Agent skill

Landing Craft

by EliasOulkadi in EliasOulkadi/shokunin

Build conversion-optimized landing pages with CRO frameworks (Conversion Research, LIFT Model), scroll effects, A/B testing, personalization, form optimization, and Core Web Vitals (INP, LCP, CLS).

MITAuto-check passedFrontend & Design

Install Landing Craft

skills CLI
$ npx skills add EliasOulkadi/shokunin --skill landing-craft -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install EliasOulkadi/shokunin landing-craft --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/EliasOulkadi/shokunin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.pack/skills/landing-craft .claude/skills/landing-craft && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
landing-craft
GitHub stars
114
Token cost
~4.5k tokens
SKILL.md length
1,707 words
Files
5 (incl. scripts, references, assets)
Skills in repo
49
Repo updated
First seen
Licence
MIT

At a glance

Build conversion-optimized landing pages with CRO frameworks (Conversion Research, LIFT Model), scroll effects, A/B testing, personalization, form optimization, and Core Web Vitals (INP, LCP, CLS).

  • Works in 6 steps: Select creative archetype → Wireframe the sections → Draft copy → …
  • User asks to create a landing page
  • SKILL.md covers Creative Variance Engine, Workflow, The Structure and Hero Rules (from Unbounce data), plus 14 more sections
  • Runs Shell scripts from its folder

What it does

Landing Craft is an agent skill from EliasOulkadi/shokunin. Build conversion-optimized landing pages with CRO frameworks (Conversion Research, LIFT Model), scroll effects, A/B testing, personalization, form optimization, and Core Web Vitals (INP, LCP, CLS). Use when user asks to create a landing page, sales page, lead generation page, or improve conversion rates. Do NOT use for full product design (use component-forge), animation-specific (use motion-craft), or brand identity (use design).

Its SKILL.md is about 4.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts, reference files and assets (for example `references/ab-testing-stats.md`, `references/cro-frameworks.md` and `scripts/analyze-landing-page.sh`). Compatibility notes: opencode

It sits in Frontend & Design, covering Web performance, Conversion rate optimization and Landing pages. The repository describes itself as: 職人 Shokunin 62 AI agent skills for OpenCode, Claude Code, Cursor, Windsurf. ChromaDB memory, MCP servers, declarative self-updates. Multi-model, open source, zero cost. The licence is MIT.

When your agent uses it

  • User asks to create a landing page
  • Lead generation page
  • Improve conversion rates
  • Full product design (use component-forge)

Example prompts

  • “/landing-craft”

Requirements

  • A Bash shell
  • Compatibility (from SKILL.md): opencode

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Select creative archetype
  2. Wireframe the sections
  3. Draft copy
  4. Implement with mobile-first HTML/CSS
  5. Optimize for Core Web Vitals
  6. A/B test and iterate

What it can do on your machine

Read from SKILL.md and the folder at commit 4c68e5b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    opencode

    From compatibility in the SKILL.md frontmatter.

Context cost

Landing Craft loads about 4.5k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 112 tokens; SKILL.md has 1,707 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~112
When it runs · the whole SKILL.md, loaded when a task matches
~4.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~13k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from EliasOulkadi/shokunin at commit 4c68e5b, republished under its MIT licence (© EliasOulkadi). 1,707 words, ~4,525 tokens.

Download SKILL.mdSave it as .claude/skills/landing-craft/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
landing-craft
description
Build conversion-optimized landing pages with CRO frameworks (Conversion Research, LIFT Model), scroll effects, A/B testing, personalization, form optimization, and Core Web Vitals (INP, LCP, CLS). Use when user asks to create a landing page, sales page, lead generation page, or improve conversion rates. Do NOT use for full product design (use component-forge), animation-specific (use motion-craft), or brand identity (use design).
compatibility
opencode
triggers
landing page, sales page, conversion, CRO, A/B test, conversion rate, lead generation, signup page, marketing page, pricing page, LIFT model
negatives
full product design, component library, animations only, brand identity, dashboard, app UI
license
MIT
metadata.workflow
marketing
metadata.audience
developers
metadata.version
4.0.0
metadata.author
shokunin

Landing Craft

Landing pages that convert. Based on Unbounce (44,000+ A/B tests), GoodUI, CXL Institute, and WiderFunnel LIFT Model.

