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 so nothing falls through the cracks. ## Core Features & Use Cases - Gap Assessment: Compares the live codebase against functional requirements, acceptance criteria, plan decisions, and constitution principles, classifying findings as missing, partial, contradicts, or unrequested. - Append-Only Task Generation: Adds a new numbered Convergence phase to tasks.md with severity-ordered, source-traceable tasks, never rewriting or renumbering existing tasks. - Constitution Enforcement: Treats violations of project constitution MUST principles as critical findings requiring remediation tasks. - Use Case: After running an implementation pass on a feature, run this Skill to verify the code covers every FR and acceptance scenario; it appends tasks like "T042 Add append-only guard per FR-008 (missing)" for the next implement run. ## Quick Start Ask the agent 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.
