mixrank, neverBounce, oceanio, openAi, parallel, peopleDataLabs, perplexity, piloterr, pipecorn, prospeo, proxycurl, reverseContact, rocketreach, salesNavigator, serper, sillage, snitcher, societeInfo, storeleads, theirStack, theSwarm, typesafe, waterfall, x, zeroBounce. Reads phase guides, recipes, and per-provider playbooks before any paid call. Skip when: a run already happened and misbehaved — use cargo-diagnostics.

Sections in SKILL.md

Acceptable use — MANDATORY, before anything that touches a person
Bootstrap
1) What this skill governs
Process / goal
Documentation hierarchy
2) Read behavior — MANDATORY before any execution
Routing rules — match your task to a doc and READ IT
Recipes: step-by-step playbooks (check before executing)
3) Cost discipline — MANDATORY gates
4) After every run — receipt, then grounded next steps
5) Priority provider stack (recipes lead with these 7)
6) Recipe spine (default chain)
7) Output retrieval — use run download-outputs, not run download
8) Contact accuracy — run the QA scripts, don't eyeball
9) Action shape rules (every recipe)
10) When stuck — file a workspace report

Key facts

Author: Cargo (frontmatter author: getcargo), in the vendor's own repo
License: MIT (LICENSE, README badge and plugin.json agree)
Version: 2.6.0
Installs on skills.sh: 10,557 (Nov 2, 2026)
GitHub stars: 21 (Nov 2, 2026)
Last commit: Oct 31, 2026
What installs: 105 files including SKILL.md: 19 recipes, 55 provider playbooks, 3 guides, 15 references, 2 agent specs and 9 files in scripts (4 scripts, 1 shared library, 4 test fixtures)
Needs: The cargo-ai CLI (npm) and a Cargo sign-in; a new account starts with 100 free credits
Cargo CLI license: UNLICENSED on npm; the skills bundle itself is MIT
Bundle size: README and plugin manifests say 19 skills, the skills.sh badge says 18, and the repo has 20 skill folders including a redirect stub
Works in: Claude Code, Codex, Cursor, Windsurf, GitHub Copilot, Hermes Agent and other skills.sh agents

What it includes

Checks basis, suppression and relevance before any step that touches a person.
Acceptable-use gate
Installs the CLI, signs in and confirms the workspace before any write.
Runs code · Bootstrap
Three guides: finding companies and contacts, enriching and researching, writing outreach.
Phase guides
Nineteen step-by-step playbooks from source planning to clay-to-cargo migration.
Runs code · Recipes
Sample, approval, then full run; a receipt with credits, balance and hit-rate after each.
Runs code · Cost discipline
Ends each run with two or three steps computed from the data just produced.
Next steps
Seven lead providers, from salesNavigator to peopleDataLabs, with credit costs.
Network · Provider stack
Eight-step default chain: source, dedupe, enrich, signal, contact, verify, backfill, QA.
Runs code · Recipe spine
Uses run download-outputs to get a signed link to just the output node data.
Runs code · Output retrieval
Four local Node scripts for email checks, current role, name match and a final audit.
Runs code · Contact accuracy scripts
Rules for writing action JSON so inputs are not silently stripped.
Action shape rules
Files a report to the Cargo team when a recipe fails repeatedly.
Runs code · Workspace report
Two agent specs for costed plans and pre-approved sourcing slices.
Planner and list-builder agents

From the official docs

Permissions

Medium risk

It spends Cargo credits and works with personal contact data. Cap the credits in each approval message and only contact people you have a basis to reach.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