Creative Variance Engine

Before writing code, select ONE combination based on the brief. This prevents every landing page from looking the same.

Vibe Archetypes (pick 1)
ArchetypePaletteTypographyBest for
Editorial LuxuryWarm cream (#f5f2ec), deep charcoal, ink-blue accentSerif display (Cormorant Garamond, Playfair Display) + clean bodyB2B, consulting, premium SaaS
Dark AtmosphericDeep navy (#080c1a), off-white text, burnt orange accentBold condensed display (Cabinet Grotesk, Space Grotesk)Tech, AI, developer tools
Soft StructuralWhite (#ffffff), zinc neutrals, single accentGrotesk display (Geist, Plus Jakarta Sans)SaaS, productivity, health
Minimalist EditorialWarm bone (#f7f6f3), strict 1px borders, muted pastelsSerif + system sans-serifPortfolios, indie products
Layout Archetypes (pick 1)
ArchetypeStructureMobile
Split Screen50/50: text left, visual right. Clean alignment, no center.Stack vertical: text on top, visual below
Asymmetric BentoMasonry grid with varying card sizes. col-span-8 next to col-span-4.Single column. All col-span overrides reset to 1
Editorial Z-CascadeElements overlap with slight rotation (-2deg to 3deg). Depth through stacking.Remove all rotations and negative margins. Stack vertically.
Full-Bleed TypographyHero is pure typography. No image. Text spans viewport width.Text scales down via clamp(). No overflow.

Mobile override (universal): Any asymmetric layout above md: (768px) must collapse to single-column (w-full, px-4, py-8) on viewports below 768px.


Workflow

Step 1: Select creative archetype

Pick one vibe + layout from the Creative Variance Engine. Every page must feel distinct.

Step 2: Wireframe the sections

Block out all 10 sections (Hero through Final CTA). Each section answers: what does the visitor need to hear RIGHT NOW to move forward?

Step 3: Draft copy

Headline under 10 words. One CTA above fold. Social proof near top. Use PAS framework for problem section.

Step 4: Implement with mobile-first HTML/CSS

8px grid. clamp() for fluid typography. No centered hero text. Grain overlay (opacity 0.03-0.06).

Step 5: Optimize for Core Web Vitals

Preload hero image. Inline critical CSS. Lazy-load below-fold images. Target LCP < 2.5s, INP < 200ms.

Step 6: A/B test and iterate

Test highest-impact element first (headline). 95% significance. Min 1,000 visitors per variant.

The Structure

Hero: headline + sub + CTA (above the fold)
Social proof: logos, metrics, testimonials (~100px below hero)
Problem: framed for empathy, names the pain
Solution: 3 steps max, benefit-focused
Features: 3-6 items, each with one clear benefit
Testimonials: real people, specific results
Pricing: 3 tiers, middle is the offer
FAQ: answers top 5 objections
Final CTA: same ask, different context, near scroll bottom

Every section answers: what does the visitor need to hear RIGHT NOW to move to the next section?


Hero Rules (from Unbounce data)

  1. Value in 3 seconds: headline must communicate core benefit. A/B test headline first - highest-impact element.
  2. CTA visible without scroll: primary button above the fold. Above 600px vh.
  3. One CTA: one primary action. Secondary links are text only.
  4. Headline under 10 words: "Ship 3x faster with automated deployments" not "Welcome to DeployPro - the fastest way to ship code"
  5. Never center text: Left-aligned text + right-aligned visual (Split Screen). Centered hero is the #1 AI clich-.
  6. Supporting visual: product screenshot, illustration, or demo - never a generic stock photo.
Hero alt-layouts (not all center)
LayoutHTML structureWhen
Split 50/50<div class="grid grid-cols-2"><div>text</div><div>visual</div></div>Default. Works for everything.
Text-bleed<div class="pl-[5vw]"><h1 class="text-[clamp(48px,7vw,120px)]">Hero text</h1></div>Strong brand, confident product
3D perspective<div class="perspective-[800px]"><h1 class="[transform:rotateX(15deg)]">Hero</h1></div>Creative, premium, editorial
Negative space<div class="grid"><div class="col-start-1 col-end-3">text</div><div class="col-start-2">visual</div></div>Editorial, luxury

