Skills로 돌아가기
getcargohq/cargo-skills실행 전 동작 확인

SKILL DETAIL

cargo-connection

getcargohq/cargo-skills/cargo-connection

The cargo-connection skill manages connections between Cargo and external systems. It allows you to list authenticated connectors, browse the available integration catalog, and obtain the connectorUuid and actionSlug required for workflow nodes. The skill supports a wide range of integrations, including HubSpot, Salesforce, Clearbit, and more, and provides functionality for creating, updating, deleting, and autocompleting connectors. Using this skill, you can leverage cargo-ai CLI commands to manage connectors and integrations, such as listing all connectors, searching for integrations, retrieving action lists for specific integrations, and fetching autocomplete options for fields that require dynamic values. The skill includes detailed examples and reference documentation to assist in configuring workflow nodes.

설치 수 · 135출처 보기

Installation

npx skills add https://github.com/getcargohq/cargo-skills --skill cargo-connection

스킬 파일

SKILL.md

최근 동기화 · 2026. 8. 29.

references/examples/connectors.md
# Connector examples

## List all connectors

```bash
cargo-ai connection connector list
```

## Filter connectors by integration

```bash
cargo-ai connection connector list --integration-slug clearbit
# → Returns only connectors for the Clearbit integration
```

## Get a single connector

```bash
cargo-ai connection connector get <connector-uuid>
# → Returns the full connector object (same shape as an item from connector list)
```

## Find a connector UUID for use in a workflow

```bash
# 1. List connectors (optionally filter by integration)
cargo-ai connection connector list --integration-slug clearbit
# → Extract the "uuid" field from the right connector

# 2. Use the UUID in your workflow node's connectorUuid config
```

## Create a connector

```bash
cargo-ai connection connector create \
  --integration-slug clearbit \
  --slug clearbit_production \
  --name "Clearbit - Production"
```

`--slug` is a unique identifier (no spaces), `--name` is the display name. For credit-based integrations (`useCredits: true`), this is all that's needed. For credential-based integrations, pass `--config` with the integration-specific credentials JSON.

## Update a connector

```bash
cargo-ai connection connector update --uuid <connector-uuid> --name "Clearbit - Staging"
cargo-ai connection connector update --uuid <connector-uuid> --config '{"apiKey":"new-key"}'
```

## Remove a connector

```bash
# Check usage first — list connectors and check playsCount and toolsCount
cargo-ai connection connector list
# → High counts mean the connector is heavily used — remove dependencies before deleting

cargo-ai connection connector remove <connector-uuid>
```

## Check if a slug is available

```bash
cargo-ai connection connector exists-by-slug --slug clearbit_production
# → { "exists": true }
```

## Connector usage audit

Find all connectors and how many plays/tools use each:

```bash
cargo-ai connection connector list
# → Check playsCount and toolsCount fields for each connector
```

## Autocomplete — fetch available values for an action field

When an action's `uiSchema` marks a field with `"ui:widget": "IntegrationAutocompleteWidget"`, use `connector autocomplete` to get the allowed values.

```bash
# Basic autocomplete (no params needed)
cargo-ai connection connector autocomplete \
  --connector-uuid <connector-uuid> \
  --slug listObjects \
  --params '{}'
# → { "results": [{ "label": "Contacts", "value": "contacts" }, ...] }
```

## Autocomplete with dependent parameters

Some fields depend on another field's value. Pass the dependency in `--params`:

```bash
# Get properties for a specific object type
cargo-ai connection connector autocomplete \
  --connector-uuid <connector-uuid> \
  --slug listObjectProperties \
  --params '{"objectType": "contacts"}'
# → { "results": [{ "label": "Email", "value": "email" }, ...] }
```

## Autocomplete with search filtering

Use `--value` to filter results by a search string:

```bash
cargo-ai connection connector autocomplete \
  --connector-uuid <connector-uuid> \
  --slug listObjectProperties \
  --params '{"objectType": "contacts"}' \
  --value "email"
# → Returns only properties matching "email"
```

## Autocomplete with cache refresh

Results are cached (default 30 minutes). Use `--refresh` to bypass the cache:

```bash
cargo-ai connection connector autocomplete \
  --connector-uuid <connector-uuid> \
  --slug listObjects \
  --params '{}' \
  --refresh
```

## Rate limit awareness

Some connectors have rate limits (visible in the `rateLimit` field from `connector list`):

```bash
cargo-ai connection connector list
# → Check rateLimit.unit (day/hour/minute) and rateLimit.max for each connector
# → Design batches to stay within these limits
```
references/examples/integrations.md
# Integration examples

## List all available integrations

```bash
cargo-ai connection integration list
```

Response includes `slug`, `name`, `description`, and `category` for each available integration.

