(Crystal is now Nimbalyst) Run multiple Codex and Claude Code AI sessions in parallel git worktrees. Test, compare approaches & manage AI-assisted development workflows in one desktop app.
-
Updated
Feb 26, 2026 - TypeScript
(Crystal is now Nimbalyst) Run multiple Codex and Claude Code AI sessions in parallel git worktrees. Test, compare approaches & manage AI-assisted development workflows in one desktop app.
Web Codegen Scorer is a tool for evaluating the quality of web code generated by LLMs.
An open, agent-agnostic knowledge base of AI-assisted 'vibe coding' antipatterns — each entry is falsifiable (before/after code + a concrete detection recipe + evidence) and 16 are enforced by static detectors proven in CI. Contributions welcome.
Vibecode Starter — A minimal folder structure for AI-assisted coding that actually scales. Context, plans, and agent coordination without the groundhog-day workflow.
Assignment 1: Inductive Synthesis – EN.601.727 Machine Programming
My Claude Code settings and custom commands
Documenting my experiences with AI-assisted development. Personal insights, discoveries, and reflections on coding with AI tools.
An harness and behavioral guidelines to enforce reliable execution in AI coding agents.
Andrej Karpathy's LLM coding guidelines adapted as a Gemini CLI Skill
Production-grade coding methodology for AI coding agents, Claude Code, Cursor, Codex. Six principles to stop overengineering, silent assumptions, and "while I'm here" refactors.
Portable repo-first coding guardrails for ChatGPT, Codex, Claude, and Gemini. Narrow diffs, explicit assumptions, and verification-first workflows.
Benchmarking different Large Language Models on practical software development challenges
A Claude Code skill for hypothesis-driven debugging — reproduce, isolate, hypothesize, test, fix, document. Find the root cause, not a workaround.
A production-grade SDLC harness for human + LLM software teams: mechanical gates for quality, security, architecture, evals, and release discipline.
A Claude Code skill for understanding an unfamiliar codebase fast — systematic exploration from entry points to data flow.
A Claude Code skill for domain-aware code review — classify the code, then review for the failure modes that domain actually has.
A Claude Code skill for fast troubleshooting — a lightweight diagnostic pass for common issues when the full debug protocol is overkill.
A CLAUDE.md to direct AI codegen well — hypothesis before help, scoped prompts, validate before accepting, reject working-but-wrong, AI output is a draft. Five principles for the Vibe Engineer discipline.
Live index of cursor-rules files from GitHub, updated every 15 minutes
Add a description, image, and links to the llm-coding topic page so that developers can more easily learn about it.
To associate your repository with the llm-coding topic, visit your repo's landing page and select "manage topics."