mstfash/skills ? reverse-engineered prompt

Reverse engineered prompt

Build me a small JavaScript repo for my daily AI agent workflow with Claude Code and Codex.

I want a set of reusable skills that help an agent plan work first, split it into phases, verify each phase properly, do strict code reviews, check frontend changes in a real browser, and pull docs out of single page apps into clean markdown. Make the main entry point a “ship loop” style flow so I can tell the agent to plan, pressure test the plan, build in phases, and only mark things done after the final checks pass.

Please include clear README instructions for how to use the skills, when to install them, and how the Claude Code plus Codex setup works. Also add simple visual diagrams or helper files for the workflow if that fits. Keep it practical and easy to reuse in other projects, and make sure the repo feels like something I could hand to an agent and start using right away. If you need current Claude Code or Codex plugin details, look them up online first.

Are you gonna build this?

make sure you review the code using coderabbit

Try freeSponsored — opens CodeRabbit in a new tab