ads-audit
Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok…
Strategic paid advertising planning with industry-specific templates. Covers platform selection, campaign architecture, budget planning, creative strategy, and phased implementation roadmap. Use when user says "ad plan", "ad strategy", "campaign planning", "media plan", "PPC
Claude Code
$ npx -y skills add naveedharri/benai-skills --skill ads-plan --agent claude-code
Codex
$ npx skills add naveedharri/benai-skills --skill ads-plan -a codex -y
Cursor
$ npx skills add naveedharri/benai-skills --skill ads-plan -a cursor -y
Gemini CLI
$ npx skills add naveedharri/benai-skills --skill ads-plan -a gemini-cli -y
GitHub Copilot
$ npx skills add naveedharri/benai-skills --skill ads-plan -a github-copilot -y
OpenCode
$ npx skills add naveedharri/benai-skills --skill ads-plan -a opencode -y
Windsurf
$ npx skills add naveedharri/benai-skills --skill ads-plan -a windsurf -y
name: ads-plan description: > Strategic paid advertising planning with industry-specific templates. Covers platform selection, campaign architecture, budget planning, creative strategy, and phased implementation roadmap. Use when user says "ad plan", "ad strategy", "campaign planning", "media plan", "PPC strategy", or "advertising plan". disable-model-invocation: true
Check for `./branding.md` in the project root.
**If found:** Load brand identity, voice, audience, visual guidelines, competitor positioning. Confirm with the user: "I found your brand context (branding.md). Using it for this plan." Skip to step 1.
**If not found:** Collect brand context before proceeding. This information shapes every downstream step — platform selection, creative strategy, audience targeting, and budget allocation.
> "Before building your ad strategy, I need to understand your brand. What's your brand name and website URL?"
Ask for the brand name and website URL first. If the user provides a URL, immediately run the full website extraction (step 0.2) before asking any further questions. Everything that can be extracted from the website should be extracted — never ask the user for information that's already on their site.
Also collect (if not already clear from the website):
This is the most important part of brand context setup. **Do not guess or assume anything.** Extract the actual values the business uses on their live website.
Use WebFetch on the homepage URL. Instruct it to extract ALL of the following:
**Visual identity:**
footer. Report exact hex values. Identify which is primary (most prominent brand color, usually on CTAs and headers), secondary, accent, background, and text color.
Look in CSS, `<link>` tags for Google Fonts / Typekit / custom font URLs, and inline styles. Report the exact font names (e.g., "Plus Jakarta Sans", "DM Sans", "Geist"), not generic fallbacks like "sans-serif".
saturated colors? Dark mode? Gradient-heavy? Illustration-driven? Corporate?
**Copy and messaging:**
trust badges, star ratings
"Book a Demo", "See Pricing")
**Brand voice signals:**
If the homepage alone doesn't give a complete picture, also fetch:
Only fetch these if there are genuine gaps after the homepage. Don't fetch for the sake of it.
Show the user everything extracted, organized clearly:
Here's what I found on [website]:
Brand: [name]
Tagline: "[extracted tagline]"
Industry: [detected industry]
Business model: [detected model]
Colors:
Primary: [name] #[hex] — used on [CTAs, headers, etc.]
Secondary: [name] #[hex] — used on [subheadings, etc.]
Accent: [name] #[hex] — used on [highlights, badges, etc.]
Background: #[hex]
Text: #[hex]
Fonts:
Headings: [exact font name]
Body: [exact font name]
Visual style: [description of what you observed]
Button style: [pill/rounded/square], [color], [hover behavior if visible]
Voice: [formal/casual], [serious/playful], [technical/simple]
Hero: "[exact hero headline]"
Value prop: "[extracted value proposition]"
CTAs found: "[CTA 1]", "[CTA 2]", "[CTA 3]"
Social proof: [what's shown — logos, metrics, testimonials]
Does this look right? Anything to correct or add?The user confirms or corrects. Only after confirmation, proceed with remaining questions.
After the website extraction, only ask about things that **could not** be determined from the website. Skip any section where the website gave a clear answer.
**Likely still needed (websites rarely cover these):**
Target audience specifics:
Competitor positioning:
(If skipped, note: "To be completed — run `/ads-competitor` for analysis.")
Ad-specific guidelines:
Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok…
Budget allocation and bidding strategy review across all ad platforms. Evaluates spend distribution, bidding strategy…
Competitor ad intelligence analysis across Google, Meta, LinkedIn, TikTok, and Microsoft. Analyzes competitor ad copy, creative…
Cross-platform creative quality audit covering ad copy, video, image, and format diversity across all platforms. Detects creative…
Google Ads deep analysis covering Search, Performance Max, Display, YouTube, and Demand Gen campaigns. Evaluates 74 checks across…
Landing page quality assessment for paid advertising campaigns. Evaluates message match, page speed, mobile experience, trust…
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…