naveedharri/benai-skills/ads-plan
Claude Code and agent skill by naveedharri/benai-skills
- community
Checking that the SKILL.md file is still in the repository.
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".
Install
npx vskill@latest install naveedharri/benai-skills/ads-planSKILL.md
Strategic Paid Advertising Plan
Process
0. Brand Context Setup
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?"
0.1 — Brand Identity + Website (required)
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):
- Industry
- Business model (SaaS, e-commerce, service, B2B, B2C, hybrid)
0.2 — Website Extraction (when URL provided)
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.
0.2a — Fetch the homepage
Use WebFetch on the homepage URL. Instruct it to extract ALL of the following:
Visual identity:
- All colors used prominently: backgrounds, buttons, headers, links, text, borders,
footer. Report exact hex values. Identify which is primary (most prominent brand color, usually on CTAs and headers), secondary, accent, background, and text color.
- Font families: read the actual
font-familydeclarations used on headings and body text.
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".
- Logo: describe the logo from the header/nav. Note if it's text-based, icon-based, or both.
- Visual style: describe what you observe — is it minimal with lots of whitespace? Bold with
saturated colors? Dark mode? Gradient-heavy? Illustration-driven? Corporate?
- Button styles: rounded, square, pill-shaped? What color? What text color on buttons?
- Spacing and density: tight and information-dense, or airy and spacious?
Copy and messaging:
- Tagline / slogan: extract from the hero section
- Hero headline: the main H1 or hero text
- Value proposition: what the homepage says they do and why it matters
- Key benefits: any benefit sections, feature highlights, or selling points
- Social proof: testimonials, customer logos, metrics ("10,000+ customers"), awards,
trust badges, star ratings
- CTAs: every call-to-action button text on the page (e.g., "Get Started Free",
"Book a Demo", "See Pricing")
- Navigation items: main nav labels reveal product/service categories and priorities
Brand voice signals:
- Tone of the copy: formal or casual? Technical or plain? Playful or serious?
- Person: first person ("We help...") or second person ("You can...") or third?
- Specific words/phrases: any repeated brand language, trademarked terms
0.2b — Fetch additional pages (if needed)
If the homepage alone doesn't give a complete picture, also fetch:
/aboutor/about-us— for company story, mission, team info, more voice signals/pricing— for pricing model (free trial, freemium, contact-us, subscription tiers)
Only fetch these if there are genuine gaps after the homepage. Don't fetch for the sake of it.
0.2c — Present extraction to user
Show the user everything extracted, organized clearly:
The user confirms or corrects. Only after confirmation, proceed with remaining questions.
0.3 — Fill gaps with 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:
- Who is your primary customer? (job title/role, age range)
- What are their biggest pain points?
- What motivates them to buy?
- Where do they spend time online?
- Secondary audience?
Competitor positioning:
- Who are your top 2-3 competitors?
- How are you different from each?
(If skipped, note: "To be completed — run /ads-competitor for analysis.")
Ad-specific guidelines:
- Preferred CTAs (pre-fill from extracted CTAs, ask user to confirm/adjust)
- Show pricing in ads?
- Required elements? (trust badges, ratings, certifications)
- Anything forbidden in ads?
Brand voice refinement (if the website extraction was ambiguous):
- Words or phrases you always use?
- Words or phrases you never use?
Do NOT ask about colors, fonts, tagline, visual style, or value proposition if the website extraction already captured them. Only ask if the extraction was inconclusive.
0.4 — No-URL fallback
If the user does not provide a website URL, fall back to asking all questions manually:
Visual identity:
- Brand colors (primary, secondary, accent — hex codes)
- Headline and body fonts
- Visual style description
- Logo description
Copy and messaging:
- Tagline or slogan
- One-sentence value proposition
- Top 3 benefits with proof points
- Social proof highlights
Brand voice:
- Formal vs casual (1-10)
- Serious vs playful
- Technical vs simple
- Brand words (always use)
- Forbidden words (never use)
Target audience, competitor positioning, and ad guidelines — same as step 0.3.