It spends credits through data providers
Enrichment, verification and phone lookups bill per record. SKILL.md requires a 10 to 20 record sample and an approval message with the record count and credit estimate before a batch. github.com
It handles contact data about third parties
Recipes enrich names, emails, phone numbers and LinkedIn profiles. SKILL.md requires a consent basis and a suppression check before outreach and refuses scraped or purchased lists. github.com
Claude runs the cargo-ai CLI as you
The skill drives the cargo-ai CLI. Sign-in is saved to ~/.config/cargo-ai/credentials.json, and the docs say to confirm the workspace with cargo-ai whoami before any write. github.com
The plugin route adds hooks that run shell commands
The plugin wires a PreToolUse hook on Bash that auto-approves safe cargo-ai calls, and a SessionStart hook that runs npm install -g @cargo-ai/cli at the pinned version. Login, token creation, report creation, project deploy and any remove or delete still prompt. github.com
The plugin sends a session summary to your Cargo workspace
The SessionEnd hook passes the last 60,000 bytes of the transcript to claude -p to write a title and summary, then stores them in your Cargo workspace session record. Use the skills CLI route if you do not want that. github.com
Local scripts read files and Cargo credentials
The four scripts write output files. When given a workflow id, the shared library reads CARGO_API_TOKEN or ~/.config/cargo-ai/credentials.json, loads @cargo-ai/api and downloads a signed output link. github.com
Failed recipes can file a report to Cargo
After repeated failures SKILL.md tells Claude to file a report with cargo-ai workspaceManagement report create. Read it before it is sent, because reports can carry session details. github.com
The plugin also adds two subagents
cargo-execution-planner and cargo-list-builder run on the haiku model with Read, Grep, Glob and Bash tools. The planner is described as read-only and the list builder as executing only pre-approved slices. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Talks to	api.getcargo.io (Cargo API). registry.npmjs.org (CLI install). app.getcargo.io (token creation)
Sign-in and keys	Sign-in by emailed code, browser (OAuth) or an API token. Browser and email sign-in save a session to ~/.config/cargo-ai/credentials.json; API tokens are workspace-scoped and the README says to store them in a secrets manager.
Scopes	Runs cargo-ai commands that spend credits on data providers Runs four local Node scripts that write output files Cargo workspace sign-in (saved in ~/.config/cargo-ai/credentials.json)

Questions

What does cargo-gtm do?

It makes Claude do B2B go-to-market work through Cargo: find companies and people, enrich and verify contacts, score leads, draft outreach copy and sync results to a CRM. It reads a matching recipe first and tests a small sample before spending.

What does it cost?

Credits, set by the data provider actions it runs. SKILL.md gives examples such as 0.2 credits per sourced lead, 0.1 per email check, 2 per full contact enrichment, and 3 to 7 for a phone escalation. A new Cargo account starts with 100 free credits and no card.

Will it send emails for me?

SKILL.md says it never sends. Outreach recipes stop at send-ready variables for your own sequencer. Sending from a Cargo-owned mailbox is handled by a different skill, cargo-mailbox-management.

What will it refuse?

SKILL.md names undifferentiated fan-out such as emailing everyone in an industry, contacting a suppressed record, filter evasion, auto-dialing and SMS blasts, batch LinkedIn engagement and automated posting from your X account.

cargo-gtm or cargo-quickstart?

Use cargo-quickstart for a guided first demo. cargo-quickstart's own file says to switch to cargo-gtm for any real job such as building a list or enriching a CSV.

Does it need Node for the scripts?

Yes for the four accuracy scripts. SKILL.md says they are TypeScript for Node 22.18 or newer with zero dependencies. Run on a finished run, one of them also needs the @cargo-ai/api package and your Cargo credentials.

How do I install it?

Use the install box above. Install the whole Cargo bundle, then the Cargo CLI and sign in. The README says to pick one channel, plugin or skills add, not both.

Is it official?

Yes. It sits in Cargo's own repo (getcargohq/cargo-skills), the LICENSE names Cargo as the copyright holder and the plugin manifest lists Cargo as the author.

Does it work in the Claude app, Codex or Cursor?

The README names Claude Code, Codex, Cursor, Windsurf, GitHub Copilot and Hermes Agent. For Claude Desktop it documents a Claude Cowork plugin route with network egress turned on. The skill drives a local CLI, so there is no plain Claude app skill upload here.

Is it safe to use?

It spends Cargo credits and handles contact data about third parties. SKILL.md gates this with a sample-then-approve rule, a receipt after each paid action and an acceptable-use check, and its accuracy scripts write output files. Our advice: set a credit ceiling in the approval message and keep outreach to people you have a basis to contact.

Information

updated Nov 2, 2026

Repository: getcargohq/cargo-skills
Folder: cargo-gtm

getcargohq/cargo-skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 8

cargo-skills README · github.com
cargo prerequisites.md · github.com
cargo-gtm SKILL.md · github.com
cargo-gtm scripts/lib/common.ts · github.com
cargo-skills LICENSE · github.com
cargo-skills plugin.json · github.com
session-end.sh · github.com
session-start.sh · github.com