본문으로 건너뛰기
cccskills
무료GitHub에 공개

content-asset-creator

Creates beautiful, branded HTML content assets — industry reports, landing pages, comparison sheets, one-pagers — from structured data. Uses Gamma API (preferred), v0.dev Platform API, or a self-hosted HTML template system with Tailwind CSS. Outputs self-contained HTML files that can be hosted as web pages or converted to PDF.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

실행 점수 미검증

설치 방법 보기

포함된 파일(2)

  • SKILL.md8.8 KB
  • skill.meta.json264 B

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Content Asset Creator

Generates beautiful, branded content assets (reports, landing pages, one-pagers) from structured data. Designed for producing lead magnets, industry reports, and marketing collateral programmatically.

Quick Start

Create a 2-page industry report for Juicebox about "The State of AI Recruiting in 2026".
Use these data points: [list stats]. Brand: Juicebox blue, clean modern design.

Inputs

  • Asset type (required) — report, landing-page, comparison, one-pager
  • Content data (required) — structured data for the asset (title, sections, stats, narrative)
  • Brand config (optional) — colors, fonts, logo URL. Defaults to Juicebox brand.
  • Output — HTML file path (default: output/[asset-type]-[date].html)

Asset Types

1. Industry Report (2-3 pages)

A data-forward document with stats, narrative sections, and visualizations.

Input structure:

type: report
title: "The State of AI Recruiting — 2026"
subtitle: "Data-driven insights on how AI is transforming talent acquisition"
brand:
  name: "Juicebox"
  primary_color: "#4F46E5"  # Indigo/blue
  secondary_color: "#10B981"  # Green accent
  font: "Inter"
  logo_url: "https://juicebox.ai/logo.svg"
sections:
  - type: hero-stat
    stat: "93%"
    label: "of recruiters plan to increase AI use in 2026"
    source: "LinkedIn Talent Solutions"
  - type: narrative
    title: "The AI Recruiting Revolution"
    body: "AI adoption in recruiting jumped from 26% to 43% in just two years..."
  - type: stat-grid
    stats:
      - { value: "800M+", label: "Profiles searchable by AI" }
      - { value: "47%", label: "Reduction in time-to-fill" }
      - { value: "10x", label: "Cheaper than LinkedIn Recruiter" }
  - type: comparison-table
    headers: ["Feature", "Traditional", "AI-Powered"]
    rows:
      - ["Search method", "Boolean keywords", "Natural language"]
      - ["Data sources", "1 (LinkedIn)", "60+ sources"]
  - type: cta
    headline: "See AI recruiting in action"
    body: "Try PeopleGPT free — search 800M+ profiles in natural language"
    button_text: "Get Started Free"
    button_url: "https://juicebox.ai"
footer:
  text: "© 2026 Juicebox. Data sources cited throughout."

2. Landing Page (single page with CTA)

A single-page marketing asset with a headline, value props, and email capture.

3. Comparison Page (side-by-side)

A visual comparison of two products (e.g., Juicebox vs LinkedIn Recruiter).

4. One-Pager (quick reference)

A dense, single-page reference sheet (e.g., "PeopleGPT Prompt Library").

Step-by-Step Process

Step 1: Choose Generation Method

Check which tools are available (in priority order):

  1. Gamma API (preferred) — If GAMMA_API_KEY is set, use Gamma Generate API v1.0 (GA since Nov 2025). Requires Pro account ($16/mo). Can create presentations, documents, and web pages programmatically. Supports 60+ languages, up to 100K token input. Rate limit: hundreds per hour.
  2. v0.dev Platform API — If V0_API_KEY is set, use Vercel's v0 Platform API (beta). Requires Premium ($20/mo) or Team plan. Generates React + Tailwind code from prompts. Best for landing pages and interactive web content.
  3. Self-hosted HTML — Fallback: generate HTML directly using Tailwind CSS templates. No external dependency. Full control over output.

Step 2A: Gamma API Generation (Preferred)

Gamma's Generate API v1.0 creates presentations, documents, and web pages from text prompts.

API docs: https://developers.gamma.app/docs/getting-started

curl -X POST https://api.gamma.app/v1/generate \
  -H "Authorization: Bearer $GAMMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "<structured content prompt>",
    "format": "document",
    "theme": "<optional theme ID>"
  }'

Tips for Gamma:

  • List your available themes first: GET /v1/themes
  • Can share via email programmatically
  • Supports creating from templates: use POST /v1/generate-from-template
  • Output can be viewed as a hosted Gamma page or exported

Step 2B: v0.dev Platform API Generation

v0's Platform API generates React + Tailwind code from natural language prompts.

API docs: https://v0.app/docs/api/platform/overview

The workflow: prompt → project → code files → deployment. Output is deployable to Vercel instantly.