## Filter integrations

```bash
# By category
cargo-ai connection integration list --category enrichment

# By name search
cargo-ai connection integration list --search "hubspot"

# By exact slug(s)
cargo-ai connection integration list --slugs clearbit

# Only those with actions (usable in workflow nodes)
cargo-ai connection integration list --has-actions true

# Only those with extractors (can sync data into models)
cargo-ai connection integration list --has-extractors true
```

**Categories:** `engagement`, `marketing`, `sales`, `finance`, `analytics`, `freeform`, `success`, `support`, `enrichment`, `storage`, `custom`.

## Find an integration slug

```bash
cargo-ai connection integration list --search "hubspot"
# → Extract the "slug" value
# → Use slug when creating connectors: --integration-slug <slug>
```

## Get full integration details

```bash
cargo-ai connection integration get clearbit
# → Returns the full integration object with actions, extractors, and configuration schemas
```

Use this to discover all available actions and extractors for an integration, including their `config.jsonSchema` for building workflow nodes.

## Get integration documentation

```bash
cargo-ai connection integration get-documentation clearbit
cargo-ai connection integration get-documentation hubspot
```

Returns plain text documentation for the integration, including available actions and their configuration.

## Discover actions for a specific integration (e.g. HubSpot)

```bash
cargo-ai connection integration get hubspot
# → Returns HubSpot-specific actions (e.g. "create_contact", "update_deal") and extractors
# → Each action includes its config.jsonSchema for building workflow nodes

cargo-ai connection integration get-documentation hubspot
# → Plain text overview of all HubSpot actions
```

**Use `integration get <slug>` when you need service-specific actions** — HubSpot, Salesforce, Clearbit, etc.

## Discover native (built-in Cargo) actions and extractors

```bash
cargo-ai connection native-integration get
# → Returns built-in Cargo actions ONLY — NOT HubSpot or other third-party actions
# → actions: keyed by actionSlug (generic platform utilities)
# → extractors: keyed by extractor slug
```

**Important:** `native-integration get` does **not** return HubSpot-specific or other third-party connector actions. To get those, use `integration get <slug>` instead.

Use `actionSlug` values in workflow node configs (see `cargo-orchestration/references/nodes.md`).

## Set up a connector for use in workflows (full flow)

```bash
# 1. Find the integration slug
cargo-ai connection integration list --search "hubspot"
# → Extract the "slug" value

# 2. Create the connector
cargo-ai connection connector create \
  --integration-slug hubspot \
  --slug hubspot_production \
  --name "HubSpot - Production"
# → Note the returned connector UUID

# 3. Get the integration details to discover available actions
cargo-ai connection integration get hubspot
# → Or get plain text docs: cargo-ai connection integration get-documentation hubspot

# 4. Use the connector UUID and action slug in a workflow node
# See cargo-orchestration references/nodes.md for node syntax
```

## Common integration slugs

| Service       | Slug           |
| ------------- | -------------- |
| Clearbit      | `clearbit`     |
| HubSpot       | `hubspot`      |
| Salesforce    | `salesforce`   |
| Apollo.io     | `apolloio`     |
| HTTP (custom) | `http`         |
| Slack         | `slack`        |
| Google Sheets | `googleSheets` |

Run `integration list` for the complete current list.
references/response-shapes.md
# Response shapes

JSON response structures returned by Cargo CLI commands used in the `cargo-connection` skill.

## cargo-ai connection connector list

```json
{
  "connectors": [
    {
      "uuid": "connector-uuid",
      "workspaceUuid": "...",
      "userUuid": "...",
      "name": "Clearbit - Production",
      "slug": "clearbit_production",
      "integrationSlug": "clearbit",
      "rateLimit": { "unit": "day", "max": 1000 },
      "cacheTtlMilliseconds": 86400000,
      "playsCount": 2,
      "toolsCount": 5,
      "modelsCount": 0,
      "useCredits": true,
      "config": null,
      "createdAt": "2025-01-01T00:00:00Z",
      "updatedAt": "2025-01-15T00:00:00Z",
      "deletedAt": null
    }
  ]
}
```

**Key fields:** `uuid`, `name`, `integrationSlug`, `useCredits`, `playsCount`, `toolsCount`.

When `useCredits` is `true`, actions on this connector consume Cargo credits. When `false`, `config` contains the integration-specific credentials.

## cargo-ai connection connector get

```json
{
  "connector": {
    "uuid": "connector-uuid",
    "workspaceUuid": "...",
    "userUuid": "...",
    "name": "Clearbit - Production",
    "slug": "clearbit_production",
    "integrationSlug": "clearbit",
    "rateLimit": { "unit": "day", "max": 1000 },
    "cacheTtlMilliseconds": 86400000,
    "playsCount": 2,
    "toolsCount": 5,
    "modelsCount": 0,
    "useCredits": true,
    "config": null,
    "createdAt": "2025-01-01T00:00:00Z",
    "updatedAt": "2025-01-15T00:00:00Z",
    "deletedAt": null
  }
}
```

Same shape as a single item from `connector list`.

