getcargohq

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.

Turn something heard in the field into durable context, at the right confidence level. Use when the user relays an objection, a competitor mention, a win or loss reason, a signal, or any claim from a call, and asks to remember it. Enforces the repetition rule and the confidence ladder.

Audit and repair the context layer. Use when asked to clean up context, before a quarterly review, or when the knowledge graph feels stale. Finds missing frontmatter, broken references, orphan files, and stale content, then fixes them file by file.

How this GTM repository works. Load when orienting in this repo, deciding where a change belongs, or explaining the layer conventions to someone. Covers the layers, the dependency direction, the PR workflow, the confidence ladder, and where each kind of change goes.

Write today's entry in the cadence log. Use at the end of a working day, or when the user recaps what happened. Captures what moved, what is stuck, and anything worth remembering, then routes stuck items to carryover and repeated observations toward context.

Scaffold a new GTM motion end to end across all three layers. Use whenever creating a new motion, campaign, play, or automation in this repo, so the narrative (context), the implementation (infra), and the regression suite (evals) ship together and never drift apart. Enforces the outreach hypothesis rule.

Plan the coming week in the cadence layer. Use every Monday, or whenever asked what this week should focus on. Pulls from plan/ and open initiatives/, carries over unresolved items, and writes cadence/weekly/YYYY-Www.md. Escalates anything that has slipped three weeks into a decision instead of a task.

Digest the outputs archive into durable context. Use for the weekly GTM review, or whenever asked what happened recently and what we learned. Reads recent outputs entries, summarizes results, and proposes context updates as a PR. This is the repo's memory flywheel.