ugc-storyboard-sheet
Skill4 starsChanged 5 months agoMITView on GitHub
Step 3 of the ugc-ad pipeline. Generate ONE 16:9 storyboard sheet holding three side-by-side 9:16 panels (Hook / Setup-Action / Recommendation) at framings Tight / Macro / Wide, using the product and character images as references to lock identity. This sheet is the visual narrative map the video model follows. Brand-agnostic.
In this repository7 other files it gives its agents.
- ugc-adSkill
- ugc-base-characterSkill
- ugc-briefSkill
- ugc-enhanceSkill
- ugc-multicut-scriptSkill
- ugc-product-profileSkill
- ugc-videoSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Generate the sheet: Call generate_image:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
ugc-storyboard-sheet
Produces the three-panel storyboard that dictates the ad's scene sequence and locks visual identity.
Inputs
PRODUCT_MEDIA_ID(from ugc-product-profile)CHARACTER_JOB_ID(from ugc-base-character)PROFILE(path to product-profile.md, for the usage steps)DEST(path)
Steps
- Confirm the image model + reference roles. Default
nano_banana_pro(handles multiple reference images + clean layout/text; 16:9 supported, no max on image references). Callmodels_explore(action="get", model_id="nano_banana_pro")to confirm. NOTE (validated 2026-06-22): requestingnano_banana_promay report back as modelnano_banana_2in the job response — this is a server-side alias; references still bind and the 3-panel sheet renders correctly. Not an error. - Generate the sheet. Call
generate_image:model: "nano_banana_pro"aspect_ratio: "16:9",count: 1medias: pass the product and character as references, e.g.[{ "value": "<PRODUCT_MEDIA_ID>", "role": "image" }, { "value": "<CHARACTER_JOB_ID>", "role": "image" }](use the exact role names returned by models_explore).prompt: one horizontal sheet, three equal vertical 9:16 panels side by side, same creator and same product in every panel:- Panel 1 — Hook (Tight): tight selfie-framing of the creator reacting/speaking to camera.
- Panel 2 — Setup/Action (Macro): macro on the creator's hands performing the product's exact usage step (pull from PROFILE).
- Panel 3 — Recommendation (Wide): waist-up wide of the creator holding/presenting the product to camera.
- Poll
job_status; capturejob_id+ URL.
- Download:
curl -fsSL <url> -o "$DEST/storyboard.png".
Output
DEST/storyboard.png + its job_id (report it — the video step uses it as the scene-sequence reference).
Constraints
- Same face + same product packaging in all three panels (that is the whole point — continuity lock).
- Three distinct framings (Tight / Macro / Wide) for dynamic progression.
- 16:9 canvas, three 9:16 panels. Verify the output actually shows three panels before reporting success.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

