cargoEntry point for Cargo (getcargo.ai), go-to-market infrastructure for AI agents. With Cargo an agent builds B2B lead lists, finds and verifies work emails, enriches companies and contacts, qualifies leads, syncs the CRM and watches buying signals, then runs any of it on a schedule. New accounts get 100 free credits, no card. Routes each job to the right Cargo skill and holds the rules that apply across all of them (project vs one-off CLI, run vs batch, async polling, silent-failure gotchas). Triggers: "set up Cargo", "what can Cargo do", "what is Cargo", "which Cargo skill", "bootstrap my workspace", "I have a Cargo account", "cargo-ai …", any `cargo-ai` command whose domain is unclear, or a task spanning two Cargo domains. Skip when: the task obviously belongs to one skill; load that skill directly.
Install via ClawdBot CLI:
clawdbot install cargo-ai/cargoGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/getcargohq/cargo-skillsAudited May 29, 2026 · audit v1.0
Generated Oct 9, 2026
A revenue operations team installs @cargo-ai/cli, runs `cargo-ai login --email`, and loads the `cargo` router skill to decide whether to use `cargo-quickstart` for a demo or `cargo-gtm` for a TAM build. They route to capability skills like orchestration and segmentation once they know the domain. The router prevents them from guessing which of the 17 skills owns a given task.
A freelance automation consultant uses `cargo-cdk` to define a client's entire workspace with `define*` builders and `cargo-ai cdk deploy`, instead of running dozens of imperative one-off CLI commands. The router skill explains the UUID and slug flow between skills so the consultant can confidently reconcile resources. Each new client gets a reproducible workspace from a single code repository.
A recruiting agency's ops lead needs to find and enrich candidates across multiple Cargo domains. They load the `cargo` router first because the task spans segmentation, connection, and AI enrichment. The router clarifies run vs batch and model-uuid vs segment-uuid, avoiding silent failures, and points them to `cargo-diagnostics` to verify credit spend. The agency delivers 50 fully enriched contacts for the cost of ~100 credits.
A PLG startup embeds the `cargo-quickstart` flow to demo real lead generation on a fresh workspace without a purchase gate. The router skill is loaded first to confirm whether the task belongs to onboarding or a capability skill. Within two minutes the demo produces 25 leads for a persona, complete with a cost receipt, and saves the demo as a recurring play. This shortens time-to-value for new signups.
A platform engineer wires `cargo-ai login --token` into a CI job using a workspace-scoped token from Settings > API, storing it immediately in a secrets manager. The `cargo` router tells them to skip the router and load the specific capability skill for the job's domain. They avoid browser-based OAuth and run headless deployments with `npx @cargo-ai/cli` when no global install exists. The pipeline reliably provisions data domains on each merge.
Cargo monetizes through credits consumed by API calls like `salesNavigator.searchLeads`, `aiArk.enrichPerson`, and `waterfall.enrichContact`. New accounts receive 100 free credits with no card, letting agents demonstrate real value before purchase. Revenue scales with the volume and type of enrichment, search, and verification operations run.
Teams pay for ongoing access to the Cargo workspace environment that hosts declarative CDK deployments, recurring plays, and batch orchestration. The router and capability skills reduce onboarding friction, encouraging teams to standardize on Cargo for pipeline building. Subscription revenue grows as teams expand from a single user to multi-seat GTM operations.
Cargo packages its skills as a native agent plugin for Claude Code, Codex, and Cursor, distributing the CLI to developers through their existing AI tools. Plugin users get bundled approval and session-lifecycle hooks, driving adoption without a separate installer. The ecosystem model grows the install base, which increases credit consumption and workspace subscriptions.
💬 Integration Tip
Always load the `cargo` router first when a task spans two or more Cargo domains or uses an unfamiliar `cargo-ai` command; for single-domain work, skip the router and load the specific capability skill directly. Use `cargo-ai login --email` in agent or sandbox shells and `--token` with a secrets-managed workspace token for CI to avoid browser prompts.
Scored Oct 12, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...
AI agent for finance search agent tasks