Design Palette

ElementSpecification
BackgroundDark (#080808) or cream (#f5f2ec). Never flat #ffffff or #f5f5f5
HeadlineEditorial serif or bold display. clamp(2.5rem, 5vw, 4.5rem)
BodyClean sans. Min 16px. Line height 1.6
Spacing8px base. Section: clamp(4rem, 8vw, 8rem)
TextureGrain overlay: opacity 0.03-0.06
IconsLucide or Phosphor. No emoji icons.
MotionSubtle scroll-triggered. Parallax or 3D on hero. No gratuitous animation.

CRO Methodology

LIFT Model (WiderFunnel)

Evaluate every element against these six factors:

FactorQuestionMeasurement
Value propositionDoes this clearly communicate the benefit?"What do I get?" answerable in 3 seconds
RelevanceDoes this match the visitor's intent?Bounce rate < 50%
ClarityIs the message immediately understandable?"What is this?" answerable in 5 seconds
DistractionWhat can we remove to focus attention?Scroll depth > 50%
AnxietyWhat reassures the visitor?Trust signals visible above fold
UrgencyWhy should they act now?Deadline or scarcity (real, not fake)
High-Impact Test Elements (in order of ROI)
TestWhyExpected lift
HeadlineFirst thing read. Shapes entire perception.10-40%
CTA button text and colorFinal friction point.5-25%
Hero image/videoVisual sets trust and expectation.5-15%
Social proof placementTop vs mid page changes trust curve.3-10%
Pricing structureTiers, placement, toggle.3-15%

Test one element at a time. 95% statistical significance. Min 1,000 visitors per variant.


Hero Architecture (Exact CSS)

css
.hero {
  min-height: 100dvh;
  display: grid;
  grid-template-columns: 1fr 1fr;
  align-items: center;
  padding: 0 clamp(2rem, 5vw, 6rem);
  background: #080c1a;
}

.hero-text {
  max-width: 650px;
}

.hero-text h1 {
  font-family: 'Cabinet Grotesk', 'Geist', sans-serif;
  font-size: clamp(2.5rem, 5vw, 4.5rem);
  font-weight: 700;
  line-height: 1.05;
  letter-spacing: -0.02em;
  color: #f0ede8;
}

.hero-text p {
  font-size: clamp(1rem, 1.2vw, 1.25rem);
  line-height: 1.6;
  color: #a09c96;
  max-width: 480px;
  margin-top: 1.5rem;
}

.hero-cta {
  display: inline-flex;
  align-items: center;
  gap: 0.75rem;
  padding: 16px 48px;
  background: #1B365D;
  color: #f0ede8;
  font-size: 0.9rem;
  font-weight: 500;
  text-transform: uppercase;
  letter-spacing: 0.05em;
  border: none;
  border-radius: 0;
  margin-top: 2rem;
  transition: transform 160ms cubic-bezier(0.23, 1, 0.32, 1),
              background 200ms ease;
}

.hero-cta:hover {
  background: #e05a20;
  transform: translateY(-2px);
}

.hero-cta:active {
  transform: scale(0.97);
}

Social Proof

Place near the top (within first 2 sections). Types by effectiveness:

  1. Logos of recognizable companies (3-12, grayscale, hover color. Never use without permission.)
  2. Specific user metrics: "Join 10,000+ paying customers" - number must be real
  3. Relevant testimonial: quote with name, title, photo, specific result
  4. Award/certification badge: only if recognizable (SOC 2, YC, Product Hunt)
html
<div class="social-proof">
  <p class="text-sm uppercase tracking-wider text-slate-400 mb-6">Trusted by teams at</p>
  <div class="flex flex-wrap gap-8 items-center opacity-60">
    <img src="stripe.svg" alt="Stripe" class="h-8 grayscale hover:grayscale-0 transition" />
    <img src="vercel.svg" alt="Vercel" class="h-8 grayscale hover:grayscale-0 transition" />
    <img src="shopify.svg" alt="Shopify" class="h-8 grayscale hover:grayscale-0 transition" />
  </div>
</div>

