Interviews you about a real operating problem, systems that don't talk to each other, data nobody has time to analyze, insights that never make it back into a decision, then walks the Five Generations ladder to pick the earliest generation of AI, or no AI at all, that clears the bar at every stage of the pipeline. Scaffolds a real, runnable Python project with a branded local web UI that animates each stage live as it runs, on your uploaded data or realistic sample data standing in for it, and produces insights plus concrete recommended revisions and optimizations. After the plan is approved, forks into a fast build (sample data, no keys required) or a real build (your integrations, a stamped .env, and a six-persona compliance review, HIPAA, PCI, a CISO, GDPR, SOC 2, and a software and AI lawyer, before anything ships).
- Interview: the problem, the systems involved, the data's shape, the decision it should drive, and how often it should run.
- Design: the earliest generation of AI that clears the bar at every pipeline stage, stated and reasoned, then the full plan approved before anything is built.
- Fork: a fast build on sample data with no keys required, or a real build with your named integrations and API keys.
- Build and run: a working Python repository with a branded, animated local UI; on the real build, six independent compliance reviews with strategic recommendations and applied fixes.
You provide
- Your description of the problem, the systems, and the data
- The decision the output should drive, and how often it should run
- Your own files, or a go-ahead to use realistic sample data
- Fast build or real build, and, on the real build, the systems and integrations to name in .env
You receive
- A complete, runnable Python repository with a README and the exact command line to start it
- A branded local web UI animating the pipeline live, stage by stage, each tagged with its generation of AI
- results/: every run, timestamped, with the insights and recommended revisions and optimizations
- Real build only: docs/compliance-review/, six persona reviews plus applied-fixes.md and punch-list.md
Download this skill and its install guide: https://exec-skills.paulcheek.com/skills/cheek-art-of-the-possible
How to use this skill
Once installed, start a new conversation and paste this prompt. The slash command invokes the skill directly; everything after it is your opening brief, so edit it to fit.
Sample output
A completed run of this skill for a sample company, Mastercard, exactly as the deliverable would arrive. Open it in a new tab.
The samples are illustrative demonstrations of the output format, built from public information. Mastercard is not affiliated with and has not endorsed these materials.