vcard-skills

Generate polished, consistent shareable card image sets from user-provided content using HTML/CSS plus Playwright screenshots. Use when Codex needs deterministic browser-rendered cards with dense exact text, per-card HTML pages, ratios such as 1:1, 3:4, 9:16, or custom aspect ratios, optional card count, style direction, visual QA scoring, and iterative regeneration. For GPT-image-2-led image cards instead, use `image-card-generator`.

Generate GPT-image-2-led social image card sets from a brief, article, notes, URL, or topic. Use when Codex needs information-first mobile feed image cards, explainers, visual notes, cover cards, or shareable image-card series with saved prompts, direct GPT Image 2 PNG outputs, and visual QA.