ai-readiness

Review API design across 7 weighted categories — REST conventions, HTTP status codes, schemas, contracts, versioning, pagination, and idempotency.

Review codebase architecture across 6 weighted categories — layering, dependencies, design patterns, module boundaries, SOLID principles, and scalability.

Perform a structured code review across 7 weighted categories — naming, duplication, error handling, complexity, dead code, language practices, and style consistency.

Run a comprehensive 10-section AI readiness audit covering documentation, naming, DRY, structure, dependencies, tests, security, git hygiene, and AI config.

Audit git repository health using the 71 anti-patterns framework with DORA-derived severity scoring across branching, commits, merges, and release patterns.

Security-focused code review across 6 categories with OWASP Top 10 mapping — injection, auth, secrets, input validation, config, and cryptography.

Assess test quality combining 6-category weighted evaluation with test pyramid analysis and desiderata macro goals.

Evidence-first auditor that assesses how well a codebase supports AI coding assistants. Use when performing a comprehensive AI readiness assessment, running multiple audit types, or producing a unified readiness report.

Knowledge about AI context windows, token budgets, and signal-to-noise ratio. Use when assessing AI readiness or explaining how context impacts AI performance.

DORA metrics knowledge — deployment frequency, lead time, MTTR, and change failure rate. Use when evaluating git health or delivery performance.

Common fixes across audit categories organized by priority. Use when producing actionable remediation recommendations in audit reports.

Unified scoring framework with weighted categories, severity levels, pass/fail thresholds, and auto-fail conditions. Use when computing or interpreting audit scores.