Communitygithub.com

modbender/skill-library-mcp

Generate landing page content from PRD — hero section, features, A/B headline variants, CTA, and SEO meta tags. Use when user says "create landing page", "write landing copy", "hero section", "A/B headlines", or "landing content". Can scaffold actual pages for astro-static. Do NOT use for SEO auditing (use /seo-audit).

O que é skill-library-mcp?

skill-library-mcp is a Claude Code agent skill that generate landing page content from PRD — hero section, features, A/B headline variants, CTA, and SEO meta tags. Use when user says "create landing page", "write landing copy", "hero section", "A/B headlines", or "landing content". Can scaffold actual pages for astro-static. Do NOT use for SEO auditing (use /seo-audit).

Funciona com~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/modbender/skill-library-mcp/tree/HEAD/data/solo-landing-gen

Perguntar na sua IA favorita

Abre um novo chat com esta habilidade de agente já pré-carregada.

Documentação

/landing-gen

Generate landing page content from a project's PRD. Produces hero section, features, social proof, CTA, SEO meta tags, and A/B headline variants. If astro-static stack detected, can scaffold actual page files.

MCP Tools (use if available)

  • kb_search(query) — find related methodology (conversion, copywriting)
  • project_info(name) — get project stack and details
  • web_search(query) — competitor landing analysis

If MCP tools are not available, fall back to Glob + Grep + Read.

Steps

  1. Parse project from $ARGUMENTS.

    • Read PRD, README, or research.md for product info.
    • If empty: ask via AskUserQuestion.
  2. Detect stack:

    • Check for astro.config.* → astro-static (can scaffold page)
    • Check for next.config.* → Next.js (can scaffold route)
    • Otherwise: generate content-only markdown
  3. Extract landing inputs from PRD/README:

    • Problem: 1 sentence pain statement
    • Solution: 1 sentence product description
    • ICP: Target user persona
    • Features: Top 3-4 differentiating features with descriptions
    • Competitors: From research.md (if exists) — for positioning
    • Pricing: If available
  4. Competitor landing analysis (optional, if MCP/WebSearch available):

    • Search for top 3 competitor landing pages
    • Note: headline patterns, CTA language, social proof types
    • Identify positioning gaps
  5. Forced reasoning — conversion strategy: Before generating, write out:

    • Primary conversion: What's the ONE action? (sign up / download / buy)
    • Objections: Top 3 reasons someone wouldn't convert
    • Trust signals: What overcomes each objection?
    • Above the fold: Problem + Solution + CTA — nothing else
  6. Generate landing content:

    6a. Hero Section

    • Headline: Problem-focused, benefit-driven (8-12 words)
    • Subheadline: How the product solves it (15-25 words)
    • CTA button: Action verb + outcome ("Start Free Trial", "Download Now")
    • Visual: Describe what image/screenshot/demo should be shown

    6b. A/B Headline Variants (5 options)

    Generate 5 distinct headline approaches:

    1. Pain-focused: "Tired of {problem}?"
    2. Benefit-focused: "{Outcome} without {hassle}"
    3. Curiosity: "The {adjective} way to {action}"
    4. Social proof: "Join {N}+ {users} who {outcome}"
    5. Direct: "{Product}: {one-line value prop}"

    6c. Features Section (3-4 features)

    For each feature:

    • Icon suggestion (emoji or icon name)
    • Feature title (3-5 words)
    • Feature description (1-2 sentences)
    • Benefit framing (what user gains, not what product does)

    6d. Social Proof Section

    • Placeholder for testimonials (template with name, role, quote)
    • Metrics placeholders ("X+ users", "Y% faster", "Z countries")
    • Trust badges placeholder (App Store rating, awards, press)

    6e. CTA Section

    • Repeat headline (or variation)
    • CTA button (same as hero)
    • Risk reducer ("Free forever" / "No credit card" / "Cancel anytime")

    6f. SEO Meta Tags

    <title>{title — 50-60 chars}</title>
    <meta name="description" content="{description — 150-160 chars}">
    <meta property="og:title" content="{og title}">
    <meta property="og:description" content="{og description}">
    <meta property="og:image" content="{suggest image dimensions 1200x630}">
    <meta property="og:type" content="website">
    
  7. Write output:

    If astro-static detected: scaffold page at src/pages/index.astro or new route.

    Otherwise: write to docs/landing-content.md:

    # Landing Page Content: {Project Name}
    
    **Generated:** {YYYY-MM-DD}
    **Primary CTA:** {action}
    **Target ICP:** {persona}
    
    ## Hero
    **Headline:** {headline}
    **Subheadline:** {subheadline}
    **CTA:** {button text}
    **Visual:** {description}
    
    ## A/B Headlines
    1. {variant 1}
    2. {variant 2}
    3. {variant 3}
    4. {variant 4}
    5. {variant 5}
    
    ## Features
    {features with icons and descriptions}
    
    ## Social Proof
    {templates and placeholders}
    
    ## Final CTA
    {closing section}
    
    ## SEO Meta Tags
    {html meta tags}
    
    ---
    *Generated by /landing-gen. Fill in social proof, add visuals, then publish.*
    
  8. Output summary — headline, CTA, and suggested next steps.

Notes

  • Headline should be testable — run A/B with 2-3 variants
  • "Above the fold" = hero only — don't overload
  • Social proof is placeholder — fill with real data as it comes
  • For fake-door tests: hero + CTA + email capture is enough (2-hour launch)
  • Works with /seo-audit — generate content, then audit the deployed page

Common Issues

No PRD or product info found

Cause: Project lacks docs/prd.md or README with product description. Fix: Run /validate to generate PRD first, or provide a README with problem/solution/features.

