Agent skills

Sume CLI commands are designed to make agent automation explicit and auditable.

Use read-only first

Prefer read commands while planning:

Require confirmation for writes

Agents should not create resources or submit paid provider work without explicit operator confirmation.

GateUse for
--confirm-submitNon-paid writes such as job cancellation or asset registration.
--confirm-paidGeneration that can reserve or spend credits (Avatar / Avatar Video).

Image, Video, and Music generation are not CLI submit commands yet — agents should call the Developer API for those families and still use CLI job recovery where helpful.

Redact sensitive output

Use --agent --json when automation reads command output. Agent mode redacts or summarizes URL-like fields and account/workspace details where supported.

Bundled skills

Install or refresh the packaged Sume skill into local agent skill directories:

sume skills install writes into .agents/skills or .claude/skills. Use export to review source files before a custom install.

MCP for agents

Prefer hosted MCP (https://mcp.sume.com/mcp) for Cursor/Claude remote connectors. Local sume mcp is not launched in current CLI releases — see sume mcp doctor --json and the CLI command reference.

  1. Inspect catalog and local readiness.
  2. Validate the payload with a read-only/schema command.
  3. Ask for confirmation before writes or paid work.
  4. Submit one bounded job (CLI for Avatar; API for Image/Video/Music).
  5. Recover through job status/events/result commands.
  6. Summarize outputs without pasting secrets or signed URLs.