Builds the Product Hunt gallery as a five-beat visual story - 5-8 slides at 1270x760 under 3MB each with the roles hook, workflow, differentiator, proof, CTA - plus an animated 240x240 thumbnail designed to survive the roughly 80px feed render. Use when someone asks "design our Product Hunt gallery images", "what should our Product Hunt thumbnail be", "what order should our launch gallery slides go in", or "make our launch gallery tell a story instead of dumping screenshots". Do NOT use for launch timing, taglines, hunter strategy, or the maker comment - use product-hunt-launch instead; for the launch video, use product-demo-director; for the X and LinkedIn launch images, use social-image-designer; frames come from marketing-screenshot-craft.
---
name: product-hunt-gallery-designer
description: Builds the Product Hunt gallery as a five-beat visual story - 5-8 slides at 1270x760 under 3MB each with the roles hook, workflow, differentiator, proof, CTA - plus an animated 240x240 thumbnail designed to survive the roughly 80px feed render. Use when someone asks "design our Product Hunt gallery images", "what should our Product Hunt thumbnail be", "what order should our launch gallery slides go in", or "make our launch gallery tell a story instead of dumping screenshots". Do NOT use for launch timing, taglines, hunter strategy, or the maker comment - use product-hunt-launch instead; for the launch video, use product-demo-director; for the X and LinkedIn launch images, use social-image-designer; frames come from marketing-screenshot-craft.
---
# product-hunt-gallery-designer
Voters skim the gallery like a story, and the 240x240 thumbnail is the only asset competing for the click at roughly 80px in the feed. The costly mistake is the screenshot dump: a random pile of UI captures that forces the voter to do the synthesis themselves - they simply do not. This skill casts the gallery as a five-beat visual story, each slide answering the objection the previous slide raised, and designs the one moving asset that earns the click in the first place.
## Operating procedure
Work the steps in order: beats before art, because each slide exists to answer the next objection in sequence and art laid down first locks the wrong order in; the thumbnail comes last because it compresses the strongest beat, and the strongest beat is unknown until the story is cast.
### Step 1: Gather the charter and the launch inputs
Ask for these before designing anything. If any input is a guess, label it a guess and move on.
1. **Charter**: the client's charter block, in the format defined in premium-design-foundations. Paste the charter block if one exists. If the client has a charter but the foundations pack is not installed, elicit the needed values directly and label them provisional. If no charter exists at all, halt and route to premium-design-foundations - never substitute worked-example values.
2. **Promise**: the one-line promise the launch makes.
3. **Workflow**: the hero workflow the product will be judged on.
4. **Differentiator**: what this product does that the named alternative does not - name the alternative.
5. **Proof**: the strongest available evidence - a metric, a testimonial, a before/after - with its date and source. An undated number is unusable as evidence.
6. **Launch context**: timing, tagline, and hunter plan from product-hunt-launch. This skill consumes those decisions, it never makes them.
### Step 2: Cast the five beats