ads-dna
The ads-dna skill extracts brand identity elements from a website URL to generate a structured brand-profile.json file. It analyzes visual identity, tone of voice, color palettes, typography, and imagery styles to support consistent creative generation for advertising campaigns.
Is ads-dna safe to install?
Review the source first: our audit of ads-dna's source files found 4 shell commands, 1 external URL, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes shell commands to capture screenshots and writes a brand-profile.json file to the local directory.
How we audit skills: our security review methodology.
Who is this skill for?
Users of Claude Code who need to maintain brand consistency across generated advertising creative.
What can you do with it?
- Extracting brand voice and visual style from a company website.
- Generating a brand-profile.json file for use with other /ads commands.
- Capturing website screenshots to serve as visual style references for AI image generation.
How good is this skill?
Quality score: 9/10. The skill provides clear, structured instructions and a well-defined schema for the output. It includes robust fallback logic for missing content and errors.
What does the skill file contain?
# Ads DNA: Brand DNA Extractor Extracts brand identity from a website and saves it as `brand-profile.json` for use by `/ads create`, `/ads generate`, and `/ads photoshoot`. Brand DNA extraction is OBSERVE and LISTEN made concrete (see the **10-Principle Thinking Framework** in `ads/references/thinking-framework.md`). The website is the input; the brand profile is what the site is *saying* about itself when no one is curating the message. Listen to the voice before you label it. Observe the visual choices before you classify them. ## Quick Reference | Command | What it does | |---------|---...
Frequently asked questions
What information does the skill extract from a website?
It extracts visual identity, tone of voice, color palette, typography, imagery style, and structured metadata like Open Graph tags and schema.org markup.
How does the skill determine the brand voice?
It analyzes hero headlines, subheadlines, About page content, and CTA buttons against specific heuristics, such as sentence length, use of technical jargon, and emotional versus rational language.
Can I skip the screenshot capture process?
Yes, using the --quick flag skips both the secondary page fetching and the screenshot capture process.
What happens if the skill cannot find specific brand elements?
It assigns a null value to those fields in the brand-profile.json file rather than guessing.
Related skills
lark-workflow-meeting-summary
219.7KUsers who need to summarize meeting minutes, generate weekly reports, or review meeting history within the Lark ecosystem
The lark-workflow-meeting-summary skill provides a structured workflow for agents to aggregate meeting minutes from Lark VC, generate summaries, and create or update reports in Lark Docs.
programmatic-seo
83.5KContent strategists, SEO specialists, and marketers building large-scale, data-driven website content
The programmatic-seo skill provides a framework for generating SEO-optimized pages at scale using templates and data. It guides users through keyword research, data sourcing, template design, internal linking, and indexation strategies while emphasizing content uniqueness to avoid search engine penalties.
brandkit
71.8KDesigners, art directors, and brand strategists who need to generate professional, cohesive brand identity presentations
The brandkit skill generates high-end brand identity boards, including logo systems, visual-world presentations, and brand-guideline decks. It focuses on minimalist, cinematic, and strategic design, providing structured layouts for various brand categories like developer tools, security, and luxury services.
ad-creative
64.0KPerformance marketers, growth teams, and advertisers who need to produce ad copy at scale or optimize existing ad creative
The ad-creative skill generates, iterates, and scales ad copy for paid advertising platforms including Google, Meta, LinkedIn, TikTok, and Twitter. It provides frameworks for creating ad headlines, descriptions, and primary text based on product context and performance data.