Discover the power of scripts. Add in a review process to the end of every session that identifies repeated processes and ask Claude to turn it into a script. A very simple process that gives enormous leverage on your time and credits.

I was struggling for three months using Catalina, Claude Code V1.0.0, no Desktop integration and no VS CODE integration and very disconnected platforms. I tried installing Docker to run Ubuntu and even Docker was not working correctly on Catalina. Solution: I removed Catalina and installed Ubuntu for the first time. After using Windows and iOS for decades I can't believe I have never used Linux before, its incredible. In under half a day I had all of the latest builds of Claude Code, Openclaw, VS CODE and various agents up and running. What took me days to do now takes hours. I wasted days copy and pasting git diffs for review!

Just to test things out I loaded Jake's paper into claude/gemini and asked to guide me in implementing. What I finally came up with was a production-ready implementation of an Interpretable Context Methodology (ICM) workspace for processing multiple raw markdown drafts into publication-ready Hugo blog posts. A detailed project break-down and file contents at: https://rainmakers.pl/posts/172_extended_icm_for_hugo_posts/ Maybe someone struggling with implementation of the ICM will find it useful. Happy building! Wojtek

A folder structure based off 10 years of manufacturing experience. I've been overseeing delivery of systems from design through manufacturing and deployment in my professional work. Everyone has their own system for organizing and building their solutions; this is a natural extension of the environment I work in every day and managing these projects the same way I would any other. The beauty is just like the lean practices inspiring this, this is a framework. All the specifics and magic in the workflow live in the context files, template details, and addition resources. Want to add in your specific quality guidelines? Throw it in config and reference it in the quality stage context file. Want to always build a specific component the same way? Add another file and reference it in design and assembly. This framework can be shaped any way to fit your workflow but the principals remain the same. Here's a brief breakdown of the process flow as well as the files produced. The intention is that this is the flow of objects created called "systems". A system can be anything inside a folder: an artifact, and ICM workflow, a collection of files. As long as it can fit in a folder, it’s applicable. The system folder template is: - References - inspiration or applicable documents relevant to that specific system build - Work Instructions - Where all the documents named below are stored and read from during the workflow. Documents are moved from active to processed subfolders as they are used in the sequence. - System - Where the actual output of the build is placed. This is the resulting files, or workspace produced. - travel-sheet.md - a document recording progress and a summary of every step executed on the project as it progresses. The workflow is as follows: 01 Design: 1. Scope - Define the goal of the project. The outcome written in one statement. What success looks like. Produces scope.md 2. Design - Define a full breakdown of the intent of the system/artifact/solution to be built. What it is, what it isn't. What success looks like with a wider explanation as well as what failure looks like. The gritty details. Produces design-brief.md 3. Review - A sanity check of design-brief.md that all pieces are in place. Was anything missed? Will the build team need more information? Produces design-review.md 4. Manufacturing Kickoff - Converts design-brief.md into a condensed format for handoff to the build agents. Removes reasoning and intent for build and only provides instructions for build for context tightening. Also provides instruction for quality check and testing down the road. Produces blueprint.md, qa-brief.md, test-plan.md

I have spent over 100 hours going backwards with skills, the more I tried to fix folder structures and update Skills and add context and memory, the more shit started to break, I almost gave up, particularly with Opus, who is very literal. I was so used to brainstorming in Claude.ai chat that my verbose approach became my biggest enemy. Finally it clicked, i stripped it all back to a basic structure and clear instructions with a heavy focus on learning and iteration, within a couple of sessions code has transformed itself into the most amazing work partner. If anyone is struggling to get AI under control, stick at it, the end result is worth the pain and effort.