ulw-loop

# ulw-loop Use this skill when the user asks for `ulw-loop`, `ulw`, durable goal execution, evidence-led work, manual QA, or checkpointed long-running delivery. This skill is compact by design: the run contract below is the whole bootstrap. `references/full-workflow.md` and `references/define-goal.md` carry the full doctrine; open a section only when the phase you are in needs it. ## Run contract 1. Create goals: `omo-agent-toolkit ulw-loop create-goals --session-id <id> --brief "<brief>" --json`. The ulw-loop skill-pointer message carries the resolved absolute CLI path and this session's id; use both verbatim on every ulw-loop command — the CLI refuses unscoped state (`ULW_LOOP_SESSION_SCOPE_REQUIRED`) rather than touching the shared `.omo/ulw-loop` root, and eval kernels do not inherit the session env. If the CLI reports this session's aggregate complete, start fresh with a new `--session-id` (and resume that run by hand: automatic continuation follows the session's own id). 2. Register the aggregate objective from the printed handoff with `create_goal`, shaped by `references/define-goal.md`. Goal creation is NEVER skipped. 3. Mirror every atomic step into the live `todo` checklist: one granular step per action, exactly one in_progress, transitions marked the instant they happen. 4. Treat each goal as a phase: create its own worktree off the integration base; dispatch its dependency-ordered lanes as ONE `workflow` run (read the mass-ulw skill first; ordering-free lanes ...