Agents / CLI
Dry run skill
Simulate what an agent would do without executing any side effects. Returns the LLM's plan, intended tool calls, model used, and token usage. No DB writes, no LinkedIn sends. Use to vet a skill before turning autonomy up.
pipeline dry-run-skillBackend AI, consent requiredParameters
workspaceIdOptional · string- Optional workspace ID or slug. Required when this credential can access multiple workspaces and no workspace was configured on the client.
agentRoleRequired · string- See the input schema for this field.scout · researcher · icp · strategist · writer · campaign_builder · closer · coach
skillIdsOptional · array- Optional. Skill IDs to consider; omit to let the agent pick.
userMessageOptional · string- Optional free-text instruction for the agent.
allowHostedAiOptional · boolean- Must be true when this operation uses Pipeline hosted inference.
pipeline dry-run-skill \
--agent-role "scout" \
--allow-hosted-aiFull input schema
{
"type": "object",
"properties": {
"workspaceId": {
"type": "string",
"minLength": 1,
"description": "Optional workspace ID or slug. Required when this credential can access multiple workspaces and no workspace was configured on the client."
},
"agentRole": {
"type": "string",
"enum": [
"scout",
"researcher",
"icp",
"strategist",
"writer",
"campaign_builder",
"closer",
"coach"
]
},
"skillIds": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional. Skill IDs to consider; omit to let the agent pick."
},
"userMessage": {
"type": "string",
"description": "Optional free-text instruction for the agent."
},
"allowHostedAi": {
"type": "boolean",
"description": "Must be true when this operation uses Pipeline hosted inference."
}
},
"required": [
"agentRole"
]
}