## cargo-ai connection integration list

Each integration in the list is a full integration object (same shape as `integration get`).

```json
{
  "integrations": [
    {
      "slug": "clearbit",
      "name": "Clearbit",
      "description": "Company and person enrichment",
      "category": "enrichment",
      "icon": "https://...",
      "color": "#...",
      "url": "https://...",
      "subCategories": [],
      "documentationPath": "...",
      "connector": { "config": { "jsonSchema": { ... } } },
      "actions": { "enrichCompanyFromDomain": { ... } },
      "extractors": {},
      "dynamicSchemas": {}
    }
  ]
}
```

**Key fields:** `slug` (used when creating connectors and filtering), `name`, `category`, `actions`, `extractors`.

Supports `--category`, `--slugs`, `--search`, `--has-actions`, `--has-extractors` to filter results.

**Integration categories:** `engagement`, `marketing`, `sales`, `finance`, `analytics`, `freeform`, `success`, `support`, `enrichment`, `storage`, `custom`.

## cargo-ai connection integration get

Returns the full integration object, including all actions and extractors with their configuration schemas.

```json
{
  "integration": {
    "slug": "clearbit",
    "name": "Clearbit",
    "description": "Company and person enrichment",
    "category": "enrichment",
    "icon": "https://...",
    "color": "#...",
    "url": "https://...",
    "subCategories": [],
    "documentationPath": "...",
    "connector": {
      "config": {
        "jsonSchema": { "type": "object", "properties": { "apiKey": { "type": "string" } } }
      }
    },
    "actions": {
      "enrichCompanyFromDomain": {
        "name": "Enrich Company From Domain",
        "description": "Enrich a company by domain",
        "category": "enrichment",
        "icon": "https://...",
        "isSerialized": false,
        "config": {
          "jsonSchema": { "type": "object", "properties": { "domain": { "type": "string" } } }
        },
        "output": {
          "schema": {
            "type": "object",
            "properties": { "name": { "type": "string" }, "domain": { "type": "string" } }
          }
        },
        "credits": {
          "costs": [{ "type": "fixed", "cost": 1 }]
        },
        "childrenCount": 0
      },
      "findRecords": {
        "name": "Find records",
        "description": "Find records matching the given criterias.",
        "category": "enrichment",
        "icon": "https://...",
        "isSerialized": false,
        "config": {
          "jsonSchema": {
            "type": "object",
            "properties": {
              "objectType": { "type": "string", "description": "The object type" },
              "propertyName": { "type": "string", "description": "Property to search on" }
            }
          },
          "uiSchema": {
            "objectType": {
              "ui:widget": "IntegrationAutocompleteWidget",
              "ui:options": {
                "slug": "listObjects",
                "allowRefresh": true
              }
            },
            "propertyName": {
              "ui:widget": "IntegrationAutocompleteWidget",
              "ui:options": {
                "slug": "listObjectProperties",
                "allowRefresh": true,
                "params": {
                  "objectType": "$this.$parent.objectType"
                }
              }
            }
          }
        },
        "credits": {
          "costs": [{ "type": "fixed", "cost": 1 }]
        },
        "childrenCount": 0
      }
    },
    "extractors": {},
    "dynamicSchemas": {}
  }
}
```

**Key fields:** `actions` is keyed by `actionSlug` — use these in workflow connector nodes. Each action's `config.jsonSchema` is its **input**; `output.schema`, when present, is the JSON Schema of what the action **emits** — read it instead of guessing the output shape (not every action declares one; `integration list` includes it too). `connector.config.jsonSchema` describes the credentials needed when creating a connector (for non-credit integrations). `extractors` is keyed by extractor slug — use these when creating models.

**`uiSchema` and autocomplete:** Each action's `config` may include a `uiSchema` alongside `jsonSchema`. When a field in `uiSchema` has `"ui:widget": "IntegrationAutocompleteWidget"`, its allowed values must be fetched via `connector autocomplete`. The `ui:options.slug` tells you which autocomplete slug to use, and `ui:options.params` (if present) specifies dependent parameters — replace `$this.$parent...` expressions with actual values. See the main SKILL.md for the full autocomplete workflow.

