skills/landing-page-gtm/SKILL.md
Build and update high-converting SaaS landing pages with GTM-aware marketing copy, competitive positioning, and sales psychology. Use when creating new landing pages, rewriting feature cards, updating marketing copy, launching product pages, or transforming technical features into customer-facing sales language. Triggers on "build landing page", "update feature cards", "rewrite marketing copy", "create product page", "launch page", "GTM", "sales copy", "competitive positioning", or when converting product features into conversion-focused web pages.
npx skillsauth add ooiyeefei/ccc landing-page-gtmInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Build conversion-focused landing pages that sell — not just describe. Combine product research, competitive positioning, sales copywriting, and frontend implementation into a single workflow.
Before any work, collect these inputs:
| Input | Question |
|-------|----------|
| Target URL | "What URL or route is this for?" (e.g., myapp.com/pricing) |
| Codebase path | "Where's the source code?" (e.g., /home/user/project/src) |
| Product/feature | "What product or feature is this page selling?" |
| Audience | "Who's the buyer? (role, company size, pain level)" |
| Competitors | "Who do they compare you against?" |
| Constraints | "Existing design system, form provider, CTA destination?" |
If the page already exists, read it first. Never propose changes to code you haven't read.
Study the actual product before writing a single word of copy. Never invent features.
Frame every section as "why us, not them" without naming competitors.
Positioning formula:
Pain they feel daily
+ What competitors do about it (poorly)
+ What you do differently
+ Outcome they'll experience
Anti-generic test — If copy could appear on a competitor's site unchanged, rewrite it:
Competitor dismissal patterns:
Transform features into desire. Think like a buyer, not an engineer.
Voice by audience:
| Audience | Tone | Example | |----------|------|---------| | SME owner | Warm, direct | "Snap a receipt. Done." | | Finance manager | Outcome-driven | "Every match shows you exactly why." | | Enterprise | Trust-building | "Control without complexity." | | Technical | Precise, credible | "Gets measurably smarter every week." |
Copy rules:
Talking about AI/tech without jargon:
| Technical reality | Say instead | |---|---| | ML model retrains weekly | "Gets smarter every week from your feedback" | | Internal optimization framework | Never mention. Say "learns from corrections" | | LLM / GPT / Claude | "AI assistant" or just "your assistant" | | API integration | "Connects to your existing tools" | | Training data from user corrections | "Every correction teaches it something new" | | Accuracy gating prevents regression | "Can only get better — never worse" | | Explainable AI / reasoning traces | "Shows you exactly why each decision was made" |
Conversion-focused page anatomy:
1. Hero — Headline + subheadline + primary CTA
2. Pain Points — 3-4 scenarios the buyer FEELS (red/warm tones)
3. Solution — Transformation cards, not feature lists
4. Social Proof — Testimonials or metrics
5. How It Works — 3 steps max (reduce perceived complexity)
6. Pricing — vs. status quo comparison, not just a table
7. FAQ — Objection handling disguised as helpfulness
8. Final CTA — Urgency + form (repeat primary CTA)
Not every page needs all sections. Match to product complexity:
CTA and forms:
_source field to distinguish which page the lead came from.Early Access / Waitlist pattern:
Before pushing:
_source fieldtesting
Decide whether your agent actually needs persistent memory, feedback loops, or closed-loop learning, then design the smallest thing that pays for itself. Use when the user says "add memory", "give my agent context management", "make my agent learn", "self-improving / closed-loop", "Reflexion / mem0 / Letta / MemGPT", "AriGraph", "agent memory architecture", "long-term memory for chatbot", "why does my agent keep forgetting / making the same mistake", "fine-tune from agent traces", or asks for a memory schema / experience store / reward model. Filters ruthlessly — most teams want a state cache, not memory + learning. Default position is scratchpad-only with a stateless agent shipped first.
tools
Prescriptive Q&A workflow for designing agentic pipelines, multi-model councils, sub-agent hierarchies, and tool-loop hardening for any domain. Use when the user asks to "design an agent", "design a multi-agent system", "should I use a council/debate", "build a [domain] review agent" (HAZOP, finance, tutorial, marketing, compliance, accounting), "real agency vs workflow", "how to add sub-agents", "AI for [domain] review", or names patterns like "orchestrator-worker", "evaluator-optimizer", "Magentic", "ReAct", "plan-and-execute", "handoffs". Walks the user through 12 stages one question at a time and emits a buildable design doc with citations. Do NOT use for general coding questions, single-shot prompt tuning, or bare "use Claude to do X" requests with no agency requirement.
development
This skill should be used when the user asks to "share this HTML", "publish HTML", "get a link for this file", "share this report", "make this shareable", "upload this HTML", or wants to publish any HTML artifact for others to view. ALSO use it for collaborative review on an HTML doc/spec/report — triggers include "get feedback on this", "let reviewers comment", "collect feedback", "share for review", "let people annotate this", "synthesize the feedback", "converge the feedback", "what did reviewers say", "incorporate the comments", or "improve this from the feedback". Wraps Surge.sh for zero-cost hosting with guided privacy options, plus an embedded annotation + AI converge workflow.
tools
End-to-end User Acceptance Testing for web applications. Analyzes branch changes and specs to generate exhaustive test cases, sets up the local environment, executes tests via Playwright browser automation, and produces a pass/fail results report with screenshots and fix documentation. Use when the user says "run UAT", "test this feature", "UAT testing", "acceptance test", "test my branch", "generate test cases", or wants to verify a feature branch against its spec before merge.