mcpbeat Sign in

Draft Landing Agent Skill

| Use when asked to structure a landing page, design page layout for conversion, for SaaS", "conversion-optimized layout"

729 tokens
context cost
SKILL.md, read when the skill is used
2
files
plus reference files
0
copies elsewhere
how many repositories repackaged it
2 679
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace --skill draft-landing

What comes with it

277 bytes besides the instruction
.claude-plugin/plugin.json

The instruction itself

6 sections, as written by the author

draft-landing — Landing Page Information Architecture

Follow the output format defined in docs/output-kit.md — 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

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

Output format

┌─ Landing Page IA — {product_type} ──────────────────────────────────┐
│ #  │ Section            │ Purpose                    │ CTA?          │
├────┼────────────────────┼────────────────────────────┼───────────────┤
│  1 │ {section_name}     │ {purpose}                  │ Primary CTA   │
│  2 │ {section_name}     │ {purpose}                  │ —             │
│  3 │ {section_name}     │ {purpose}                  │ Secondary CTA │
│  … │ …                  │ …                          │ …             │
└────┴────────────────────┴────────────────────────────┴───────────────┘

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

Anti-patterns

  • Never skip the "so what?" test per section — 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 — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

How to use it

Copy the folder

Take jeremylongshore/draft-landing from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.