## cargo-ai connection native-integration get

> **Note:** This command returns **built-in Cargo actions only** (e.g. `start`, `end`, `branch`, `filter`, `agent`, `python`). It does **not** return HubSpot, Salesforce, Clearbit, or other third-party connector actions. For those, use `cargo-ai connection integration get <slug>`.

```json
{
  "nativeIntegration": {
    "actions": {
      "send_email": {
        "name": "Send Email",
        "description": "Send an email via the native Cargo email action",
        "category": "enrichment",
        "icon": "https://...",
        "isSerialized": false,
        "config": {
          "jsonSchema": { "type": "object", "properties": { "domain": { "type": "string" } } },
          "uiSchema": {}
        },
        "meta": {
          "jsonSchema": { "type": "object" }
        },
        "credits": {
          "costs": [{ "type": "fixed", "cost": 1 }]
        },
        "childrenCount": 0
      }
    },
    "extractors": {
      "contacts": {
        "name": "Contacts",
        "description": "Sync contacts from integration",
        "icon": "https://...",
        "config": {
          "jsonSchema": { "type": "object", "properties": {} },
          "uiSchema": {}
        },
        "mode": {
          "kind": "fetch",
          "isIncremental": true
        }
      }
    }
  }
}
```

**`actions`** is keyed by action slug. Each key is an `actionSlug` for use in workflow connector nodes.

| Field | Description |
| ----- | ----------- |
| `name` | Display name |
| `description` | What the action does |
| `category` | One of: `invisible`, `logic`, `storage`, `ai`, `sales`, `code` |
| `icon` | Icon URL |
| `config.jsonSchema` | JSON Schema describing the action's input parameters |
| `config.uiSchema` | UI hints for each field — check for `IntegrationAutocompleteWidget` to detect autocomplete fields |
| `childrenCount` | Number of child branches (0 for most actions) |
| `credits.costs` | Credit cost per execution. Each cost has `type` (`fixed` or `unit`) and `cost` (number) |

**`extractors`** is keyed by extractor slug. Extractors sync data from an integration into a model.

| Field | Description |
| ----- | ----------- |
| `name` | Display name |
| `description` | What the extractor syncs |
| `icon` | Icon URL |
| `config.jsonSchema` | JSON Schema describing the extractor's configuration |
| `mode.kind` | `"fetch"` (pull-based) or `"ingest"` (push-based) |
| `mode.isIncremental` | Whether the extractor supports incremental sync (fetch mode only) |

## cargo-ai connection connector autocomplete

Fetches the allowed values for a field that uses `IntegrationAutocompleteWidget` in its `uiSchema`.

```json
{
  "results": [
    {
      "label": "Contacts",
      "value": "contacts",
      "description": "HubSpot contacts object"
    },
    {
      "label": "Companies",
      "value": "companies"
    },
    {
      "label": "Deals",
      "value": "deals"
    }
  ]
}
```

| Field | Required | Description |
| ----- | -------- | ----------- |
| `label` | yes | Human-readable display name |
| `value` | yes | The value to use in node config |
| `description` | no | Additional context about the option |
| `parent` | no | Parent grouping identifier (for hierarchical options) |
| `configOverride` | no | Additional config values that should be set when this option is selected |

Use the `value` field when setting the corresponding property in a workflow node's `config`.
references/troubleshooting.md
# Troubleshooting

Common errors and recovery steps for `cargo-connection` commands.

## General

| Symptom                                      | Cause                            | Fix                                                                       |
| -------------------------------------------- | -------------------------------- | ------------------------------------------------------------------------- |
| `{"errorMessage": "..."}` with non-zero exit | Any CLI error                    | Read the `errorMessage` — it usually says exactly what's wrong            |
| `command not found: cargo-ai`                | CLI not installed or not in PATH | Run `npm install -g @cargo-ai/cli` or prefix with `npx @cargo-ai/cli`     |
| `Unauthorized` or `Forbidden`                | Bad or expired credentials       | Re-run `cargo-ai login --oauth` (browser sign-in) or `cargo-ai login --token <token>`; verify with `cargo-ai whoami` |

## Connectors

| Symptom                                 | Cause                                            | Fix                                                                                              |
| --------------------------------------- | ------------------------------------------------ | ------------------------------------------------------------------------------------------------ |
| `connector get` returns not found       | Wrong UUID                                       | Re-run `connector list` to get the correct UUID                                                  |
| `connector create` fails                | Integration slug doesn't exist                   | Run `integration list` to find valid `integrationSlug` values                                    |
| `connector remove` fails                | Connector is referenced by active plays or tools | Check `playsCount` and `toolsCount` on the connector; remove or update dependent resources first |
| Workflow fails with connector not found | Connector UUID in node graph is wrong            | Re-run `connector list` to verify the UUID used in the node config                               |
| Action not executing as expected        | Wrong `actionSlug`                               | For third-party connector actions (HubSpot, Salesforce, etc.), run `integration get <slug>` to see correct `actionSlug` values. Only use `native-integration get` for built-in Cargo actions. |