0.5 — Save branding.md
Write ./branding.md in the project root using the canonical format from ads/references/brand-context.md.
Every value in branding.md must come from the website extraction or the user's direct answers. Never fill in defaults or placeholders. If a field has no data, leave it blank or omit the section entirely.
Validate before writing:
- Brand name is not empty
- At least one color with hex value exists
- At least one audience description exists
- Business model is identified
Display summary:
Note: Many of these answers feed directly into step 1 (Discovery) — do not re-ask questions the user already answered. Carry forward business type, audience, goals, and budget context.
1. Discovery
- Carry forward from step 0: business type, target audience, value proposition
- Current advertising status (active platforms, spend, performance)
- Goals: brand awareness, lead generation, e-commerce sales, app installs
- Budget range (monthly/quarterly)
- Timeline and urgency
- In-house team capacity vs agency needs
2. Competitive Analysis
- Identify top 3-5 competitors
- Analyze their ad presence across platforms (Google Ads Transparency, Meta Ad Library)
- Estimate competitor spend levels and platform mix
- Identify messaging themes and creative approaches
- Note keyword/audience gaps (opportunities competitors are missing)
3. Platform Selection
- Load industry template from
assets/directory - Match business type to recommended platform mix
- Read
ads/references/budget-allocation.mdfor platform selection matrix - Read
ads/references/conversion-tracking.mdfor tracking setup requirements - Assess platform fit based on:
- Target audience demographics per platform
- Product/service type suitability
- Budget requirements per platform (minimums)
- Sales cycle length and attribution needs
- Creative capabilities and content availability
4. Campaign Architecture
Naming Convention
Example: META_CONV_Prospecting_US_2026Q1
Campaign Structure Template
5. Budget Planning
Monthly Budget Distribution
Read ads/references/budget-allocation.md for the 70/20/10 framework.
| Tier | Allocation | Purpose | |
|---|---|---|---|
| Proven (70%) | Primary platforms with proven ROI | Revenue engine | |
| Scaling (20%) | Platforms showing promise | Growth engine | |
| Testing (10%) | New platforms or strategies | Innovation |
Budget Pacing
- Month 1-2: heavy testing, expect higher CPA (learning)
- Month 3-4: optimize based on data, tighten targeting
- Month 5-6: scale winners, kill losers, expand
- Ongoing: 70/20/10 maintenance with quarterly reviews
6. Creative Strategy
Content Pillars
- Pain Point: address specific problems your audience faces
- Social Proof: testimonials, case studies, reviews
- Product Demo: show the product/service in action
- Offer: promotions, free trials, lead magnets
- Education: teach something valuable related to your product
Creative Production Plan
| Priority | Asset Type | Platforms | Quantity | |
|---|---|---|---|---|
| P1 | Product/service videos (15-30s) | Meta, TikTok, YouTube | 5-10 | |
| P2 | Static images with copy | Google, Meta, LinkedIn | 10-15 | |
| P3 | Carousel/collection | Meta, LinkedIn | 3-5 | |
| P4 | UGC/testimonial video | TikTok, Meta | 3-5 | |
| P5 | Long-form video (1-3 min) | YouTube | 2-3 |
Brand-Aware Creative Production
If branding.md is available, personalize CREATIVE-BRIEF.md with:
- Ad copy written in brand voice (tone dimensions from Brand Voice section)
- Visual descriptions referencing brand colors (hex values) and typography
- CTAs pulled from approved CTA list (Ad-Specific Guidelines)
- Headlines using brand words; avoiding forbidden words
- Audience messaging mapped to primary/secondary persona pain points
- Competitor differentiation woven into positioning
Read ads/references/creative-volume.md for per-platform volume requirements.
7. Tracking Setup Plan
Before launching any ads, ensure tracking is configured:
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingshared-skills/ads-plan/SKILL.md
Popularity
- Repository stars
- 61
- Repository forks
- 26
- 7-day trend score
- 21
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/naveedharri/benai-skills/ads-plan)