| name | photo-art-direction |
| description | Preserve source-specific photographic storytelling when planning, generating, reviewing, or implementing images for websites and mockups. Use with mockup-to-code or image generation when source subject relationships, gaze, environment, copy space, focal geometry, responsive crops, tone, or distinct semantic photo stories must survive instead of becoming generic substitutes. |
Photo Art Direction
Treat each source photo as a spatial story, not a bag of visual keywords. Freeze the story contract before generation, bind every candidate to the exact prompt receipt, and adopt only evidence-backed candidates.
Workflow
- Read the source and implementation constraints. Create one
stories[] entry per semantically distinct source photo or photo field. Never merge stories to save generation calls or reuse one candidate for different stories.
- Record the source path and a verbatim source quote that explains why the photo exists. If no quote exists, keep the plan
blocked; do not invent client intent.
- Map every subject as a normalized
[0,1] zone. Record gaze, relationships, environment, copy spaces, tone, semantic cause-and-effect, and one focal point per responsive frame.
- Write each exact prompt to a UTF-8 file. Issue a pre-generation
prompt-generation-receipt/v1 receipt. When mockup-to-code is available, prefer its scripts/prompt_receipt.py; otherwise emit the same receipt contract. Never cite a prompt that was merely consulted.
- Validate the plan before generation. Do not generate while the validator reports malformed data or unresolved placeholders. A valid pre-generation plan still remains incomplete until candidates are reviewed.
- Generate candidates only when the user authorizes image generation. Preserve identities only when permitted; otherwise preserve roles, relative geometry, gaze logic, and semantic relationships without claiming identity fidelity.
- Review every candidate against all seven axes: subject relationships, gaze, environment, copy space, focal geometry, tone, and semantic story. Record real candidate, comparison, review, and responsive evidence paths.
