image-curator

# Image Curator Generates the 4-field metadata that the WordPress publisher requires on every image upload. This is non-optional: without curated metadata, the publisher uploads images with empty caption + description fields, and the media library record is SEO-incomplete. ## Inputs - `workspace/{task_id}/outline.json` — section context for each slot - `workspace/{task_id}/image_slots.json` — slot allocation (cover + sections) - `workspace/{task_id}/image_prompts.json` — the prompts used to generate each image - `workspace/{task_id}/research.json` — entity intelligence, primary keyword - `projects/{slug}/brand/brand-config.json` — brand voice, banned competitor mentions ## Output `workspace/{task_id}/image_metadata.json`: ```json [ { "media_id": null, "slot": "cover", "title": "{primary_keyword} {short_context}", "alt_text": "{accessibility-first description, ~120-180 chars, contains primary keyword naturally}", "caption": "{one short sentence visible under image, ~120-160 chars, reader-facing context}", "description": "{paragraph-length 400-1000 chars, includes technical entities + primary keyword + image's significance — populates the attachment page body}" }, ... ] ``` `media_id` is null at this stage; the publisher populates it after the upload returns the WP media ID. ## The four-field discipline All four fields are required on every image. Each serves a distinct SEO + accessibility purpose: | Field | Length | Renders where | Purpo...