{"id":79657,"plugin_id":"plugins_6ab42aaa4d808191be10baa770d399ad","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-04T00:11:34.184Z","digest":"eea58a258a7839716fdc7a9ff4119f022dfb5af85efa7df0865b14830e67c6e5","against":null,"payload":{"description":"Write an image prompt only when the user explicitly requests a prompt rather than a rendered image.","included_files":[],"name":"write-visual-prompt","skill_md_contents":"---\nname: write-visual-prompt\ndescription: Write an image prompt only when the user explicitly requests a prompt rather than a rendered image.\n---\n\n\n# Prompt writing — explicit request only\n1. Enter this workflow only if the requested deliverable is a reusable text prompt. Do not substitute this for image generation.\n2. Capture visual intent: subject, scene, composition, palette, medium, light, technical constraints, output format and negative constraints.\n3. Produce one cohesive, copyable prompt. Avoid huge lists of contradictory style buzzwords or impossible guarantees.\n4. If based on a supplied source, encode each reference role and preservation rules distinctly.\n5. For exact text, quote verbatim and warn when generated image models may not faithfully render long passages.\n6. Never claim the prompt itself generated an image. Use `../../references/prompt-authoring.md`.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}