## Connector autocomplete

| Symptom                                              | Cause                                                              | Fix                                                                                                                          |
| ---------------------------------------------------- | ------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------- |
| `connector autocomplete` returns empty results       | Wrong autocomplete slug or params                                  | Re-check the `uiSchema` from `integration get <slug>` — use the exact `ui:options.slug` and pass required `params`           |
| `Invalid autocomplete params` error                  | Missing or wrong params keys                                       | Check `ui:options.params` in the `uiSchema` — each key listed there must be provided in `--params` with an actual value       |
| `connectorNotFound` reason                           | Wrong connector UUID                                               | Re-run `connector list` to get the correct UUID                                                                               |
| `failedToGetIntegration` reason                      | Integration doesn't support autocomplete for this slug             | Verify the autocomplete slug exists in the integration's `uiSchema` — not all fields use autocomplete                         |
| Stale or outdated autocomplete results               | Results are cached (default 30 minutes)                            | Pass `--refresh` to bypass the cache                                                                                          |
| Used a freeform value instead of autocomplete result  | Field requires a specific value from the autocomplete result set   | Always check `uiSchema` for `IntegrationAutocompleteWidget` — if present, fetch and use a `value` from the autocomplete results |

## Integrations

| Symptom                                                 | Cause                                                         | Fix                                                             |
| ------------------------------------------------------- | ------------------------------------------------------------- | --------------------------------------------------------------- |
| `integration list` doesn't show an expected integration | Integration may not be available in your region or plan       | Contact Cargo support or check the integrations page in the app |
| Third-party actions (e.g. HubSpot) not found via `native-integration get` | `native-integration get` only returns built-in Cargo actions | Use `integration get <slug>` (e.g. `integration get hubspot`) to get service-specific actions |
| OAuth flow incomplete                                   | `complete-oauth` not called after creating an OAuth connector | Complete the OAuth flow through the Cargo app UI or via the API |
skill-metadata.json
{
  "$comment": "Generated by .github/scripts/skills-metadata.mjs — do not hand-edit. Regenerate with: node .github/scripts/skills-metadata.mjs --write .",
  "name": "cargo-connection",
  "version": "1.4.0",
  "documents": [
    {
      "path": "SKILL.md",
      "kind": "entrypoint",
      "title": "Cargo CLI — Connections"
    },
    {
      "path": "references/examples/connectors.md",
      "kind": "example",
      "title": "Connector examples"
    },
    {
      "path": "references/examples/integrations.md",
      "kind": "example",
      "title": "Integration examples"
    },
    {
      "path": "references/response-shapes.md",
      "kind": "reference",
      "title": "Response shapes"
    },
    {
      "path": "references/troubleshooting.md",
      "kind": "reference",
      "title": "Troubleshooting"
    }
  ],
  "contentHash": "f13696973045922b006b9665a679d99fd8fb2ed5463a9c4fd3012f0e7eb171f8"
}
SKILL.md
---
name: cargo-connection
description: "Connect Cargo to an external system and find out what it can do — authenticate connectors, browse the integration catalog, and resolve the `connectorUuid` and `actionSlug` a workflow node needs. Triggers: \"connect my HubSpot\", \"is Salesforce connected\", \"what integrations do you support\", \"can Cargo talk to <tool>\", \"what actions does <provider> have\", \"I need the connector UUID\", \"set up the API key for\", \"it is asking for credentials again\", \"why is this connector failing auth\", \"list my connectors\". Integrations: amplemarket, amplitude, attio, bigQuery, calendly, closecom, contrast, csv, customerio, dbt, emailBison, expandi, googleAds, googleSheets, heyReach, http, hubspot, hubspotMcp, instantly, instantlyV2, intercom, jira, kitt, lemlist, lgm, linkedinAds, linkedinMatchedAudience, livestorm, manus, marketo, metabase, microsoftTeams, mixpanel, netsuite, netsuiteSoap, notionMcp, octave, onesignal, outreach, pipedrive, postgresql, redshift, resend, rift, salesforce, salesforceMcp, salesloft, Sendgrid, sillage, slack, smartlead, snowflake, sql, stripe, and 83 more. Skip when: choosing between enrichment providers for a GTM job — use cargo-gtm and its provider playbooks."
version: "1.4.0"
compatibility: Requires @cargo-ai/cli (npm). Sign in or create an account with `cargo-ai login --email` (emailed code, no browser), `--oauth`, or an API token
homepage: https://github.com/getcargohq/cargo-skills
metadata:
  author: getcargo
  openclaw:
    requires:
      bins:
        - cargo-ai
    install:
      - kind: node
        package: "@cargo-ai/cli@latest"
        bins:
          - cargo-ai
    homepage: https://github.com/getcargohq/cargo-skills
---

# Cargo CLI — Connections

Connector and integration management: listing connectors, discovering available integrations, and managing authenticated connector instances.

