bradygaster Work Monitoring
Use this skill when monitoring Squad issues, pull requests, CI, review feedback, or a labeled work queue.
Scope
- Start with a named repository, explicit workstream, label set, and state filter.
- Produce monitoring reports, triage summaries, and narrowly scoped coordination actions.
- Do not turn monitoring into product implementation or broad cleanup.
Procedure
- List candidates using the narrowest available filters.
- Hydrate every candidate before mutating it; list results alone are not sufficient evidence.
- Prioritize untriaged work, assigned work, CI failures, review feedback, and approved pull requests according to the active request.
- Route domain work to the accountable specialist in
.squad/routing.md. - After every mutation, refetch the exact item and verify the requested transition and fields.
- Stop immediately on a verification mismatch; do not continue with later mutations.
- Use the focused two-pass scan for broad retrieval, then inspect only actionable candidates.
Stop Conditions
- Stop before mutation when the workstream, labels, repository, or state filter is ambiguous.
- Stop when candidates cannot be hydrated or post-mutation state cannot be verified.
- Stop when an action would exceed the explicitly scoped queue or become product work.
Anti-Patterns
- Applying bulk changes from a generic label alone.
- Closing, relabeling, assigning, or deleting based only on list output.
- Treating Ralph's monitoring role as authorization to modify product artifacts.