What problem does it solve? After running an implementation pass, teams often cannot tell whether the code actually satisfies everything the spec, plan, and tasks demanded. This Skill closes that gap by auditing the current codebase against the feature's spec.md, plan.md, and tasks.md, then appending any unbuilt or incomplete work as new traceable tasks so the implement step can finish the job. ## Core Features & Use Cases - Gap Assessment: Compares functional requirements, acceptance scenarios, plan decisions, and constitution principles against the actual code, classifying findings as missing, partial, contradicts, or unrequested. - Append-Only Task Generation: Adds a new numbered Convergence phase to tasks.md with zero-padded task IDs ordered by severity, never modifying existing tasks, specs, or code. - Severity Grading: Ranks findings CRITICAL through LOW, with constitution MUST violations treated as the highest severity. - Use Case: After running /speckit-implement on a feature, run this Skill to discover that FR-008's append-only guard was never built; it appends a new task to tasks.md so the next implement pass completes it. ## Quick Start Run the speckit-converge skill to check my current feature implementation against its spec, plan, and tasks and append any remaining work to tasks.md.
