// Use when coordinating PR review, CI triage, second-peer critique, requested-changes loops, merge readiness, or deciding whether implementation needs independent verification.
Parallel divergent ideation via mesh fan-out. Spawns N frame-shifted peers, scores results, deepens top survivors. Use on open-ended design choices, fuzzy bugs, naming, API surfaces, or explicit /adhd invocation. Skip for syntax, lookups, or closed prompts ("quick", "standard", "canonical").
Use when orchestrating complex or multi-lane work, decomposing tasks across peers, choosing status/board surfaces, running mesh roundups, or keeping high-level progress visible.
Use when creating, updating, or explaining a standing Repowire agent folder, worker folder, durable-job executor context, or reusable agent-specific AGENTS.md guidance.
Use when adding, updating, splitting, or reviewing local orchestrator skills for reusable procedures, including controlled self-improvement of the orchestrator.
Use when transferring orchestrator responsibility, summarizing current state for a new peer, recovering after a closed session, or preparing takeover notes.
Use when splitting work across peers, creating or selecting feature worktrees, preventing overlapping edits, or deciding whether to reroute implementation out of the main worktree.
| name | review-cycle |
| description | Use when coordinating PR review, CI triage, second-peer critique, requested-changes loops, merge readiness, or deciding whether implementation needs independent verification. |
Use review cycles when the cost of a missed bug is higher than the cost of an independent pass.
For failed checks, inspect the failing job and logs before guessing. Prefer the user's existing GitHub tooling or plugin when available.
Do not treat green CI as proof of product behavior. UI, daemon workflow, transport, and docs changes often need a targeted smoke test.
Call out:
Do not ship personal release cadence or authority rules in this skill.