Problem Section (PAS Framework)

Problem: name the exact pain with specific numbers. "Your landing page converts at 0.8%. The industry average is 3.2%." Agitate: explore consequences of NOT solving it. Money lost. Growth stalled. Competitors winning. Solution: present your approach. "DeployPro uses conversion science from 44,000+ A/B tests to lift conversion rates."


Features Grid

3-6 features. Each one gets:

  • Icon (meaningful, not decorative). Single color, consistent stroke width.
  • Benefit-led headline: "Ship 3x faster" not "Automated CI/CD"
  • 1-2 sentence explanation. No fluff.
html
<div class="grid grid-cols-1 md:grid-cols-3 gap-8">
  <div class="feature">
    <Icon icon="zap" class="w-8 h-8 text-amber-500 mb-4" />
    <h3 class="text-lg font-semibold mb-2">Ship 3x faster</h3>
    <p class="text-slate-400">Automated build and deploy pipeline. One command to production.</p>
  </div>
</div>

Testimonials

ElementRule
PhotoRequired. Real person. No stock.
AttributionFull real name, title, company
QuoteSpecific, results-oriented. "We shipped 40% more features after switching" not "Great product"
Length1-3 sentences
PlacementNear relevant claim. Don't pile all at the bottom.

Pricing

3 tiers. Middle is your real offer.

PositionRoleStrategy
Left (Starter)Anchor lowMakes middle look reasonable. Price at 40-60% of Pro.
Center (Pro)The offerBest value, highlighted visually. "Most popular" badge.
Right (Enterprise)Anchor highMakes middle look affordable. 2-3x Pro.
css
.pricing-card-featured {
  border: 2px solid var(--accent);
  transform: scale(1.05);
  position: relative;
  z-index: 1;
}

.pricing-card-featured::before {
  content: 'Most popular';
  position: absolute;
  top: 0;
  left: 50%;
  transform: translate(-50%, -50%);
  background: var(--accent);
  color: white;
  padding: 4px 16px;
  border-radius: 9999px;
  font-size: 0.75rem;
  text-transform: uppercase;
  letter-spacing: 0.05em;
}

Rules:

  • Annual/monthly toggle (annual = 17-20% discount)
  • Every tier lists features explicitly
  • Include money-back guarantee near pricing
  • No fake scarcity. No "Only 3 spots left" when unlimited.

Show full SKILL.md (715 more words)Show less

Form Optimization (exact specs)

ElementBest practice
FieldsMinimum viable. Email only for lead gen.
ValidationInline, real-time, specific error messages
AutofillEnable autocomplete attributes
SubmitButton says what happens: "Get my free guide", "Start free trial" not "Submit"
Error recoveryPreserve entered values, highlight fields
Privacy"No spam. Unsubscribe anytime."
Input height48px minimum for mobile
Input font16px minimum (prevents iOS zoom on focus)
html
<form class="space-y-4 max-w-md">
  <div>
    <label for="email" class="block text-sm font-medium mb-1">Work email</label>
    <input
      id="email"
      type="email"
      autocomplete="email"
      required
      class="w-full h-12 px-4 border border-slate-200 text-base rounded-md"
      placeholder="you@company.com"
    />
  </div>
  <button
    type="submit"
    class="w-full h-12 bg-slate-900 text-white font-medium rounded-md
           transition-all duration-160 ease-out
           active:scale-[0.97]"
  >
    Get my free guide
  </button>
  <p class="text-xs text-slate-400 text-center">
    No spam. Unsubscribe anytime.
  </p>
</form>

Performance (Core Web Vitals 2026)

MetricTargetMeasurement
INP (Interaction to Next Paint)< 200msField data (Chrome UX Report)
LCP (Largest Contentful Paint)< 2.5sLab + field
CLS (Cumulative Layout Shift)< 0.1Lab + field
TBT (Total Blocking Time)< 200msLab only
Lighthouse Performance> 90Lab

Achievement checklist:

  • No render-blocking resources above fold
  • Hero image preloaded: <link rel="preload" as="image" href="hero.webp">
  • Critical CSS inlined in <style> tag. Async load for rest.
  • Images lazy-loaded (loading="lazy") with explicit width/height
  • Fonts self-hosted or preloaded with font-display: swap
  • Third-party scripts loaded with defer or async
  • Minimal JS. No frameworks for simple landing pages.

Mobile Optimization

ElementMobile rule
CTAFull-width, min 48px tall, thumb-friendly
FormsSingle column, large inputs (48px min)
Font sizeBody never below 16px
Touch targets44-44px min, 12px gap
Horizontal scrollNever. Test on 320px width.
HeroFull-width text, no image until 768px

CRO Audit Checklist

Before launching, verify:

  • Value proposition clear in 3 seconds (show to someone new, ask "what is this?")
  • CTA visible without scrolling on mobile and desktop
  • Only one primary CTA above fold
  • Headline under 10 words with specific benefit
  • Hero text NOT centered (left-aligned + right visual)
  • Social proof above fold (logos or metrics)
  • Real testimonials with attribution and specific results
  • LIFT Model: all 6 factors score 4/5 or higher
  • Form: minimum fields, 16px+ font, 48px+ input height
  • Privacy reassurance near form
  • Money-back guarantee near pricing
  • FAQ addresses top 5 real objections
  • Lighthouse Performance > 90
  • Core Web Vitals pass (LCP < 2.5s, INP < 200ms, CLS < 0.1)
  • Mobile: all touch targets = 44-44px, no horizontal scroll
  • A/B test plan: identify highest-impact element, document hypothesis
  • No fake urgency or scarcity
  • No generic stock photos - real product, real people, or illustration

Error Handling

ScenarioCauseFix
Hero image LCP > 4sNo preload or unoptimized formatPreload with <link rel="preload" as="image">, use WebP/AVIF, serve via CDN
CLS from late-loading fontsWeb font triggers layout shiftSelf-host fonts. Use font-display: swap. Preload with <link rel="preload" as="font">
A/B test inconclusiveNot enough traffic or significanceMin 1,000 visitors/variant, 95% significance, run for 2+ business cycles
Form abandonment spikeToo many fields or validation confusionReduce to minimum viable fields. Inline real-time validation. Preserve values on error.
Mobile bounce rate > 70%Touch targets too small, horizontal scrollAll touch targets >= 44px. Test at 320px width. No horizontal overflow.
Scroll effects jank on mobilerequestAnimationFrame scroll listenersUse CSS animation-timeline: view() or IntersectionObserver. Debounce JS scroll handlers.
CTA click-through below 1%Weak copy, wrong placementA/B test CTA text. Ensure CTA visible without scroll. Single primary action above fold.

Anti-Patterns

MistakeFix
Multiple CTAs competingOne primary action per viewport
No social proof above foldAdd logos or metrics in hero
Weak headline ("Welcome to Our Product")Specific benefit + audience in 10 words
Generic stock photosReal product screenshots or real people
No mobile testMost traffic is mobile. Test at 320px.
Auto-playing video with soundUser-initiated playback only
No A/B testing planIdentify highest-impact element, test one change
Centered hero textLeft-aligned text + right-aligned visual
"Only 3 spots left" when unlimitedFake scarcity destroys trust
Pricing without annual toggleAnnual = 17-20% discount. Always offer it.
CTA says "Submit"Action verb + value: "Get my free guide"
Hero image without preload<link rel="preload" as="image"> for LCP
h-screen for heromin-h-[100dvh] - avoids iOS Safari jump
Form inputs under 48px on mobileiOS zooms on anything under 16px font

