Summary This unofficial project reconstructs design decision principles from Mino Drive's public materials into AI Skills. It targets engineers and power users seeking to improve the repeatability and verifiability of their design processes. By systematically checking problem framing, domain models, contracts, and architecture, the suite enables evidence-based decision-making and produces robust, traceable deliverables, moving beyond mere imitation of human style.

How It Works The core approach packages design principles as distinct AI Skills (e.g., mino-problem-framing, mino-design-by-contract), invoked via an AI agent (Codex). Skills can be triggered implicitly or explicitly. The suite emphasizes structured, evidence-driven methodology, focusing on verifiable outcomes like code and contract tests, rather than AI explanations. It distinguishes original principles from suite mechanics (schemas, gates, workflows).

Quick Start & Requirements Skills integrate into an AI agent's environment, typically in a .agents/skills/ directory. Invocation is implicit or explicit (e.g., $mino-problem-framing). Validation scripts (validate-suite.ps1, validate-suite.sh) require PowerShell (Windows) or Bash 3.2+ (Linux/macOS) for structural integrity checks. The suite aims for cross-platform compatibility, abstracting OS-specific differences.

Highlighted Details

• Focuses on reconstructing decision principles and verifiable outcomes, not mimicking human speech.
• Emphasizes evidence, contract tests, and independent verification over AI explanations.
• Retains human judgment for critical decisions like product value and release approval.
• Skills are portable and designed to function independently of the original repository structure at runtime.

Maintenance & Community This is an unofficial project, not endorsed by Mino Drive. No specific community channels or dedicated maintainer information are provided in the README.

Licensing & Compatibility Licensing information is not specified in the provided README content. Compatibility for commercial use or linking with closed-source projects is therefore undetermined.

Limitations & Caveats The project is marked "Experimental / Preview." Structural validation passes on Linux/WSL but fails on the native macOS fixture runner. Behavioral evidence and application runtime correctness are unexecuted. Native Windows validation is also unexecuted. The suite supports decision-making, not domain expertise or approval.