What problem does it solve?
This Skill helps you evaluate how well an existing codebase supports AI agent workflows by checking whether key properties for safe, reliable automation are present and by documenting what to add when they are missing.
Core Features & Use Cases
- Assesses agent-friendliness via four quality gates: type safety, convention-based structure, popularity within the language family, and documentation quality, producing a clear matrix-style assessment.
- Detects stack components from your project files: reads real markers like package.json/tsconfig, pyproject.toml, Cargo.toml, go.mod, Gemfile, composer.json, and *.csproj to infer language, framework, build tooling, CI signals, and instruction-file presence.
- Generates concrete compensation strategies: when a gate fails, it provides ready-to-paste instruction rules to add to AGENTS.md/related docs so an agent can operate effectively without replacing the stack.
- Writes an actionable output file: creates context/foundation/stack-assessment.md (brownfield) for downstream health checks and planning.
Quick Start
Run the skill in your existing project directory to produce an evidence-based stack assessment and ready-to-paste instruction-file additions for any gaps it finds.
