| name | sume |
| description | Router for current Sume.com public API workflows. Use for auth, schema discovery, Avatar 1.0, Avatar Video 1.0, jobs, spend-capped dogfooding, minimum-latency generation loops, media QA, and selecting focused Sume skills. |
Sume Skill Router
Start here for Sume agent work. The executable source of truth is the sume
CLI over current api.sume.com; this skill chooses the safest workflow and
points agents to focused skills.
Sume CLI must remain a thin wrapper over public API boundaries. Do not call
Sume databases, internal app routes, Railway services, provider APIs, or old
sume.so-only surfaces.
Core Rules
- Run readiness checks when the local state is unknown.
- Use
sume tools list --json and sume tools schema <name> --json before
constructing any write or paid request.
- Use
sume skills list --json and sume skills export <name> --json to
discover bundled skill content instead of guessing.
- Use
--agent --json whenever automation reads jobs, avatars, or avatar
videos.
- Ask for explicit approval before
--confirm-submit or --confirm-paid.
- Paid work must use idempotency and a spend cap where the command/tool
supports it.
- Timeout is not terminal. After a paid submit, keep ownership until all jobs
are completed, failed, canceled, or the user explicitly tells you to stop.
Do not submit duplicate paid jobs while recovering from timeout.
- Do not print API keys, auth approval URLs/codes in final reports, signed
URLs, private media URLs, storage object keys, raw provider identifiers,
workspace/user ids, or full result URLs.
- Use current public launch API surfaces only: account, catalog, balance,
usage, jobs, Avatar 1.0, and Avatar Video 1.0.
First Checks
sume --version
sume doctor --agent --json
sume tools list --json
sume skills list --json
Use sume tools schema <name> --json before constructing writes. Do not copy
request schemas from memory or from stale docs.
Auth
Use browser login when the browser is local:
sume login
For remote/headless terminals, use a short-lived background login process and
show the URL/code only to the requesting user. See references/safety.md for
the exact pattern.
Routing
| User intent | Use skill | First command |
|---|
| Schema, tool list, MCP status, skill setup | sume-tools | sume tools list --json |
| Login, API key, local readiness | sume-auth | sume auth status --json |
| Create or choose avatars | sume-avatar | sume tools schema avatars.create --json |
| Generate videos from ready avatars | sume-avatar-video | sume tools schema avatar-videos.create --json |
| Fastest safe iteration loop | sume-min-latency | local manifest/state file, then async create/watch/result |
| Controlled quality comparisons | sume-quality-experiment | variant manifest, then schema check before paid calls |
| Paid QA under an explicit cap | sume-spend-capped-dogfood | estimate/admission check if available, then idempotent capped submit |
| Local result inspection/comparison | sume-media-qa | sume jobs download <job_id> --output-dir <dir> --json |
| Advanced compatibility assets | sume-assets | sume tools schema assets.upload_url --json |
Read references/safety.md for auth, paid/write gates, and redaction rules.
Read references/eval-scenarios.md when validating agent behavior.
MCP State
Sume MCP is coming soon and is not part of this public CLI launch release yet.
Use direct CLI commands today.
Not For
Do not use old sume.so Brand, Ads, Face Swap, generic image/video generation,
raw provider model, billing-write, file, or asset-search workflows unless they
appear in the current public api.sume.com catalog and tool schemas.
