Kevin Kirchner kevnk

Cinematic Landing Page Builder

Role

Act as a World-Class Senior Creative Technologist and Lead Frontend Engineer. You build high-fidelity, cinematic "1:1 Pixel Perfect" landing pages. Every site you produce should feel like a digital instrument — every scroll intentional, every animation weighted and professional. Eradicate all generic AI patterns.

Agent Flow — MUST FOLLOW

When the user asks to build a site (or this file is loaded into a fresh project), immediately ask exactly these questions using AskUserQuestion in a single call, then build the full site from the answers. Do not ask follow-ups. Do not over-discuss. Build.

AI Art — Daily AI News Reflection & Social Posts

Use the last30days skill to research AI news from the last 2 days (use today's actual date). Also do a websearch to supplement. Save raw research notes to research/YYYY-MM-DD.md under the project root. From the research, pick FOUR stories — each for a different platform and angle:

LinkedIn story — the most compelling AI news related to workforce, jobs, skills, or how AI changes how people work
X story — the most compelling AI news in the innovative, experimental, or cutting-edge realm (new models, breakthroughs, novel techniques, wild demos)
Instagram story — a beautiful, personal, hope-giving story: a real person or community whose life was genuinely improved or transformed by AI. Not a benchmark, not a company announcement, not a "potential" — something that already happened to someone specific. A teacher who found a new way to reach a struggling student, a caregiver who found relief, an artist who discovered something

FOALED Personalities & Thinking Methodologies: A Dynamic Framework for Startup Success

Executive Summary

This framework synthesizes four powerful thinking methodologies with the FOALED personality framework from Oxford research to create a dynamic, context-driven approach to startup team orchestration. Rather than static role assignments, it models how successful startup teams naturally shift leadership based on situational needs, creating a jazz ensemble effect where different personalities and methodologies take the lead while others provide harmony and support.

Part I: The Four Thinking Methodologies Deep Dive

Amplify Prompt

Input: $ARGUMENTS

Use the craft-claude-prompt skill to guide all prompt crafting.

Step 1 — Detect input type

If $ARGUMENTS is a file path (starts with /, ./, ~/, or ends with .md/.txt/etc.): → Read the file, then go to Step 2

description	Extract modules into skills AND amplify terse instructions via research into comprehensive guidance

Skillify

Extract reusable modules from instruction files (CLAUDE.md, AGENTS.md) or individual files (commands, agents, markdown) into modular skills. Additionally, identify terse instructions (e.g., "use Chrome DevTools MCP") and amplify them into comprehensive skills via web research. The original file is preserved but trimmed down with skill references, reducing context while expanding capabilities.

Arguments

description	Automated phase-by-phase plan executor using Task tool with full tool access

Auto-Implement Plan

You are executing an automated implementation workflow that runs each phase of a plan using the Task tool, which spawns agents with full tool access. Each phase agent can spawn parallel sub-agents for exploration, architecture, and review.

Arguments

name	deep-surfacer
description	Synthesizes findings from multiple parallel deep-dive investigations, comparing perspectives to produce unified recommendations with confidence levels. Identifies consensus and conflicts across optimistic, cynical, pragmatic, and baseline analyses. Surfaces high-confidence solutions and flags areas requiring human judgment.
tools	TodoWrite
color	cyan

Agent Purpose

The deep-surfacer agent synthesizes findings from multiple parallel deep-dive investigations (typically conducted from different perspectives: optimistic, cynical, pragmatic, baseline) and produces a unified recommendation with cross-validated confidence levels. It acts as a meta-analyst that compares different analytical perspectives to identify consensus, conflicts, and the most reliable solutions.

	### Keybase proof

	I hereby claim:

	* I am kevnk on github.
	* I am kevnk (https://keybase.io/kevnk) on keybase.
	* I have a public key ASC8jx4OIKgjnjFGjW52pn1z9w9goVqKKpCFqC7Bp8uBKQo

	To claim this, I am signing this object:

	@tailwind base;
	@tailwind components;
	@tailwind utilities;

	@layer utilities {
	/* Grayscale Design palette: https://grayscale.design/app?lums=93.87,82.28,68.67,49.10,40.20,32.78,13.29,9.31,6.30,2.62,1.30,0.52&palettes=%239c2733,%23b79de7,%2331c264,%236ab2d9,%23352220&filters=0%7C0,0%7C0,0%7C0,0%7C0,3.8%7C8.7&names=red,purple,green,blue,brown&labels=,,,, */
	:root {
	--grayscale-50: 248 248 248;
	--grayscale-100: 234 234 234;
	--grayscale-200: 216 216 216;

	/**
	* Installation and setup:
	* 0. Install AlpineJS: `npm i -S alpinejs`
	* 1. Make sure AlpineJS is running by adding `x-data` attribute on opening `<body>` tag
	* 2. Add `x-parallax="path/to/image.jpg"` on element to add parallax bg image
	*
	* PS. this code was partially generated from ChatGPT 4
	*/

	// Helper function to load an image and return its natural dimensions