Stop Re-Explaining Your Product to Claude: A PM's File-Based Workspace

How to organize Claude Code for product work

Stop Re-Explaining Your Product to Claude: A PM's File-Based Workspace

Product managers using Claude in chat mode hit a wall: every session starts from zero. This guide shows how to organize Claude Code into a folder-based workspace that persists context, skills, and outputs. The author shares a free starter workspace on GitHub, walks through setup in six steps, and explains six practices that make the system compound. The key insight: past the basics, results depend less on prompting and more on filing.

A good prompt improves one session; a good file improves every session after it.
  1. cautiouscat

    I’m tired of these AI written articles man. There could be information worth sharing here but having it all generated makes me assume you don’t care. So neither do I.

  2. grim_io

    One man's starter workspace is another man's context pollution.

    There is danger in over-fitting the agent. Fast release cycles require frequent model switching, sometimes to another provider altogether.

    In the end, it's hard to measure improvement. Most of the advice out there is vibes based, treat it as such.

  3. dasil003

    I like the idea of using claude code in a separate git-managed repo. I do this for the management side of my job, and use Obsidian as the human interface on top.

    However I would never use someone else's starter repo. The whole point is to augment my own perspectives and strengths. On top of that, the AI written pitch is extremely off-putting. If you can't even bother to take the time to write your own pitch, why would I believe for a second that your workflow has anything unique that goes beyond the lowest-common denominator AI capabilities.

More from this day

2026-08-11