rainmanjam/poka-yoke

Audit code like spacecraft software. /nasa-code enforces NASA JPL’s Power of Ten rules: extended for the age of AI-generated code. Detect dangerous complexity, unsafe control flow, resource misuse, abstraction leaks, and LLM-induced engineering anti-patterns before they ship.

The agent that writes the code never reviews it. Spec-driven TDD with agent separation, adversarial QA, and dynamic rigor for Claude Code.

A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/Apps Script/JS/Swift). Security-first, phase-aware engineering discipline with a spec→plan→TDD→verify workflow.

Engineering guardrails for Claude Code: 51 skills, reviewer agents and hooks, most written after a real defect shipped. Installable as a plugin.

Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.

Expert code review skill: SOLID, security, performance, error handling, boundary conditions

Professional slash commands for Claude Code that provide structured workflows for software development tasks including code review, feature creation, security auditing, and architectural analysis.

Local-first AI coding workflow for vibe coders, indie hackers, technical founders and product managers — catch missing tests and safety checks across Claude Code, Cursor, Windsurf, Replit, Lovable and Bolt.new.

14 installable skills for Claude Code, OpenAI Codex, and Hermes: find unknowns, clarify requirements, manage context, test assumptions, and verify bug fixes with regression evidence.