What problem does it solve? After an implementation pass, it is hard to know whether the code actually satisfies everything the feature's spec, plan, and tasks promised. This Skill closes that gap by auditing the current codebase against those artifacts and appending any unbuilt or incomplete work as new, traceable tasks to tasks.md. ## Core Features & Use Cases - Gap Assessment: Reads spec.md, plan.md, and tasks.md as the source of intent, inspects the code in scope, and classifies findings as missing, partial, contradicts, or unrequested. - Severity-Graded Findings: Ranks findings CRITICAL through LOW, treating constitution MUST violations as highest severity, and presents a summary table before writing anything. - Append-Only Task Generation: Appends a new "Phase N: Convergence" section with zero-padded task IDs to tasks.md without modifying spec.md, plan.md, existing tasks, or any application code. - Use Case: After running /speckit-implement on a feature, run converge to verify FR-008 is actually enforced in the code; if not, a new task like "T042 Add append-only enforcement per FR-008 (missing)" is appended for the next implement pass. ## Quick Start Run the speckit-converge skill to check my current implementation against the feature spec and append any remaining work to tasks.md.
