Skip to content
SkillModel-led163 tokens in use

Brand Profile Extraction

Builds a public-safe brand and offer profile for paid ads from an authorized website, keeping what it saw apart from what it infers.

11,191 stars on the repository MIT LicenseAgriciDaniel/claude-ads · skills/ads-dna
/plugin marketplace add agricidaniel/claude-ads /plugin install claude-ads@ai-marketing-hub-claude-ads
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Brand Profile Extraction costs

55tokens idle
163tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Fair
  • Frontmatter12/15
  • Structure11/25
  • Examples0/15
  • Output7/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity84
  • Maintenance100
  • Community56
  • Maturity32
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers