Product marketing and landing page architect for Raamattu Nyt. Generates landing page copy, feature page copy, and CTA suggestions based on the canonical user model. Translates user paths into benefit narratives and core tasks into user value propositions. Use when (1) creating or updating the main landing page, (2) writing feature page copy, (3) generating marketing messaging for app features, (4) crafting CTAs, (5) translating technical features into user benefits, (6) planning marketing page structure. Triggers: "landing page", "marketing copy", "feature page", "CTA", "value proposition", "markkinointi", "laskeutumissivu", "ominaisuussivu", "benefits copy", "marketing messaging".
Installation
Details
Usage
After installing, this skill will be available to your AI coding assistant.
Verify installation:
npx agent-skills-cli listSkill Instructions
name: landing-page-architect description: > Product marketing and landing page architect for Raamattu Nyt. Generates landing page copy, feature page copy, and CTA suggestions based on the canonical user model. Translates user paths into benefit narratives and core tasks into user value propositions. Use when (1) creating or updating the main landing page, (2) writing feature page copy, (3) generating marketing messaging for app features, (4) crafting CTAs, (5) translating technical features into user benefits, (6) planning marketing page structure. Triggers: "landing page", "marketing copy", "feature page", "CTA", "value proposition", "markkinointi", "laskeutumissivu", "ominaisuussivu", "benefits copy", "marketing messaging".
Landing Page Architect
Generate marketing copy and landing pages for Raamattu Nyt by translating the canonical user model into benefits and value.
Authority
- Consumes
Docs/ai/core-user-model.jsonas the single source of truth - NEVER redefines tasks or paths — translates them into benefits and value
- The
core-ux-detectiveskill owns definitions; this skill owns marketing presentation
Workflow
1. Read the User Model
Read Docs/ai/core-user-model.json
If file doesn't exist, inform the user to run core-ux-detective first.
2. Determine Scope
From user request, determine what to generate:
- Full landing page: Hero + feature sections + CTAs
- Feature page: Single feature deep-dive
- CTA copy: Call-to-action suggestions
- Messaging framework: Benefit mapping for all tasks/paths
3. Transform Paths → Narratives
For each user_path, generate a benefit narrative:
| Model Field | Marketing Use |
|---|---|
user_paths[].intent | Problem statement / user need |
user_paths[].label | Section heading (Finnish) |
user_paths[].steps | Implied complexity → simplicity promise |
user_paths[].primary | Hero section (true) vs. feature section (false) |
Primary paths → hero section and main value proposition. Secondary paths → feature cards / supporting sections.
4. Transform Tasks → Benefits
For each core_task, map to a user benefit:
Task intent (English) → What problem it solves
Task label (Finnish) → Feature name in copy
Task appears_in → Context for where to show it
Focus on outcomes, not mechanics:
- "Löydä jakeet hetkessä" (Find verses instantly) — not "Hakutoiminto käyttää tekstihakua"
- "Kuuntele Raamattu matkalla" (Listen to the Bible on the go) — not "TTS-toisto ElevenLabs APIlla"
5. Generate Copy
See references/copy-patterns.md for page structure templates and Finnish copywriting patterns.
6. Output
| Output | Format | Location |
|---|---|---|
| Landing page | React component or HTML | apps/raamattu-nyt/src/pages/LandingPage.tsx |
| Feature sections | Component per section | apps/raamattu-nyt/src/components/landing/ |
| Copy data | JSON | apps/raamattu-nyt/src/data/marketing-copy.json |
| Static landing | HTML (if standalone) | apps/raamattu-nyt/public/landing/ |
Messaging Rules
- Never rename tasks or paths from the canonical model
- Never invent features that don't exist in
core-user-model.json - User intent language — describe what the user wants, not what the app does
- Finnish first — all user-facing copy in Finnish, English for dev comments only
- No superlatives — avoid "paras", "vallankumouksellinen", "uskomaton"
- Trustworthy tone — clear, honest, non-pushy
- No step-by-step — marketing explains why, not how (help-system-architect owns how)
Tone
- Trustworthy: Honest about what the app does, no exaggeration
- Clear: Short sentences, concrete benefits, no jargon
- Non-pushy: Invite, don't pressure — "Kokeile" over "Osta nyt"
- Warm: The Bible is personal; copy should feel respectful and inviting
More by Spectaculous-Code
View allDiscover, define and canonicalize the core user tasks and user paths of the application. Use when (1) mapping what users can actually do in the app, (2) defining canonical user journeys/flows, (3) creating the AI-readable user model (core-user-model.json), (4) reviewing whether a new feature introduces a new core path, (5) other skills (help, marketing, onboarding) need authoritative task/path definitions to consume. Triggers: "core tasks", "user paths", "user journeys", "UX model", "what can users do", "core flows", "user model", "canonical tasks", file types: core-user-model.json.
Codebase exploration and location finder for the Raamattu Nyt monorepo. Use when finding where specific functionality is implemented, locating constants/tokens/config values, discovering file patterns, or answering "where is X coded?" questions. Helps other skills and agents locate code quickly.
Expert assistant for managing biblical topics in the KR92 Bible Voice project. Use when (1) creating/editing topics and their Finnish translations, (2) managing topic relations (related, opposite, broader, narrower), (3) validating Finnish translations and pronunciations with Voikko/Omorfi, (4) reviewing topics marked with qa_status='unchecked', (5) bulk updating topic translations, (6) managing topic aliases and synonyms, or (7) fixing incorrectly translated Finnish topic names.
Search Engine Optimization and AI Search Optimization (GEO) specialist. Use when: (1) optimizing for traditional search (Google, Bing), (2) optimizing for AI search engines (ChatGPT, Perplexity, Google AI Overviews, Claude), (3) implementing schema markup for AI citation, (4) improving Core Web Vitals (LCP, INP, CLS), (5) creating citation-worthy content structure, (6) zero-click optimization, (7) E-E-A-T signal implementation. Expert in GEO (Generative Engine Optimization), structured data, and AI-readable content.
