What problem does it solve? Teams adopting AI coding agents on existing (brownfield) projects often don't know whether their current stack helps or hinders agent workflows. This Skill audits the detected stack against four quality gates—typed, convention-based, popular in training data, and well-documented—and produces concrete compensation strategies instead of recommending a rewrite. ## Core Features & Use Cases - File-driven stack detection: Reads project markers like package.json, pyproject.toml, Cargo.toml, go.mod, and Gemfile to identify language, framework, build tool, test runner, package manager, CI/CD, and deployment target. - Four-gate scoring matrix: Scores each component with cited evidence from actual config files, producing a pass/fail matrix and an overall readiness verdict (ready, ready-with-compensation, or significant-friction). - Ready-to-paste compensation rules: For every failed gate, generates concrete AGENTS.md instruction entries (conventions, type rules, framework idioms) the user can copy directly. - Use Case: A team with an Express.js codebase runs the assessment, learns the stack fails the typed and convention-based gates, and receives paste-ready AGENTS.md rules documenting middleware order and validation patterns before running a health check. ## Quick Start Ask the AI to assess my stack for agent-friendliness in the current project directory.
