llm-coding

(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.

Lightweight AI coding agent for the terminal, with one-shot automation, persistent agent teams, and a small reusable OpenAI-compatible agent kernel.

How to build production applications with AI coding agents (without losing control).

Vibecode Starter — A minimal folder structure for AI-assisted coding that actually scales. Context, plans, and agent coordination without the groundhog-day workflow.

Live index of cursor-rules files from GitHub, updated every 15 minutes

A production-grade SDLC harness for human + LLM software teams: mechanical gates for quality, security, architecture, evals, and release discipline.

Assignment 1: Inductive Synthesis – EN.601.727 Machine Programming

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.

A Claude Code skill for understanding an unfamiliar codebase fast — systematic exploration from entry points to data flow.

Documenting my experiences with AI-assisted development. Personal insights, discoveries, and reflections on coding with AI tools.

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.

An harness and behavioral guidelines to enforce reliable execution in AI coding agents.

Benchmarking different Large Language Models on practical software development challenges

Andrej Karpathy's LLM coding guidelines adapted as a Gemini CLI Skill

Disclosure Pilot AI is a full-stack desktop application that demonstrates using Large Language Models to automate the drafting, compilation, and iXBRL compliance tagging of SEC quarterly Form 10-Q and yearly Form 10-K financial reports.

Portable repo-first coding guardrails for ChatGPT, Codex, Claude, and Gemini. Narrow diffs, explicit assumptions, and verification-first workflows.

A Claude Code skill for hypothesis-driven debugging — reproduce, isolate, hypothesize, test, fix, document. Find the root cause, not a workaround.

A Claude Code skill for fast troubleshooting — a lightweight diagnostic pass for common issues when the full debug protocol is overkill.

A Claude Code skill for domain-aware code review — classify the code, then review for the failure modes that domain actually has.