Spec-driven coding skills for AI agents: plan with acceptance criteria, self-correct from feedback, and remember reusable project knowledge.
Skill Claude CodeCodex
Run a spec-driven correction loop for code that already exists by comparing the current implementation against the spec and using linter output, test failures, runtime logs, and review feedback to diagnose and fix gaps. Use this whenever code is failing checks, drifting from acceptance criteria, regressing after…
Skill Claude CodeCodex
Capture and retrieve durable project memory for spec-driven engineering, including decisions, constraints, setup steps, root causes, fixes, patterns, and reusable snippets through lightweight local indexing and keyword retrieval. Use this whenever the user wants to save knowledge for later, look up prior solutions…
Skill Claude CodeCodex
Turn ambiguous software requests into BDD-style implementation-ready specs with clear scope, constraints, assumptions, acceptance criteria, validation steps, execution guardrails, and an implementation plan. Use this whenever the user is defining requirements, asking for a plan or spec, wants boundaries clarified…