KNOWLEDGE NOTESKnowledge Notes
Explore curated knowledge, course notes and methods, with their existing content and sources preserved.
This index lists complete English editions. Additional Chinese notes and bilingual updates remain available in the Chinese index.
350knowledge notesWill’s complete pipeline for non-technical PMs to go from “idea to runnable prototype”, breaking vibe coding into 7 copyable steps: ① Use 3 tiers of templates to turn a one-sentence product idea into structured input; ② Have AI act as a “requirements interrogator” to ask follow-up questions in sequence and force out a Grill Summary; ③ Use a “top-tier product architect” role prompt to expand the 5 answers into an investment-grade PRD; ④ Extract feature points from the PRD to generate 3 non-overlapping interaction DRD options, then convert the chosen option into a coding prompt that can directly produce a product; ⑤ Feed it to Figma Make (to produce an interactive demo) or Claude (to produce a real launch-ready product) to generate a prototype; ⑥ Feed screenshots back in to let AI spot errors and iterate on its own; ⑦ Publish to mobile (Claude outputs HTML → Netlify Drop drag-and-drop hosting → add to home screen as an App) + one-click reskinning with ReferoStyle. Each step provides reusable prompt skeletons + Why + examples + pitfalls. Three parallel methods (Method 1 Document-driven mainline / Method 2 Document-driven HTML output / Method 3 GPT+Figma natural language UI building). The audience is non-technical product managers who care about “when to use which step, how to copy the prompts” rather than code. Division of labor with [[newtype-ai-coding]]: that article covers tool stack selection and mindset (how to choose Cursor/Claude Code/Codex), while this article covers the concrete action chain and prompt templates for non-technical PMs to run through a prototype from scratch.
Synthesis of 4 schools of perspective on the AI Coding tool stack (2024-08 → 2026-05). Huang Yihe (Cursor shock → v0+Claude+Cursor three-piece suite → Cline self-built MCP → Gemini 2.5 → Claude Code → OpenCode camp) / Wang Kai (product manager path: Cursor $50,000 → Claude Code terminal → disruptive data analysis → hundredfold token consumption) / Xiaohongshu vibecoding (three core mindsets + 0-80 vs 80-100 life-or-death line + Astro Kid 400 million financing) / Lao D (using OpenRouter to connect Claude Code in China without scientific internet access). Covers 4 code retrieval methods / three tiers of Ultra think / Plan Mode / tool stack division of labor philosophy / Vibe Coding cleansing prophecy
Huang Yihe 2024-09 → 2026-05 AI Coding tool stack practice. Cursor-dominant phase → v0+Claude+Cursor three-piece suite → Cline self-built MCP → Gemini 2.5 large-context codebase scanning → Claude Code main battlefield → Codex/GitHub Copilot/OpenCode + newtype-os multi-Agent orchestration. Vibe Coding experience, AI Coding division of labor philosophy, Cursor internal modes, Ultra think, Plan Mode, Claude Code Sub-agents
Huang Yihe's non-technical indie development roadmap from 2024-09 to 2026. Blog → Prompt House → LearnFromYouTube → Super Analyst Skill → newtype Profile/CLI/OS. Tool stack (Next.js + Supabase + Stripe + Cursor + Electron) / Business model (global merchant + tax filing) / Network setup (VPS+VLESS+Reality+SOCKS5) / Go Fundamental design philosophy / AI Coding division of labor
Integration of Vibe Coding and independent development from 5 perspectives. Karpathy (Software 3.0 + definition of Vibe Coding + Iron Man Suit + Agentic Decade) / newtype Lao Huang (6+ practical non-technical independent products + 3 core mindsets on Unit Economics + Vibe Coding cleansing prophecy) / Xiaohongshu vibecoding (three core mindsets + 0-80 vs 80-100 make-or-break line + Ci Le Ge Ci interview + Astro Kid's 400 million financing) / Wang Kai (product manager transition + AI Coding changing collaboration workflows + disruptive nature of data analysis) / **zara Zhang Zala (liberal arts background + Build small + Opinionated products + Build first learn later + Coding ≠ Shipping 70/30 + 4 core mindsets for working with models + Frontend Slides 16k+ stars)**. Covers definition of Vibe Coding, cleansing prophecy, 0-80 vs 80-100 make-or-break line, platformization of Vibe Gaming, and cross-over for liberal arts graduates.