> See `references/response-shapes.md` for full JSON response structures.
> See `references/troubleshooting.md` for common errors and how to fix them.
> See `references/examples/connectors.md` for connector CRUD and discovery examples.
> See `references/examples/integrations.md` for listing available integrations and OAuth flows.
> For third-party connector rate limit handling and retry config in workflows, see `cargo-orchestration/references/polling.md` and `cargo-orchestration/references/troubleshooting.md`. Native integrations do not have rate limits.

## Bootstrap

Already signed in (`cargo-ai whoami` returns a workspace)? Skip to the next section.

```bash
npm install -g @cargo-ai/cli            # no global install? prefix every command with `npx @cargo-ai/cli`
cargo-ai login --email [email protected]  # emailed code, no browser; creates the account on first use
                                        # alternatives: --oauth (browser) · --token <api-token> (CI)
cargo-ai whoami                         # confirm the active workspace before any write
```

Every command prints JSON to stdout; failures exit non-zero with `{"errorMessage": "..."}`. Anything that creates a run or a batch is async — pass `--wait-until-finished` or poll the matching `get`. When the full skill bundle is installed, [`../cargo/references/prerequisites.md`](../cargo/references/prerequisites.md) adds the CLI version pin, token scopes, and the admin-only surface.

## Key concepts

**Integration:** The external service type (e.g. HubSpot, Clearbit, Salesforce). Integrations define what actions are available.

**Connector:** An authenticated instance of an integration. One integration can have multiple connectors (e.g. two different HubSpot accounts). Connectors are what you reference in workflow node graphs.

## Discover resources first

**Looking for an action? Search for it — don't browse the catalog.** Two keyword
searches cover the whole surface, and both beat paging `integration list` or
reading a whole `integration get` payload:

```bash
cargo-ai orchestration action list <query>                # START HERE — connector + native + tools + agents.
                                                          # Returns a ready-to-run action object (connectorUuid
                                                          # resolved) and the action's credit costs.
cargo-ai connection action search <query> --credits-only  # connector catalog only, but filters by category
                                                          # and by "is it paid" — which `action list` cannot.
```

Reach for the catalog commands when you need the *integration*, not an action —
its auth fields, its extractors, or the full input schema of an action you have
already picked:

```bash
cargo-ai connection connector list                        # all authenticated connectors
cargo-ai connection integration list                      # all available integration types
cargo-ai connection integration list --search "hubspot"   # search by name
cargo-ai connection integration get <slug>                # one integration's actions + input schemas
cargo-ai connection native-integration get                # built-in Cargo actions only (NOT third-party)
```

### Which action search?

| | `orchestration action list` | `connection action search` |
|---|---|---|
| Covers | connector, native, **tools, agents** | connector catalog only |
| Returns | a runnable `action` object with `connectorUuid`, workspace connectors, `credits`, autocompletes | `integrationSlug` + `actionSlug`, category, `credits` — you assemble the action yourself |
| Filters | `--kind`, `--integration-slug`, `--limit` | `--category`, `--integration`, **`--credits-only`**, `--limit` |
| Needs | CLI ≥ 1.0.66 | CLI ≥ 1.0.36 |

Default to `action list` — it is the one that hands you something you can execute.
Switch to `action search` for the two questions it alone answers: *which paid
actions match this?* (`--credits-only`) and *what does this category offer?*
(`--category`). Both rank an action-slug or name hit above an integration hit,
above a description hit, and require **all** query terms to match.

### `integration get` vs `native-integration get`

These two commands return **different sets of actions** and are not interchangeable:

| Command | Third-party service actions (HubSpot, Salesforce, Clearbit, …) | Built-in Cargo actions (HTTP, transforms, utilities) | When to use |
|---|---|---|---|
| `integration get <slug>` | ✓ | ✗ | You need actions for a specific third-party service — **use this for HubSpot, Salesforce, Clearbit, etc.** |
| `native-integration get` | ✗ | ✓ | You need Cargo-native capabilities that don't belong to any specific third-party connector |

**Example:** To find HubSpot-specific actions, use `integration get hubspot` — `native-integration get` will not return them.

