Two follow-ups in backlog-burndown "Dispatching a Worker", both one-clause fixes, left out of the pull request that added the skill because they are pre-existing rather than introduced by the round that found them.
The local-strict-review bullet retires a worktree unconditionally, then conditionally. It reads "It reports that rather than pushing, and its worktree is then retired, since git refuses to attach that branch anywhere else while the reporting tree holds it", and two sentences later "A clean tree is retired and the group re-dispatched to a seat that can dispatch. A dirty one is left exactly as it stands and the group stopped for the maintainer." Followed literally, the first sentence removes a tree holding uncommitted work, which is the exact harm both "Cleanup Is the Orchestrator's" and "Bounding the Wait on a Worker" exist to prevent. One qualifier settles it: a clean one is then retired.
A stopped standalone-clone group has no end state. The skill now says such a group "stops for the maintainer with the clone named, and no seat this skill defines resumes it". The only stopped-group machinery is "Raising a Blocked Question", which says "A stopped group keeps its branch and its claim" and "Resuming retires that worktree first, then dispatches a fresh worker" — and the new clause denies exactly that resume. So the group holds its claim comment indefinitely, nothing releases it, and nothing returns the issue to a later round's ranking after the maintainer acts. The section needs to say what releases a claim whose group will never resume, which is a design call rather than a wording fix.
Two smaller items surfaced in the same read:
Raised by the local-strict-review carried-content passes on the pull request that added this skill, and deferred there under that skill's own review-round budget.
Two follow-ups in
backlog-burndown"Dispatching a Worker", both one-clause fixes, left out of the pull request that added the skill because they are pre-existing rather than introduced by the round that found them.The
local-strict-reviewbullet retires a worktree unconditionally, then conditionally. It reads "It reports that rather than pushing, and its worktree is then retired, since git refuses to attach that branch anywhere else while the reporting tree holds it", and two sentences later "A clean tree is retired and the group re-dispatched to a seat that can dispatch. A dirty one is left exactly as it stands and the group stopped for the maintainer." Followed literally, the first sentence removes a tree holding uncommitted work, which is the exact harm both "Cleanup Is the Orchestrator's" and "Bounding the Wait on a Worker" exist to prevent. One qualifier settles it: a clean one is then retired.A stopped standalone-clone group has no end state. The skill now says such a group "stops for the maintainer with the clone named, and no seat this skill defines resumes it". The only stopped-group machinery is "Raising a Blocked Question", which says "A stopped group keeps its branch and its claim" and "Resuming retires that worktree first, then dispatches a fresh worker" — and the new clause denies exactly that resume. So the group holds its claim comment indefinitely, nothing releases it, and nothing returns the issue to a later round's ranking after the maintainer acts. The section needs to say what releases a claim whose group will never resume, which is a design call rather than a wording fix.
Two smaller items surfaced in the same read:
Raised by the local-strict-review carried-content passes on the pull request that added this skill, and deferred there under that skill's own review-round budget.