Headlines too generic

Cause: Weak problem statement or missing competitor differentiation. Fix: Add research.md with competitive analysis. Specific pain points produce specific headlines.

Stack not detected for page scaffolding

Cause: No astro.config.* or next.config.* found. Fix: Skill outputs content-only markdown by default. To get actual page files, ensure the project uses astro-static or nextjs-supabase stack.

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

modbender/skill-library-mcp

Native video analysis using Google Gemini API. Upload and analyze video files — describe scenes, extract text/UI, answer questions about content, transcribe speech, identify objects and actions. Use when: (1) User sends a video file and wants it analyzed, (2) Video summarization or description needed, (3) Extracting text, UI elements, or information from screen recordings, (4) Answering questions about video content, (5) Comparing multiple videos, (6) Analyzing tutorials, demos, or walkthroughs.

modbender/skill-library-mcp

Complete investment portfolio risk management system. Analyze positions, calculate risk metrics, stress test scenarios, optimize allocations, and generate institutional-grade risk reports — all wit...

modbender/skill-library-mcp

Borrow from Aave via credit delegation. Agent self-funds by borrowing against delegator collateral. Supports borrow, repay, health checks. Works on Aave V2/V3.

modbender/skill-library-mcp

Discover and register autonomous AI agents. Use when: browsing the agent registry, submitting an agent for verification, or embedding agent badges. NOT for: general web search or agent capability analysis.

modbender/skill-library-mcp

Create AI avatar and talking head videos with OmniHuman, Fabric, PixVerse via inference.sh CLI. Models: OmniHuman 1.5, OmniHuman 1.0, Fabric 1.0, PixVerse Lipsync. Capabilities: audio-driven avatars, lipsync videos, talking head generation, virtual presenters. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human

modbender/skill-library-mcp

AI代码编辑器规则模板集合 - 为Cursor、Windsurf、Claude Code、Cline等AI编辑器提供项目规则配置。适用于需要配置AI编码助手规则的开发者,包含全栈Web、移动端、Vue3+SpringBoot等技术栈模板。

modbender/skill-library-mcp

Generate landing page code from product descriptions

modbender/skill-library-mcp

Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video

modbender/skill-library-mcp

Generate AI music videos end-to-end. Creates music with Suno (sunoapi.org), generates visuals with OpenAI/Seedream/Google/Seedance, and assembles into music video with ffmpeg. Supports timestamped lyrics (auto SRT), Suno native music video generation, slideshow/video/hybrid modes. Token-based cost tracking per generation.

modbender/skill-library-mcp

Generate AI-powered notes from videos (document, outline, or graphic-text formats)

modbender/skill-library-mcp

The video AI notes tool is provided by Baidu. Based on the video download address provided by the user, it downloads and parses the video, and finally generates AI notes corresponding to the video (a total of three types of notes can be generated: document notes, outline notes, and image-text notes).

modbender/skill-library-mcp

Bird identification, life list tracking, and trading card generation. Use this skill when the user: sends a bird photo to identify, says "set up my Birdfolio" or "set my region", asks "how's my checklist", asks "Birdfolio progress", asks "how many birds have I found", asks "show my Birdfolio" or "show my life list", asks "what's my rarest bird", or asks "tell me about [bird species]". Handles everything from first-time setup through ongoing life list tracking and visual trading card generation.

modbender/skill-library-mcp

Track stock and crypto portfolios with CLI - real-time prices, P&L, dividend tracking, multiple portfolios

modbender/skill-library-mcp

Track cryptocurrency portfolios with real-time prices, P&L calculations, and allocation analysis. Query Bitcoin, Ethereum, Solana and 10,000+ token holdings.

modbender/skill-library-mcp

加密貨幣Portfolio追蹤 - 支援TRON/ETH/BSC,分析持倉、收益、Gas費用

modbender/skill-library-mcp

Lead strategy with competitive analysis, strategic planning, growth roadmaps, and business portfolio management.

modbender/skill-library-mcp

Query land ownership, leases, landlord info, and land payments. Write operations for payment management and lease renewals.

modbender/skill-library-mcp

Expert in building portfolios that actually land jobs and clients - not just showing work, but creating memorable experiences. Covers developer portfolios, designer portfolios, creative portfolios, and portfolios that convert visitors into opportunities. Use when: portfolio, personal website, showcase work, developer portfolio, designer portfolio.

modbender/skill-library-mcp

Generate a beautiful HTML landing page from your package.json. Use when you need a quick marketing page for your project.

modbender/skill-library-mcp

Build a single-page landing page from a text prompt or design brief. USE WHEN: - User asks for a landing page, marketing page, product page, sales page, or startup website - User provides a business name/idea and wants a deployable web page - User sends an HTML template and wants it adapted with new content/branding - User asks for a "one-pager" or "single-page site" DON'T USE WHEN: - User wants a multi-page website (use a web framework instead) - User wants an email template or newsletter (different format/constraints) - User wants a blog, documentation site, or wiki - User wants to edit an existing live site (this builds new pages, not patches) - User wants a web app with backend logic, auth, or databases OUTPUTS: Single self-contained .html file (no external dependencies except Google Fonts). Ready to open in browser, deploy to any static host, or deliver to a client. INPUTS: Business name, what it does, target audience, desired tone. Optionally: a reference HTML template to adapt.

Habilidades Relacionadas