์ธํ„ฐํŽ˜์ด์Šค๋Š” ํ˜„์ง€ํ™”๋˜์–ด ์žˆ์œผ๋ฉฐ, Skill ์†Œ๊ฐœ์™€ ์„ค๋ช… ๋ฌธ์„œ๋Š” ์„ ํƒํ•œ ์–ธ์–ด๋กœ AI๊ฐ€ ์ž๋™ ๋ฒˆ์—ญํ•ฉ๋‹ˆ๋‹ค. ์ฝ”๋“œยท๋ช…๋ น์–ดยท๊ฒฝ๋กœยท์ „๋ฌธ ์šฉ์–ด๋Š” ์›๋ฌธ์„ ์œ ์ง€ํ•˜๋ฉฐ ์›์ž‘์ž ๋ฌธ์„œ๊ฐ€ ์šฐ์„ ํ•ฉ๋‹ˆ๋‹ค.
Skills ๋‘˜๋Ÿฌ๋ณด๊ธฐ
๋””์ž์ธ ๋ฐ ์ฐฝ์ž‘ ยท SKILL.md

draft-landing

draft-landing

Use when asked to structure a landing page, design page layout for conversion, or plan landing page information architecture. Examples: "landing page structure for SaaS", "conversion-optimized layout"

Independent GitHub snapshot ยท Automated classification ยท Original documentation governs

Skill ๋ฌธ์„œ

GitHub

name: draft-landing description: | Use when asked to structure a landing page, design page layout for conversion, or plan landing page information architecture. Examples: "landing page structure for SaaS", "conversion-optimized layout" allowed-tools: Read, Bash, Glob, Grep version: 0.6.6 author: tonone-ai hello@tonone.ai license: MIT

draft-landing โ€” Landing Page Information Architecture

Follow the output format defined in docs/output-kit.md โ€” 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

When to use

User needs a landing page structure, section order, or conversion-optimized layout. Product type is known or discoverable.

Workflow

  1. Identify product type from user request or project context
  2. Search landing page patterns:
    python3 -m draft_agent.uiux search --domain landing --query "{product_type}" --limit 3
    
  3. Search product reasoning for audience + conversion context:
    python3 -m draft_agent.uiux search --domain product --query "{product_type}" --limit 3
    
  4. Validate each section against the "so what?" test โ€” every section must earn its place
  5. Output section order with CTA placement markers

Output format

โ”Œโ”€ Landing Page IA โ€” {product_type} โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
โ”‚ #  โ”‚ Section            โ”‚ Purpose                    โ”‚ CTA?          โ”‚
โ”œโ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
โ”‚  1 โ”‚ {section_name}     โ”‚ {purpose}                  โ”‚ Primary CTA   โ”‚
โ”‚  2 โ”‚ {section_name}     โ”‚ {purpose}                  โ”‚ โ€”             โ”‚
โ”‚  3 โ”‚ {section_name}     โ”‚ {purpose}                  โ”‚ Secondary CTA โ”‚
โ”‚  โ€ฆ โ”‚ โ€ฆ                  โ”‚ โ€ฆ                          โ”‚ โ€ฆ             โ”‚
โ””โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜

Conversion strategy: {strategy}
CTA copy guidance:   {cta_guidance}

Anti-patterns

  • Never skip the "so what?" test per section โ€” if a section can't answer it, cut it
  • Never add sections without a clear conversion purpose
  • Never place the primary CTA below the fold on the first screen
  • Never structure the page without knowing the primary audience and their job-to-be-done

Delivery

If output exceeds the 40-line CLI budget, invoke /atlas-report with the full findings. The HTML report is the output. CLI is the receipt โ€” box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

์ €์žฅํ•œ Skills