blender-art-direction-intake git:20260907.4a1e3c8A

Immutable. This exact content is served forever at /api/v1/blob/dc4e4b7694bbf789.

---
name: blender-art-direction-intake
description: Clarify a Blender creation request and optionally generate a concept/mockup image before modeling. Use before modeling, procedural scene creation, rendering, simulation, or character work when art style, subject, scale, platform, shot, materials, constraints, or reference direction are unclear.
---

# Blender Art Direction Intake

Read [the shared execution guidance](references/astra-workflow.md) once per task
for autonomous decisions, evidence cadence, and long-task continuity.

Resolve the visual contract from the request, supplied references, and existing
scene. Record routine assumptions and start authorized work; a missing field
does not by itself require a question or a user-approved contract.

## Clarify the brief

Consider these decisions, asking only about consequential unresolved choices
for which context provides no reasonable default:

- subject, purpose, platform, scale, and export target;
- art style, reference period/genre, level of realism, and visual priorities;
- required parts, materials, colors, logos/text, motion, and interaction;
- camera/view requirements, lighting/mood, and whether the result is for a
  single shot, turntable, animation, or runtime asset;
- performance, topology, rigging, simulation, and delivery constraints.

If a choice is still open, use a concrete default and label it as an assumption.
Wait on the dependent work only when a missing answer would cause substantial
rework and no reasonable default is available. Continue independent work.
Respect explicit requests for consultation or approval at stage boundaries.

## Offer optional concept generation

When requested, or when a concept would resolve a consequential visual
ambiguity, offer an optional image-generation pass. Do not routinely interrupt
an actionable modeling brief with a concept offer. A concept is not a
prerequisite for geometry:

> I can generate a concept/mockup reference before modeling; it will guide
> silhouette, materials, palette, and camera—not become the final 3D asset.

When accepted, generate one focused concept using the agreed subject, style,
material palette, environment, camera, and exclusions. Inspect it with the
user, then record what is binding (silhouette, palette, major forms, mood) and
what remains flexible. Do not imply image generation guarantees manufacturable
geometry, clean topology, rigging, or a usable texture set.

## Hand off

Write a short working contract with the resolved decisions, assumptions,
reference-image path if any, and review questions. Then invoke the smallest
appropriate workflow: modeling, procedural, rendering, simulation, character,
or animation.