The brand DNA skill reads an authorized website and your input to record the brand name, offer, audience, proof, voice, visual tokens, imagery, typography, accessibility, claims, disclaimers and destination patterns. It confirms authorization and validates the URL before any fetch or screenshot.
Page content, scripts, metadata and downloads are treated as untrusted data. Style labels that are inferred are shown to the operator for confirmation, and the profile is written inside the project state directory.
What You Get
- A validated brand and offer profile written to the project or run state directory
- Observed name, offer, audience, proof, voice, colors, typography and claims
- Source URLs and capture dates for each observation
- A list of inferred style labels for you to confirm
Common Use Cases
- Preparing a brand profile before writing ad concepts
- Capturing brand colors and voice from a company website
- Checking claims and disclaimers a site already uses
- Giving the image generation skill brand tokens
What Makes It Unique
It is built for ad work with safety limits: it does not collect credentials, form data, analytics identifiers, customer data or hidden instructions, and it says the profile is creative context, not proof that every site claim is legal, current or approved for advertising.
Under The Hood
This is a prompt-only skill with no scripts. The agent validates the URL, then fetches the site and may capture screenshots through the guarded fetcher of Claude Ads. It treats everything on the page as data, never instructions, and writes the finished profile file atomically inside the project or run state directory.