What problem does it solve? After an implementation pass, it is hard to know 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: Reads spec.md, plan.md, and tasks.md as the sole source of intent and classifies every finding as missing, partial, contradicts, or unrequested, with severity levels from CRITICAL to LOW. - Append-Only Task Generation: Appends a new "Phase N: Convergence" section to tasks.md with zero-padded task IDs traced to their source (FR-###, SC-###, US1/AC2, plan decisions, constitution principles), never rewriting existing tasks or touching application code. - Constitution Enforcement: Treats violations of MUST principles in .specify/memory/constitution.md as the highest-severity findings and emits remediation tasks first. - Use Case: After running /speckit-implement on a feature, run this Skill to verify nothing was missed; if gaps exist it appends tasks like "T042 Add append-only enforcement per FR-008 (missing)" so a follow-up implement pass completes them. ## Quick Start Ask the agent to run the speckit-converge skill to check the current implementation against the feature spec and append any remaining work to tasks.md.