Sources

  • Unbounce Conversion Benchmark Report (44,000+ A/B tests analyzed)
  • GoodUI.org - A/B tested UI patterns database
  • CXL Institute - Conversion optimization research
  • WiderFunnel LIFT Model
  • NN Group - Conversion studies and usability research
  • Refactoring UI - Adam Wathan, Steve Schoger
  • Google Web Vitals (web.dev)
  • Copyhackers - Conversion copywriting

Checklist

  • Skill loads without errors in the AI agent
  • YAML frontmatter is valid (description, compatibility, audience)
  • Workflow section provides clear step-by-step instructions
  • Error handling section covers common failure modes
  • All referenced files (references/, scripts/, assets/) exist
  • Skill triggers correctly for intended use cases
  • No broken links or missing resources

© EliasOulkadi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references, assets) in .pack/skills/landing-craft of EliasOulkadi/shokunin.

  • SKILL.md
  • assets/landing-page.template.html
  • references/ab-testing-stats.md
  • references/cro-frameworks.md
  • scripts/analyze-landing-page.sh

Open the folder on GitHubat commit 4c68e5b

Compare with similar skills

Landing Craft next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Landing Craft compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Landing Craft this skillEliasOulkadi/shokunin114—~4.5kAutomated safety check: PassMIT
Landing Page Optimizerthatrebeccarae/claude-marketing161—~1.1kAutomated safety check: PassMIT
Product Appeal Analyzercuriositech/some_claude_skills244—~2.4kAutomated safety check: PassMIT
Conversion Rate Optimizationmanojbajaj95/claude-gtm-plugin105—~1.2kAutomated safety check: PassMIT
Landing Page Generatorbuildfastwithai/gen-ai-experiments785—~1.5kAutomated safety check: PassMIT
Landing Page Audit 39irinabuht12-oss/marketing-skills4.1k—~1.6kAutomated safety check: PassNone

Similar skills

  • Landing Page Optimizer

    thatrebeccarae/claude-marketing

    Landing page audit and optimization for conversion. An agent skill from thatrebeccarae/claude-marketing.

    161 GitHub stars~1.1k tokensUpdated 4 mo ago
    Frontend & DesignAuto-check passed
  • Product Appeal Analyzer

    curiositech/some_claude_skills

    Evaluate product desirability, market positioning, and emotional resonance—the complement to friction analysis.

    244 GitHub stars~2.4k tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed
  • Conversion Rate Optimization

    manojbajaj95/claude-gtm-plugin

    Conversion rate optimization for marketing pages and lead-capture forms.

    105 GitHub stars~1.2k tokensUpdated 23 days ago
    Marketing & SEOAuto-check passed
  • Landing Page Generator

    buildfastwithai/gen-ai-experiments

    Builds a single self-contained HTML landing page from a template with copy frameworks, four themes and SEO meta, then runs bundled audit scripts for conversion and speed.

    785 GitHub stars~1.5k tokensUpdated 19 days ago
    Frontend & DesignAuto-check passed
  • Landing Page Audit 39

    irinabuht12-oss/marketing-skills

    CRO analysis for landing pages evaluating headline clarity, CTA placement, trust signals, mobile friction, and conversion killers.

    4.1k GitHub stars~1.6k tokensUpdated 17 days ago
    Frontend & DesignAuto-check passed
  • Squeeze Page Builder

    Affitor/affiliate-skills

    Build email capture landing pages (squeeze pages) as single self-contained HTML files.

    701 GitHub stars~3.6k tokensUpdated 26 days ago
    Frontend & DesignAuto-check passed

More from EliasOulkadi/shokunin

All 49 skills in this repo
  • CI CD

    EliasOulkadi/shokunin

    Design CI/CD pipelines for GitHub Actions, GitLab CI, and CircleCI with matrix builds, test sharding, caching, Docker layer caching, OIDC auth, deployment strategies (rolling, blue-green, canary)…

    114 GitHub stars~3.4k tokensUpdated 6 days ago
    Auto-check: notes
  • Component Forge

    EliasOulkadi/shokunin

    Build production-grade components for React, Vue 3, and Svelte 5 with all states (loading, empty, error, success, idle), TypeScript strict, WCAG 2.2 accessibility, server components (RSC), and…

