cargo-skills

Create and configure AI agents, attach knowledge for RAG, manage MCP servers, and handle agent memories using the Cargo CLI. Use when the user wants to create or update agents, configure agent releases, connect MCP tool servers, or manage agent memories. To upload knowledge files or build knowledge libraries, use the cargo-content skill. For sending messages to agents, use the cargo-orchestration skill instead.

Manage workspace knowledge files and libraries in the Cargo content domain — upload, list, rename, move, and remove files (PDFs, CSVs, text), and create or sync native and connector-backed libraries for retrieval-augmented generation (RAG). Use when the user wants to upload or organize knowledge files, build a knowledge library, or sync an external knowledge source. To attach these to an agent, use the cargo-ai skill.

Front door for any GTM task on Cargo — sourcing, waterfall enrichment, email/phone/LinkedIn lookup, email verification, scoring, qualification, sequencing, CRM sync, and signal monitoring (job changes, funding, tech-stack/hiring intent). Use when the user states a real-world goal involving prospects, leads, accounts, contacts, ICP lists, or campaign activation. Routes to phase guides (Level 2), recipes (Level 2.5), and per-provider playbooks (Level 3) before any action call.

Interact with the Cargo platform via CLI. Use when the user wants to execute an action, run a workflow, trigger a batch, message an AI agent, query orchestration runtime tables (runs/batches/spans/records) with SQL, fetch segment records, resolve an action's output schema, or inspect a model schema.

Router and overview for the Cargo CLI agent skills. Explains the fifteen skills (this router + one onboarding skill cargo-quickstart + one outcome skill cargo-gtm + twelve capability skills, including cargo-cdk for declarative workspace-as-code and cargo-diagnostics for run/batch/cost forensics), when to use the declarative CDK vs the imperative CLI, the UUID flow between them, async polling, end-to-end use cases (enrich one record, enrich and sync to CRM, AI lead scoring, custom workflow, error monitoring, fresh-workspace bootstrap, segment export, GTM context authoring), and common gotchas (`conjonction` spelling, run vs batch, model-uuid vs segment-uuid). Load first whenever working with the Cargo CLI, when unsure which sub-skill applies, when stitching multiple sub-skills together, when bootstrapping a workspace, or when the user asks about Cargo skills in general.

Manage workspace users, API tokens, folders, roles, and submit reports to workspace management using the Cargo CLI. Use when the user wants to invite or manage workspace members, create or rotate API tokens, organize resources into folders, inspect workspace roles and permissions, or submit a report to workspace management when the CLI fails or is misused.

Manage models, datasets, columns, and relationships and query workspace storage with SQL using the Cargo CLI. Use when the user wants to inspect or modify data models, create or update columns, list datasets, set model relationships, understand the schema, or run SQL against storage.

Download workflow run results, export segment data, and monitor run metrics using the Cargo CLI. Use when the user wants run metrics, error rates, data export, or download results for their Cargo workspace. For billing and credit usage, use the cargo-billing skill instead. For explaining WHY a run failed or a batch has errors, use the cargo-diagnostics skill instead.

Pull usage metrics, check subscription status, view invoices, and manage credits using the Cargo CLI. Use when the user wants billing analytics, usage reports, credit usage, cost analysis, subscription details, or invoice history for their Cargo workspace.

Define an entire Cargo workspace in code — connectors, models, plays, tools, agents, MCP servers, context, capacities, territories, segments, folders, files, workers, apps — and deploy it declaratively with `cargo-ai cdk` (init → types → plan → deploy), the way you'd manage cloud infra with Pulumi or the AWS CDK. Use when the user wants to manage Cargo resources as code: reproducibly, version-controlled, in git, from a template, or across environments. Routes to authoring/deploy/typing guides (Level 2), recipes (Level 2.5), and references. For one-off imperative operations (create one connector, read a model, run a workflow), use the matching capability skill instead.

Manage connectors and integrations using the Cargo CLI. Use when the user wants to list, create, update, or remove connectors, discover available integrations, or understand what connector actions are available for use in workflows.

Inspect and edit the workspace's git-backed context repository (the GTM knowledge base of markdown/MDX files) and its runtime sandbox using the Cargo CLI. Use when the user wants to browse/read/write/edit context files, run a command in the sandbox, or inspect the context knowledge graph.

Diagnose and explain Cargo workflow behavior after the fact — trace why a single run produced the wrong output, sweep a batch or play for errors and group them by root cause, and profile where a play's credits go and how to cut the cost. Use when a run failed or "succeeded but looks wrong", a batch has errors, records are missing downstream values, or a play costs more than expected.

Build, deploy, and manage Cargo Hosting apps and workers with the Cargo CLI — Vite SPAs served on *.cargo.app and serverless edge HTTP handlers, plus the deployments that ship and promote them. Use when the user wants to scaffold, deploy, promote, or manage a hosted app or worker on Cargo.

Guided first-run demo for the Cargo CLI — from a fresh workspace to a real deliverable (25 leads matching the user's buyer persona, with a cost receipt) in under two minutes, ending by saving the demo as a recurring play. Use when the user is new to Cargo, asks for a demo/tour/quickstart, or has an empty workspace and wants to see what the CLI can do. For real GTM work beyond the demo, route to cargo-gtm.