I spent ~4 hours building AIComicBuilder [1], a full-stack AI comic/drama generation platform, without writing a single line of code manually. This is a writeup of my "vibe coding" workflow using Claude Code. The app lets you: input a script → AI generates screenplay → character analysis → storyboard generation (with first/last frame images) → video generation. Supports...
I built a self-hostable pipeline that takes a screenplay (or a one-line idea) and produces a finished animated video — no coding required, no SaaS subscription. The pipeline: 1. Write or AI-generate a script ...
Hello HN,I built JadeAI, an open-source, AI-powered resume builder designed to take the friction out of crafting professional, ATS-friendly resumes.Why build another resume builder? Most existing tools either lock your data behind a subscription, have clunky editors, or lack deep AI integration. I wanted something that is:Developer-friendly: Self-hostable via Docker with zero-config (SQLite by...
URL: https://github.com/twwch/next-chat-skills---Text (paste into the "text" field):Hi HN,I built an open-source AI assistant that can autonomously discover, install, and execute Skills to actually complete tasks for you.The Problem:Most AI chatbots today are stuck in "read-only" mode. They can tell you how to do something, but they can't do it. Want to convert a PPTX to PDF? The AI will...
I built a Claude Code Skill that generates flowcharts, architecture diagrams, data visualizations, mind maps, and math plots from natural language. Supports Mermaid, DrawIO, ECharts, GeoGebra, and Markmap. Just describe what you want and get interactive HTML or PNG/SVG output.GitHub: https://github.com/twwch/multi-chart-draw-skills
This approach trades 1 extra LLM call (for recall detection) for significant context window savings while preserving the ability to access full details when needed.
Hello HN,I’ve been building AI agents lately and ran into a common "Context Bloat" problem. When an agent has 20+ skills, stuffing every system prompt, reference doc, and tool definition into a single request quickly hits token limits and degrades model performance (the "lost in the middle" problem).To solve this, I built OpenSkills, an open-source SDK that implements a Progressive Disclosure...
Powered by: AntV Infographic Capabilities: Creates professional digital infographics, data posters, and visual summaries. Workflow: Declarative DSL-based generation with rich built-in templates and high-quality SVG rendering.https://github.com/twwch/DeepDiagram
Hi everyone,I've been working on AI Agents recently and noticed a common frustration: most AI diagramming tools generate static images (PNG/JPG). If the AI gets one detail wrong, you can't easily fix it—you have to regenerate the whole thing.I wanted a tool that generates editable code and renders it interactively. So I built DeepDiagram.It’s an open-source web platform that uses a Multi-Agent...