← Givon AICONTENT HISTORY

Update to Givon AI

Snapshot Oct 28, 2026 · 13:10 UTC · version 0.6.2

Collection source: downloaded plugin package.

WHAT CHANGED

First saved snapshot

No earlier snapshot is available to establish a change.

Save Givon AI and check future changes in Following.

Up to 10 plugins free · no card required.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "description": "Start here for any marketplace card or slide (Wildberries, Ozon and similar), one slide or a set: plan each image's purpose, content and reference roles; alone it covers a simple slide with a short headline. Load selling-slide-composition only for a set of two or more slides, card-text-in-image only for in-frame text beyond one short headline. Not needed for listing text outside the image.",
  "included_files": [],
  "name": "marketplace-card-assets",
  "skill_md_contents": "---\nname: marketplace-card-assets\ndescription: \"Start here for any marketplace card or slide (Wildberries, Ozon and similar), one slide or a set: plan each image's purpose, content and reference roles; alone it covers a simple slide with a short headline. Load selling-slide-composition only for a set of two or more slides, card-text-in-image only for in-frame text beyond one short headline. Not needed for listing text outside the image.\"\nmetadata:\n  version: skill-render-ea6bd93365667f6d\n---\n\n# Planning marketplace card images\n\nDetermine the set from the request, the placement goal and the available materials. The result is\na list of specific images to prepare, each with a clear purpose. A single slide is a set of one.\n\n## Possible image roles\n\n- a cover or main frame;\n- an additional angle or a close-up detail;\n- the product in use or in a setting;\n- the package contents;\n- an infographic with the content the user specified;\n- a rich/A+ module or another page block.\n\nThis is professional vocabulary for describing the result. The current task decides the set;\nname the chosen roles in words the user understands.\n\n## Planning result\n\nFor each image, record its purpose, its content, the references it uses and the marketplace\nrequirements that matter. For a series, add a shared visual direction only as far as coherence\nneeds it. Choose the model, format and parameters by the current catalog and schema.\n\n## One slide with this method alone\n\nFor one slide with a short headline or offer, this method is enough:\n\n- Decide what the buyer should notice first and scale the product, the text and the free space\n  around that priority.\n- Put the lettering on a clean, calm field: text on a busy or occupied part of the photo gets\n  lost.\n- Place the text and labels around the product, not over its key details (logo, shape, texture).\n- Keep a safe margin from the frame edges, because the marketplace may crop the image or overlay\n  its own UI.\n- Put the in-frame text in quotes exactly as it should appear and check its spelling.\n- For text in the frame, choose the model by the current catalog and its confirmed ability to\n  reproduce lettering.\n- When micro-parameters are missing, choose a consistent style from the product, the niche and\n  the brand, and state the decisions you made.\n\n## When to load another method\n\n- `selling-slide-composition` — only for a set of two or more slides that must share a palette,\n  lettering character, label rhythm and grid.\n- `card-text-in-image` — only for in-frame text beyond one short headline: several lines,\n  bullets, property labels or badges with icons.\n\nOtherwise do not load them. Apply `image-prompt-craft` for the chosen image model.\n"
}

SHA-256 of public snapshot: f59a82c7866dbba19110a6925710ad010322d8c65c4fc058819adc06d64e84db