social-marketing-asset-generatorlisted

Produces a finished social/marketing image asset — a social graphic, banner, or display ad — with its headline, subhead, CTA, and brand mark baked directly into the pixels by Ideogram, not composited afterward. Use when the user asks something like "make me an Instagram ad for X," "banner ad for our launch," "social graphic announcing Y," or "give me this in Story + Feed + LinkedIn sizes." Triggers only on explicit request for finished ad/banner/social-graphic creative — it is not auto-wired from `brand-identity-sheet`, `logo-prompting`, `moodboard-generator`, or `character-model-sheet`, and does not fire just because one of those skills ran. It is a sibling to, not a replacement for, those four skills — they establish or explore brand truth (a moodboard, a locked identity system, a single mark, a character sheet); this skill spends an already-decided brand truth and literal copy on one rendered creative asset.
devkindhq/ideogram-ai-toolkit · ★ 2 · AI & Automation · score 70

Install: claude install-skill devkindhq/ideogram-ai-toolkit

# Social Marketing Asset Generator This skill's differentiation angle: baked-in typography via structured JSON captioning, not the generate-text-free-then-composite-in-HTML/CSS pattern every confirmed competitor in this space uses. Ideogram renders the scene and the headline/subhead/CTA typography together in one call, leaning into its specific strength — reliable in-image text rendering with full control over placement, size, weight, and color. See `references/typography-baking-discipline.md` for the full writeup of why this beats the composite-afterward approach, and what it costs (garbled-text risk, caught and regenerated against rather than accepted). This is a prompt-composition skill — same family as `logo-prompting`, `brand-identity-sheet`, and `moodboard-generator` — not an MCP-orchestration skill. Its center of gravity is composing a legible, on-brand, on-copy JSON caption; the MCP calls it chains (`generate_image` → optional `generate_images_bulk` fan-out → optional `edit_image` touch-up) exist to serve that composition, not the other way around. It is not a copywriting or ad-strategy skill. It accepts literal copy — headline, subhead, CTA, offer/price if any — as intake and renders it. It never runs AIDA/PAS strategy frameworks, writes ad copy unprompted, or invents a claim, price, or offer that wasn't supplied. A rendered image with a fabricated discount figure or an unapproved claim baked into the pixels is a real failure this skill guards against, not a nice-