A collection of 18 hands-on AI tool/Skill tutorials from a Xiaohongshu vibecoding creator. Covers: ① Claude Code Pixel Sprite Agent (virtual office visualized agent) ② Codex + Remotion for making follower surge animations ③ Vibe Marketing Skill for batch video production (FFmpeg concatenation, Skill calling local services) ④ Automated intelligence system (self-evolving scoring Auto-Belief referencing Kafka) ⑤ Getting IELTS 7.5 without paid classes using Claude Code Skill (IELTS Diagnose/Speaking/Writing/Reading Skill suite + Gemini Live + Notebook LM) ⑥ Obsidian skill for diagramming (Skill from Obsidian founder, draws H16Z long-form article logic diagrams in 10 seconds) ⑦ Advanced HTML PPT (3 techniques) ⑧ Google POMLY AI marketing tool ⑨ Reproducing LM with Karpathy's 243-line nanochat ⑩ Gemini+Antigravity dual-platform game
A collection of 23 AI webpage / 3D modeling / real-time typography works by Xiaohongshu vibecoding creators. Covers: ① Pretext, the viral open-source frontend typography library (by Cheng Lou, React animation author, 21 million views) ② SOP for cinematic AI-built webpages (Nano Banana + Higgsfield + Seedance + Google AI Studio + Landingbook) ③ Making premium-feeling Vibecoding pages (Page Flows + Godly godly.website + Mobbin) ④ Bringing pages to life (Unicorn Studio + React Bits reactbits.dev + Design Spells) ⑤ AI 3D modeling (Hitem3D 2.1 hi3d.AI / turn one image into a PBR 3D figurine in seconds) ⑥ Google Genie 3 world generation model ⑦ AI real-time generation of endless webpages (shared by Karpathy) ⑧ 5 ways to play with Gemini 3 3D particle animations + starry-sky particle gesture recognition ⑨ GPT Image 2 360° panoramic images ⑩ Minimax 2.7 Plus, a Vibecoding model accessible in mainland China
A collection of 10 aesthetic methodology and creator economy works from Xiaohongshu vibecoding creators. **Core thesis**: "The model is not the most important thing; aesthetics is." It covers ① Tuning vibecoding aesthetic value worth 100,000 (Xiaozhuang / Kimi 2.6 / 1:1 replication + three front-end terms Hero/Shader/Three.js + high-quality templates) ② Stanford University open course "Aesthetics is the Primary Productivity" (D3 tools + color extraction website + animation usage considerations) ③ Karpathy zero-basic interpretation (with supporting prompts) ④ The viral rise of Pretext = the future of universal creation (mother of two + building an app in 10 minutes) ⑤ Interview with the creator of Cilegeci (10,000 users as an independent developer, the 80→100 score life-or-death line) ⑥ buildinpublic music version of Cursor (Strato live coding)
A collection of 40 practical vibecoding works by Xiaohongshu creators. The most intuitive vibecoding reference for non-technical developers beyond Truman: desktop pets / N-day game development diaries / 30-day ARPG challenge / Cozy Cat Fit / Stranger Things / a full game made with Codex in one afternoon / ASCII style converter / 10,000-user interviews for Ci Le Ge Ci / music version of Cursor / terminal Tetris for waiting-mode thinking / gesture-controlled Snake / couple date projects / **Astro Kid's 400 million yuan financing = platformized realization of Vibe Gaming**. Covers the tool stack (Google AI Studio / Codex / Cursor / Gemini 2.5 / Lingguang / Figma) + three core mindsets (state requirements clearly / progress step by step / be a picky client) + the life-or-death line between 0-80 and 80-100 points + business route selection + user retention data + platform-side business models
Understand specific needs, Skills, and editable deliverables through Zara Zhang Zala's historical product portfolio; provide the official entry point and reading path for Frontend Slides, and distinguish old growth data, GitHub projects, and hosted-service capabilities.
A compilation of Zhang Zala's Vibe Coding practices: start from a small personal problem, use AI to build a working product, and learn along the way; covers topic selection, requirement description, feature cutting, and product differentiation.
