What problem does it solve? Ending a coding session cleanly requires several bookkeeping steps—confirming all work is committed, archiving finished tasks, and logging what was accomplished—which are easy to forget or do inconsistently. ## Core Features & Use Cases - Dirty-tree classification: Surveys uncommitted changes and distinguishes current-task work from unrelated parallel edits, blocking the wrap-up if task code is still uncommitted. - Task archiving: Archives the active task plus any other confirmed completed tasks via task.py archive, producing auto-committed chore(task): archive entries. - Session journaling: Records a session summary linked to the relevant commit hashes via add_session.py, producing a chore: record journal commit. - Use Case: After finishing a feature and committing code in workflow Phase 3.4, run this skill to archive the task and append a journal entry so the next session has full context. ## Quick Start Ask the AI to finish the current Trellis work session by archiving the completed task and recording a session journal with the recent commit hashes.
