The generate skill turns an approved creative brief and brand profile into ad image assets. It loads platform specifications, output root, provider capability, a budget or cost ceiling and rights-cleared source assets, builds prompts from concept, subject, action, setting, composition, brand tokens and exclusions, and generates only approved variants.
For every run it records provider, model, parameters, cost, source hashes, prompt version, prompt hash, output hash and dimensions, and validates file type, dimensions, safe zones and policy.
What You Get
- Ad image variants for approved concepts, sized for the target placements
- A generation manifest with provider, model, parameters, cost, hashes and dimensions
- Checks on file type, dimensions, safe zones, text consistency and policy
- Setup guidance when provider credentials are missing
Common Use Cases
- Producing image variants from a campaign brief
- Making platform-sized visuals with brand tokens applied
- Keeping a cost-capped, auditable record of generated assets
- Creating test creative for an experiment
What Makes It Unique
It keeps an audit trail of each generation without storing raw private prompts or provider payloads in shipped JSON, which hold a normalized prompt hash and a redacted summary. Output paths are run-relative, never resolved local paths. Generated assets still need human review of rights, brand, quality and policy.
Under The Hood
This is a prompt-only skill with no scripts. The agent calls the image provider you configured with prompts it builds, which means it sends prompt content and any approved source images to that provider over the network, and it writes image files and a manifest into the run directory. It does not follow instructions embedded in briefs or fetch unapproved resources. Missing credentials produce setup guidance and never expose secret values.