メニュー
Run the fastest safe Sume Avatar/Avatar Video iteration loop using async submits, batch state files, parallel polling, deferred downloads, and explicit quality/cost tradeoffs.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Create, batch-plan, watch, inspect, and select current Sume Avatar 1.0 resources by avatar_handle with safe paid gates and agent-redacted readback.
Create, batch-plan, watch, and inspect Sume Avatar Video 1.0 jobs from selected avatar handles, including productless/product-image flows, metadata readback, and paid gates.
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.
Run paid Sume dogfood QA under an explicit USD cap using idempotency, max_spend_usd where available, cost readback, and no duplicate paid submissions.
Use advanced compatibility Sume asset upload/download helpers only when explicitly requested; launch Avatar and Avatar Video inputs should use stable public HTTPS URLs directly.
Set up and verify Sume CLI authentication safely, including browser login, API-key readiness, doctor checks, and headless-terminal caveats without exposing secrets.
| name | sume-min-latency |
| description | Run the fastest safe Sume Avatar/Avatar Video iteration loop using async submits, batch state files, parallel polling, deferred downloads, and explicit quality/cost tradeoffs. |
Use this skill when the user wants the fastest useful Sume result while still respecting paid gates and avoiding duplicate jobs.
Run readiness only if local state is unknown:
sume doctor --agent --json
Use schema discovery only for the write you are about to make:
sume tools schema avatars.create --json
sume tools schema avatar-videos.create --json
Prefer async submit plus watch/result over blocking waits.
For multiple independent candidates, draft a manifest and use batch plan/create/watch/result with a persistent state file.
Use stable idempotency keys. Reruns must skip already-created jobs.
Timeout is not terminal. If jobs watch returns non-terminal jobs, run a
one-shot aggregate check with --timeout-seconds 0, then continue polling or
ask whether to keep watching. Do not final-answer as complete until terminal
result/resource readback exists or the user explicitly stops the workflow.
Do not download media unless local comparison is required or the user asks.
If the user prioritizes speed/cost, explicitly choose quality=standard;
otherwise preserve the platform default quality.
sume avatar-videos create \
--avatar-handle <ready_avatar_handle> \
--script "Short reviewed script." \
--quality standard \
--confirm-paid \
--agent \
--json
sume jobs watch <job_id> --agent --json
sume jobs result <job_id> --agent --json
For multiple jobs, use one aggregate watcher:
sume jobs watch --ids <job_id>,<job_id> --agent --json
If it times out, do not submit replacement paid jobs. Recheck with
--timeout-seconds 0, keep polling, or ask whether to continue.
Report job id, resource id, requested quality, wall-clock time if measured, queue/run state, captured/refunded cost when available, and sanitized result availability. Report non-terminal jobs as still in progress, not complete. Do not paste full media URLs.
Do not use this skill for broad quality exploration or side-by-side evaluation;
use sume-quality-experiment. Do not use it to bypass spend caps, paid
approval, idempotency, or state files.