    114 GitHub stars~3.6k tokensUpdated 6 days ago
    Auto-check: notes
  • DB Admin

    EliasOulkadi/shokunin

    PostgreSQL database administration — backup/restore (pgdump, PITR, WAL archiving), health monitoring (connections, bloat, cache hit ratio, dead tuples), connection pooling (PgBouncer), replication…

    114 GitHub stars~2k tokensUpdated 6 days ago
    Auto-check: notes
  • DB Sculptor

    EliasOulkadi/shokunin

    Design database schemas with Prisma/Drizzle, PostgreSQL index strategy (B-tree, GIN, GiST, BRIN, Hash), query optimization (EXPLAIN ANALYZE), migration safety (expand/contract, zero-downtime), and…

    114 GitHub stars~3.1k tokensUpdated 6 days ago
    Auto-check: notes
  • Docker

    EliasOulkadi/shokunin

    Optimize Docker images with multi-stage builds, distroless bases, BuildKit cache mounts, multi-arch builds, compose watch, security hardening (non-root, seccomp, capabilities drop), and…

    114 GitHub stars~3.8k tokensUpdated 6 days ago
    Auto-check: notes
  • Error Handler

    EliasOulkadi/shokunin

    Design error handling, structured logging, and observability with OpenTelemetry (traces, metrics, logs), error classification, recovery patterns (retry with jitter, circuit breaker, bulkhead…

    114 GitHub stars~3.6k tokensUpdated 6 days ago
    Auto-check: notes

Questions about Landing Craft

What does Landing Craft do?

Build conversion-optimized landing pages with CRO frameworks (Conversion Research, LIFT Model), scroll effects, A/B testing, personalization, form optimization, and Core Web Vitals (INP, LCP, CLS). Landing Craft is an agent skill from EliasOulkadi/shokunin. Build conversion-optimized landing pages with CRO frameworks (Conversion Research, LIFT Model), scroll effects, A/B testing, personalization, form optimization, and Core Web Vitals (INP, LCP, CLS).

When should I use Landing Craft?

Landing Craft fits situations like: user asks to create a landing page; lead generation page; improve conversion rates; full product design (use component-forge).

How do I install Landing Craft in Claude Code?

Run `npx skills add EliasOulkadi/shokunin --skill landing-craft -a claude-code`. Or copy the skill folder (.pack/skills/landing-craft in EliasOulkadi/shokunin) into .claude/skills/landing-craft in your project. Claude Code loads it when a task matches its description.

How do I install Landing Craft in Codex?

Run `npx skills add EliasOulkadi/shokunin --skill landing-craft -a codex`. Or copy the skill folder (.pack/skills/landing-craft in EliasOulkadi/shokunin) into .agents/skills/landing-craft in your project. Codex loads it when a task matches its description.

Can I use Landing Craft in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add EliasOulkadi/shokunin --skill landing-craft -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/landing-craft, .gemini/skills/landing-craft, .github/skills/landing-craft and .opencode/skills/landing-craft in your project.

What does Landing Craft need to run?

Going by SKILL.md and its folder, Landing Craft needs a shell for the scripts in its folder. Our summary lists: A Bash shell. Compatibility (from SKILL.md): opencode.

Does Landing Craft access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Landing Craft safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Landing Craft use?

Landing Craft is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Landing Craft use?

About 4.5k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.9k tokens, read only when the agent opens those files.

What are the alternatives to Landing Craft?

Skills that share tags, products or a category with Landing Craft: Landing Page Optimizer (thatrebeccarae/claude-marketing, 161 stars), Product Appeal Analyzer (curiositech/some_claude_skills, 244 stars), Conversion Rate Optimization (manojbajaj95/claude-gtm-plugin, 105 stars) and Landing Page Generator (buildfastwithai/gen-ai-experiments, 785 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Landing Craft?

EliasOulkadi (a GitHub user) maintains it in EliasOulkadi/shokunin, which has 114 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 5, 2026.

Source: EliasOulkadi/shokunin on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.