aif-verify

What problem does it solve? After an AI-assisted implementation finishes, it is hard to know whether every planned task was actually completed, whether the code compiles and passes tests, and whether the work still aligns with project architecture, rules, and roadmap. This Skill automates that post-implementation audit. ## Core Features & Use Cases - Task Completion Audit: Walks every task in the plan file and marks each as complete, partial, not found, or skipped by inspecting the actual code. - Quality Gates: Runs build, test, and lint checks across multiple ecosystems (TypeScript, Go, Python, Rust, PHP) and reports failures with file references. - Consistency & Context Gates: Detects plan-vs-code drift, leftover TODO/FIXME markers, undocumented environment variables, and violations of architecture, rules, and roadmap documents. - Strict Mode: Use --strict before merging to enforce zero partial tasks, passing tests, and clean lint. - Use Case: After running an implementation workflow on a feature branch, invoke verification to get a report showing 7 of 8 tasks complete, one missing email-sending integration, and an undocumented environment variable—then route the findings into a fix pass. ## Quick Start Ask the assistant to verify the completed implementation against the current plan, optionally in strict mode before merging.