evidence-recap
Turn AI programming conversations and project delivery materials into a verifiable nine-part evidence chain, distinguishing problems, decisions, individual actions, delivery stages, outcome evidence, and responsibility boundaries. Use when the user runs /evidence-recap, $evidence-recap, or explicitly requests a recap of the AI programming process, delivery records, implementation status, and evidence gaps; do not use when only resume rewriting, source-code walkthroughs, or mock interviews are needed.