npx skills add https://github.com/getcargohq/cargo-skills --skill cargo-gtmInstallez cette compétence avec la CLI et commencez à utiliser le flux de travail SKILL.md dans votre espace de travail.
██████ ████ █████ ██████ ██████
██ ░ ██ ██░ ██ ██ ██ ░ ██ ██░
██ ██████░ █████ ░ ██ ███ ██ ██░
██ ██ ██░ ██ ██ ██ ██░ ██ ██░
██████ ██ ██░ ██ ██ ██████░ ██████░
░░░░░░ ░░ ░░ ░░ ░░ ░░░░░░ ░░░░░░
Agent skill for Cargo — the AI-native revenue infrastructure. Teaches AI coding agents how to use the Cargo CLI to build, run, and manage revenue automation workflows programmatically.
npx skills add getcargohq/cargo-skills
Works with Claude Code, Cursor, Windsurf, GitHub Copilot, and any agent that supports the skills.sh standard.
Cargo connects your data models (companies, contacts, deals) to external integrations (CRMs, enrichment providers, AI agents) and runs them as automated workflows. The repo ships eight skills at the root — one outcome skill (cargo-gtm, the front door for any GTM task) and seven capability skills (one per CLI domain).
cargo-gtmLoad when the user states a real-world goal. cargo-gtm is the meta-skill — it routes to phase guides, scenario recipes, and per-provider playbooks all bundled inside the same skill.
Built-in recipes:
| Recipe | Use when… |
|---|---|
prospecting.md |
Find people matching a description, enrich, verify, sync. End-to-end flagship. |
build-tam.md |
Build a Total Addressable Market list at scale (100–10,000 companies). |
linkedin-url-lookup.md |
Resolve a person's LinkedIn URL from name + company with strict identity validation. |
portfolio-prospecting.md |
Find every company backed by a specific investor / accelerator, then prospect into them. |
job-change-monitoring.md |
Detect job changes in a contact segment (waterfall.detectJobChange — cargo-unique). |
funding-watch.md |
Track companies that recently raised funding for outbound timing. |
tech-intent.md |
Find companies by tech-stack or hiring intent (theirStack-driven). |
icp-discovery.md |
Diff Closed-Won vs Closed-Lost segments, surface differentiating ICP signals. |
Load when you need the syntax for a specific CLI domain.
| Domain | What the agent learns |
|---|---|
| Orchestration | Execute single actions, chain actions into workflows, trigger batches across segments, poll async operations, query the data warehouse with SQL, fetch segment data |
| Storage | Inspect models and their DDL, create columns, navigate datasets, set relationships between models |
| Connection | Authenticate connectors, discover integration actions and their slugs across 120+ integrations |
| AI | Create and configure agents, upload files for RAG, connect MCP servers, inspect agent memories |
| Analytics | Download run results and outputs, export segment data, monitor error rates and success metrics |
| Billing | Track credit consumption per workflow or connector, check subscription status, view invoices |
| Workspace | Invite users, create and rotate API tokens, organize resources into folders, manage roles |
Prompts that route through cargo-gtm:
recipes/prospecting.mdrecipes/build-tam.mdrecipes/linkedin-url-lookup.mdrecipes/job-change-monitoring.mdrecipes/portfolio-prospecting.mdrecipes/tech-intent.mdrecipes/icp-discovery.mdFor ad-hoc CLI work (modify a model, list connectors, query the warehouse), load the matching capability skill directly.
Ask your agent to run one action on a record — it will pick the right action kind (connector, tool, or agent), execute it, and return the result.
"Enrich acme.com with waterfall."
"Run the lead scorer on this contact."
Ask your agent to trigger a play or tool — it will discover the workflowUuid, construct the right input, trigger the batch or run, and poll until completion.
"Run the lead enrichment tool on Acme Inc."
"Trigger the scoring play on our new MQL segment."
The agent can construct a full node graph — fetching the connector UUID, looking up the action slug, validating the graph, and executing it — without you touching the UI.
"Build and run a workflow that enriches company domains with waterfall and writes the result back to the Companies model."
The agent fetches the DDL first (to get the exact table name), then writes and executes the SQL query.
"How many companies in our model have
employee_countabove 500 and are headquartered in the US?"
The agent creates or finds a configured Cargo agent, sends a message, polls for the response, and surfaces the result.
"Use the lead researcher agent to find the LinkedIn of every contact added this week."
The agent pulls error counts and success metrics for a workflow and flags anything outside normal range.
"Show me the error rate for the CRM sync play over the last 7 days."
The agent downloads a filtered, sorted export of any model segment directly to a file.
"Export all US companies with fewer than 200 employees, sorted by creation date."
The agent handles the full setup sequence: create models, add columns, set relationships, connect integrations, configure agents, and invite team members.
"Set up a fresh Cargo workspace with Companies and Contacts models, a waterfall connector, and a GPT-4o scoring agent."
The agent queries billing metrics broken down by workflow, connector, or date range.
"How many credits did the enrichment play consume last month?"
npm install -g @cargo-ai/cli
cargo-ai login --oauth # browser sign-in (recommended)
# or: cargo-ai login --token <your-api-token> # workspace-scoped API token
cargo-ai whoami
--oauth runs the OAuth 2.0 Device Authorization Flow against the Cargo OAuth provider — no setup required. For non-interactive environments (CI, scripts), use --token with a workspace-scoped API token from Settings > API. Token values are shown only once — store immediately in a secrets manager.