create

create

Turn a brief into a finished motion piece (default 1080×1920 vertical; landscape/square also available) through the 甲乙环 (critic-loop) pipeline. Quality is produced by a unified design-and-build agent working in one continuous context with real design knowledge — judged on its actual rendered frames, blind-selected and critic-refined, with the user's eyes as the final gate.

You (the agent reading this skill) are the orchestrator. You spawn the sub-agents, run the render tooling, and ferry critic verdicts verbatim — you do NOT design, and you do NOT judge aesthetics. Every piece of design knowledge and every protocol reaches the sub-agents by them Reading the verbatim equipment/protocol files — never by you paraphrasing them.

The one rule that protects everything: do not summarize the equipment, the §4 self-check persona, the conceit rules, or the critic protocol in your own words. The tuned wording only binds an agent when that agent has the literal text in its context. Always delegate by Read (${CLAUDE_PLUGIN_ROOT}/…), never by retelling.

Inputs

The pipeline needs a brief and a spec before any draw. Collect both in Step 0.5 (below); for any you can't get, propose a sensible default and let the user accept it in one line.

• brief: the piece's job — audience, takeaway, tone. Required. If not given, ask for it.
• spec — the finished-video parameters:
  • aspect / resolution: vertical 1080×1920 (default — social/portrait), landscape 1920×1080, or square 1080×1080. Propose vertical as the default; the user may pick another.
  • duration — offer it as a choice, not a blank (see Step 0.5): a couple of sensible second-counts for this brief, "I'll name one", or "don't constrain it — the designer decides". Whichever second-count the user picks or states, it is locked; only the explicit "don't constrain it" option makes it free. This authority is carried all the way to Step 4.5.
  • fps (default 30).
  • on-screen copy: is there required text/wording, or is it the designer's call?
  • audio intent: does the user want sound (music / SFX / VO)? Note honestly if asked: audio is experimental here — the engine can mount <Audio>, but the design equipment and the critic loop are visual-only (no audio dimension in the 3-step process, nothing in §4 / the 甲乙环 judges sound). So an audio request is best-effort and unverified by the pipeline; surface that before committing to it. If the user still insists on sound, the minimal tool-chain pointer is: consult the remotion-best-practices skill's remotion-markup node (audio.md / sfx.md — <Audio>, remotion.media remote SFX) for what the engine supports, and source CC0 assets yourself — the pipeline neither provides nor validates audio. (Note: sfx.md uses @remotion/sfx, which is deliberately NOT in the base dep set — audio being experimental, the builder installs it on demand with npx remotion add @remotion/sfx, which resolves the version matching the pinned engine.)
• target-project port (only if asked): if the user intends to port the finished piece back into an existing Remotion project rather than ship the standalone workspace render, ask for that project's Remotion version and whether it has three / @remotion/media installed up front. The workspace builds on Remotion 4.0.515 + three (the version the pipeline is validated against — see the plugin's package.json for the current pin); an older/leaner target can drift on API, so knowing the target version before drawing avoids a port-time surprise. (Porting is a user-side activity the pipeline doesn't itself verify.)
• N (draws): independent draws before blind-select. Default 3. (More draws = higher ceiling; N is the user's knob.)
• workspace: a user-side project dir (NOT under the plugin). Default ./<piece-slug>/ in the user's CWD.