pruna-run

pruna-run (fast entrypoint)

Use this when the user wants immediate execution from one incoming prompt — agent routing only (no bundled CLI runner).

Before any API call: generation-diversity.md (random seed ritual / SSoT + axis rotation).

Before paid calls: requesting-generation-feedback.

When NOT to use

• Multi-scene plans with approval gates → use a workflow skill (avatar-multi-scene, music-video, …)
• Editing an existing image → p-image-edit
• Recipe menus or multi-step chains → pruna-generative-pipeline

What it does

Read the user's prompt and pick the shortest chain:

Route	When	Chain
image	Still only	p-image
i2v	Motion from a still	p-image → p-video
avatar	Talking head	p-image → p-video-avatar

Agent execution

1. Confirm PRUNA_API_KEY is set (and REPLICATE_API_TOKEN only if the chosen route needs Replicate).
2. Apply generation-diversity.md — ritual seed + axis rotation before the first generation.
3. Route from the table above; follow the linked tool skill for HTTP payloads and async polling.
4. For avatar: draft natural voice_script + realistic voice_prompt; get user approval before p-video-avatar.
5. Log prompts, seeds, and output URLs in a short manifest.json beside outputs for reproducibility.

Notes

• Prefer async parallel for video/avatar — poll until succeeded per pruna-api.md.
• Multi-scene work: use dedicated workflow skills — narrated films use scene-anchor-triple.md (narrated-multi-scene).