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 unfinished 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 and classifies findings as missing, partial, contradicts, or unrequested, with severity levels from CRITICAL to LOW. - Append-Only Task Generation: Adds a new "Phase N: Convergence" section to tasks.md with zero-padded task IDs traceable to requirements (e.g., FR-003, US1/AC2), never modifying existing tasks or code. - Constitution Enforcement: Treats violations of MUST principles in .specify/memory/constitution.md as the highest-severity findings. - Use Case: After running /speckit-implement on a feature, run this Skill to verify nothing was missed; it either reports "Converged" or appends the remaining tasks so /speckit-implement can finish them. ## Quick Start Ask the assistant to run the speckit-converge skill to check the current feature's implementation against its spec, plan, and tasks and append any remaining work to tasks.md.