## Quick reference

```bash
cargo-ai connection connector list --integration-slug <slug>
cargo-ai connection connector create --integration-slug <slug> --slug <slug> --name <name>
cargo-ai connection connector update --uuid <uuid> --name <name>
cargo-ai connection connector remove <connector-uuid>
cargo-ai connection connector get <connector-uuid>
cargo-ai connection connector autocomplete --connector-uuid <uuid> --slug <slug> --params '<json>'
cargo-ai connection integration list
cargo-ai connection integration get <slug>
cargo-ai connection integration get-documentation <slug>
cargo-ai connection native-integration get
```

## Connectors

Connectors are authenticated connections to external services.

```bash
# List all connectors
cargo-ai connection connector list

# Create a connector
cargo-ai connection connector create \
  --integration-slug clearbit \
  --slug clearbit_production \
  --name "Clearbit - Production"

# Update a connector
cargo-ai connection connector update --uuid <connector-uuid> --name "Clearbit - Staging"

# Remove a connector
cargo-ai connection connector remove <connector-uuid>

# Check if a connector slug is taken
cargo-ai connection connector exists-by-slug --slug clearbit_production
```

**Note:** Creating a connector requires `--slug` (unique identifier) in addition to `--name` (display name) and `--integration-slug`. For OAuth-based integrations, the authentication flow is completed separately via `connection integration complete-oauth`.

## Integrations

Integrations define the available services and their connector actions.

```bash
# List all available integrations
cargo-ai connection integration list

# Filter by category
cargo-ai connection integration list --category enrichment

# Search by name
cargo-ai connection integration list --search "hubspot"

# Find by exact slug(s)
cargo-ai connection integration list --slugs clearbit

# Only integrations that have actions (usable in workflow nodes)
cargo-ai connection integration list --has-actions true

# Only integrations that have extractors (can sync data into models)
cargo-ai connection integration list --has-extractors true

# Get built-in Cargo actions and extractors (NOT third-party connector actions)
cargo-ai connection native-integration get
```

**Integration categories:** `engagement`, `marketing`, `sales`, `finance`, `analytics`, `freeform`, `success`, `support`, `enrichment`, `storage`, `custom`.

Use `integration get <slug>` to discover all actions available for a specific third-party service (e.g. HubSpot, Salesforce). Use `native-integration get` only for built-in Cargo actions — it does **not** return HubSpot or other service-specific actions. Actions are referenced by `actionSlug` in workflow node graphs (see the `cargo-orchestration` skill's `references/nodes.md`).

## Connector autocomplete — fetching available values for action fields

Some action fields don't accept freeform input — their allowed values must be fetched dynamically from the connector. When you inspect an action's config (via `integration get <slug>` or `native-integration get`), look at the `uiSchema` alongside the `jsonSchema`. If a field's `uiSchema` contains `"ui:widget": "IntegrationAutocompleteWidget"`, the valid values for that field **must** be retrieved using `connector autocomplete`.

### How to detect autocomplete fields

When an action's config looks like this:

```json
{
  "jsonSchema": {
    "type": "object",
    "properties": {
      "objectType": { "type": "string", "description": "The object type" }
    }
  },
  "uiSchema": {
    "objectType": {
      "ui:widget": "IntegrationAutocompleteWidget",
      "ui:options": {
        "slug": "listObjects",
        "allowRefresh": true
      }
    }
  }
}
```

The `objectType` field requires autocomplete. The `ui:options.slug` (`"listObjects"`) is the autocomplete slug you pass to `connector autocomplete`.

### How to call connector autocomplete

```bash
cargo-ai connection connector autocomplete \
  --connector-uuid <connector-uuid> \
  --slug <autocomplete-slug> \
  --params '{}'
```

| Flag               | Required | Description                                                       |
| ------------------ | -------- | ----------------------------------------------------------------- |
| `--connector-uuid` | yes      | The UUID of the connector to autocomplete against                 |
| `--slug`           | yes      | The autocomplete slug from `uiSchema[field]["ui:options"].slug`   |
| `--params`         | yes      | JSON object of parameters (use `{}` when none are needed)         |
| `--value`          | no       | Search string to filter results                                   |
| `--refresh`        | no       | Bypass cache and fetch fresh results                              |

### Autocomplete with parameters

Some autocomplete fields depend on the value of another field. This is indicated by a `params` object in `ui:options`:

```json
{
  "uiSchema": {
    "objectType": {
      "ui:widget": "IntegrationAutocompleteWidget",
      "ui:options": { "slug": "listObjects" }
    },
    "propertyName": {
      "ui:widget": "IntegrationAutocompleteWidget",
      "ui:options": {
        "slug": "listObjectProperties",
        "params": { "objectType": "$this.$parent.objectType" }
      }
    }
  }
}
```

Here, `propertyName` depends on the selected `objectType`. Replace the `$this.$parent...` expression with the actual value you chose:

```bash
# 1. First, get the list of object types
cargo-ai connection connector autocomplete \
  --connector-uuid <uuid> --slug listObjects --params '{}'

# 2. Then, get properties for the chosen object type
cargo-ai connection connector autocomplete \
  --connector-uuid <uuid> --slug listObjectProperties \
  --params '{"objectType": "contacts"}'
```

### Response format

```json
{
  "results": [
    { "label": "Contacts", "value": "contacts" },
    { "label": "Companies", "value": "companies" },
    { "label": "Deals", "value": "deals" }
  ]
}
```

Use the `value` field in your node config. The `label` is the human-readable display name. Results may also include optional `description` and `parent` fields.