# Create a project with a prompt
curl -X POST https://api.v0.dev/v1/projects \
  -H "Authorization: Bearer $V0_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Create a professional industry report page with..."
  }'

Tips for v0:

  • Best for interactive web pages and landing pages
  • Output is React/Next.js + Tailwind — can be deployed or converted to static HTML
  • Usage-based billing on top of subscription

Step 2C: Self-Hosted HTML Generation (Fallback)

Generate a self-contained HTML file:

  1. Load the template for the asset type
  2. Inject content from the structured data
  3. Apply brand styles (colors, fonts, logo)
  4. Generate data visualizations using inline SVG or CSS
  5. Output as a single HTML file with all styles inlined

HTML Template Structure:

<!DOCTYPE html>
<html lang="en">
<head>
  <meta charset="UTF-8">
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
  <title>{{ title }}</title>
  <script src="https://cdn.tailwindcss.com"></script>
  <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700;800&display=swap" rel="stylesheet">
  <script>
    tailwind.config = {
      theme: {
        extend: {
          colors: {
            brand: '{{ primary_color }}',
            accent: '{{ secondary_color }}'
          },
          fontFamily: {
            sans: ['Inter', 'sans-serif']
          }
        }
      }
    }
  </script>
  <style>
    /* Print styles for PDF conversion */
    @media print {
      .page-break { page-break-before: always; }
      body { -webkit-print-color-adjust: exact; print-color-adjust: exact; }
    }
  </style>
</head>
<body class="font-sans bg-white text-gray-900">
  <!-- Content sections generated here -->
</body>
</html>

Section Templates:

  • hero-stat: Large stat number with label and source
  • narrative: Title + body text in clean typography
  • stat-grid: 3-4 stats in a responsive grid
  • comparison-table: Side-by-side table with highlighting
  • chart: Simple bar/donut chart using CSS or inline SVG
  • cta: Call-to-action block with button
  • footer: Branded footer with disclaimers

Step 3: Output

Save the HTML file:

clients/<client>/strategies/<strategy>/content/[asset-name].html

Optionally convert to PDF:

# Using playwright/puppeteer (if installed)
npx playwright screenshot output.html output.pdf --format=pdf

Or provide instructions for manual PDF conversion (print to PDF from browser).

Brand Configurations

Juicebox Brand

{
  "name": "Juicebox",
  "primary_color": "#4F46E5",
  "secondary_color": "#10B981",
  "accent_color": "#F59E0B",
  "background": "#FFFFFF",
  "text_color": "#111827",
  "font_heading": "Inter",
  "font_body": "Inter",
  "logo_url": "https://juicebox.ai/logo.svg"
}

Save brand configs at: skills/content-asset-creator/brands/[client].json

Tips

  • Keep reports to 2-3 pages max. Busy recruiters won't read more.
  • Lead with the biggest, most surprising stat. Make it impossible to scroll past.
  • Every section should have exactly ONE key takeaway. Don't dilute with multiple messages.
  • The CTA should feel natural, not bolted on. The data should lead to the conclusion that the reader needs your product.
  • For PDF distribution: test that the HTML prints well before sending. Use @media print styles.
  • For web distribution: add Open Graph meta tags so it looks good when shared on LinkedIn/Twitter.

Dependencies

  • Tailwind CSS (via CDN — no build step)
  • Google Fonts (via CDN)
  • Optional: Gamma API key (GAMMA_API_KEY) — Requires Gamma Pro account ($16/mo). API v1.0 GA. Docs: https://developers.gamma.app
  • Optional: v0.dev API key (V0_API_KEY) — Requires v0 Premium ($20/mo). Platform API (beta). Docs: https://v0.app/docs/api/platform/overview
  • Optional: Playwright/Puppeteer for PDF conversion

Templates

Templates are stored at skills/content-asset-creator/templates/:

  • report.html — Industry report template
  • landing-page.html — Landing page with email capture
  • comparison.html — Product comparison page
  • one-pager.html — Quick reference sheet

Each template accepts the content data structure defined above.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Research supported advertising promises from a specific buyer's context, current product facts, customer language and observed ads. Turn them into static, video or copy ideas; match video ideas to actual recipes and save a product-scoped angle bank for write-video-ad-script. Product-led discovery can use verified facts without reviews. Reference persistence and reach are observations, not proof of performance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gooseworks-ai/goose-skills1.3천2026년 10월 24일 업데이트

Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift recommendations and scenario modeling.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gooseworks-ai/goose-skills1.3천2026년 10월 24일 업데이트

For paid lead-gen and participant-recruitment ads, replaces vanity CPA with true CAC per qualified lead by joining ad-platform data with downstream funnel events, surfaces tracking gaps, and classifies every creative into Scale / Keep / Investigate / Cut.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gooseworks-ai/goose-skills1.3천2026년 10월 24일 업데이트

The intake stage of a Meta ad harness. Researches the brand first, states what it assumes, and asks only what it cannot infer and what would change money, claims or legal exposure if guessed wrong — at most four questions a turn, in plain business language. Writes the brand's stable facts (ads/brand.md), the campaign brief, and a log of what was asked vs assumed. Use it when someone wants to run Meta ads and the brand's ad facts are not yet recorded.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gooseworks-ai/goose-skills1.3천2026년 10월 24일 업데이트

Checks paid ads against the ad platform's rules (Meta, TikTok, Google, LinkedIn and others) and the brand's category rules: the copy, on-image or on-screen text, pictures and people. Rewrites what can be fixed honestly, adds the disclosures that are needed, and flags anything that needs a human or legal review, with one pass, fixed or flag line per ad and platform. Use alone when you already have the ad text or images and know where they will run; otherwise run the playbook for the job (e.g. make-static-ads, make-content, email-lifecycle).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gooseworks-ai/goose-skills1.3천2026년 10월 24일 업데이트

Analyze the message match between your ads and landing pages. Checks if the promise in the ad copy carries through to the landing page headline, body, and CTA. Flags disconnects that kill conversion rates. Works with Google, Meta, and LinkedIn ads.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gooseworks-ai/goose-skills1.3천2026년 10월 24일 업데이트

gooseworks-ai의 스킬 모두 보기

이 스킬의 문제 신고