### End-to-end example: configuring a HubSpot action

```bash
# 1. Find your HubSpot connector UUID
cargo-ai connection connector list --integration-slug hubspot

# 2. Get HubSpot actions and inspect their config + uiSchema
cargo-ai connection integration get hubspot
# → The "findRecords" action has objectType with autocomplete slug "listObjects"

# 3. Fetch available object types
cargo-ai connection connector autocomplete \
  --connector-uuid <hubspot-connector-uuid> \
  --slug listObjects --params '{}'
# → Returns: contacts, companies, deals, tickets, etc.

# 4. Fetch properties for the chosen object type
cargo-ai connection connector autocomplete \
  --connector-uuid <hubspot-connector-uuid> \
  --slug listObjectProperties \
  --params '{"objectType": "contacts"}'
# → Returns: email, firstname, lastname, phone, etc.

# 5. Use these values in your workflow node config
```

## Using connector actions in workflows

Connector actions are used as nodes in workflow graphs. To use an action:

```bash
# 1. Find your connector UUID
cargo-ai connection connector list
# → Filter the output by integrationSlug to find the right connector

# 2. Discover the action — search first, and only then read its schema
cargo-ai orchestration action list <keywords> --integration-slug <integration-slug>
cargo-ai connection integration get <integration-slug>
# → actions are keyed by actionSlug, with config.jsonSchema (input) for each
# → many actions also carry output.schema — the JSON Schema of what the action
#   emits; use it to wire downstream nodes instead of guessing (absent on some actions)
# → Or use get-documentation for a plain text overview
# → Or use native-integration get for built-in Cargo actions (not third-party)

# 3. Reference the connector and action in a node graph
# See cargo-orchestration references/nodes.md for the full node syntax
```

### Reading an action's input schema — and where the inputs go

An action's **input** fields live at `actions.<slug>.config.schema` in the `integration get <slug>` output (`config.jsonSchema` is the same schema decorated for the form UI). Read it before calling an action — don't guess field names.

```bash
# the required input fields for an action:
cargo-ai connection integration get linkedin \
  | jq '.integration.actions.connectProfile.config.schema'
# → required: linkedinProfileUrl, identityIds
```

Two footguns:

- **For a top-level action (`action execute` / `execute-batch`), the input values go in `--data`, NOT in the action's `config`.** The fields described by `config.schema` are the `--data` payload; the action definition carries no `config` key at all. **Misplacing them is no longer a loud failure:** older backends rejected the call with `A top-level action does not use action.config; pass the action's inputs via data instead.`, newer ones drop `config` on the way in and run the action with **no inputs at all** — you get a missing-required-field error from the provider, or an empty result, not a message about `config`. If an action comes back empty for no obvious reason, check that the inputs are in `--data`. (Inside a workflow **node graph** those same fields go in the node's `config` — see `cargo-orchestration/references/nodes.md`. The "`--data`, not `config`" rule is specific to `action execute`/`execute-batch`.)
- **Some inputs must be resolved first via autocomplete.** If a field's `uiSchema` carries `IntegrationAutocompleteWidget`, fetch its values with `connector autocomplete` (above). Notably, LinkedIn engagement/extraction actions (`connectProfile`, `visitProfile`, `extractEventAttendees`, `extractProfileViewers`) require `identityIds` — the connected account that *acts* — resolved via the `listIdentityIds` autocomplete. A `must match format "uuid"` error means that identity is missing.

Example connector node (Clearbit company enrichment):

```json
{
  "uuid": "node-uuid",
  "slug": "enrich",
  "kind": "connector",
  "integrationSlug": "clearbit",
  "actionSlug": "enrichCompany",
  "connectorUuid": "<clearbit-connector-uuid>",
  "config": {
    "domain": {
      "kind": "templateExpression",
      "expression": "{{nodes.start.domain}}",
      "instructTo": "none",
      "fromRecipe": false
    }
  },
  "childrenUuids": ["end-node-uuid"],
  "fallbackOnFailure": false,
  "position": { "x": 0, "y": 166 }
}
```

## Help

Every command supports `--help`:

```bash
cargo-ai connection connector list --help
cargo-ai connection connector create --help
cargo-ai connection integration list --help
```