Diagnose, audit, and repair OpenClaw hosts when an agent, gateway, plugin, cron, model route, memory engine, channel, approval policy, or update looks broken, expensive, slow, looping, stale, or misconfigured. Use for focused OpenClaw health checks, post-update triage, plugin update verification, model provider/API wiring audits, cron timeout/root-cause work, exec approval/reviewer problems, and rectification plans that need live proof against openclaw.ai docs instead of guesses.
Use when updating OpenClaw or debugging an OpenClaw instance after an update. This skill acts as a structured update runbook with emphasis on gateway startup, service-manager state, plugin registry and install drift, bundled-vs-npm/clawhub plugin confusion, stale config carried across upgrades, channel health, task ledger corruption, and logs that explain why the updated system is slow, disconnected, or half-broken.
Reframes terse task prompts before executing them. Use whenever the user submits a short imperative asking Claude to review, analyze, draft, evaluate, audit, summarize, or critique, AND the prompt lacks at least two of: role, output format, audience, depth. Trigger on prompts like "review this contract", "analyze this model", "draft a memo on X", "look at this code", "evaluate this", "what do you think of this". Do NOT trigger when the prompt specifies role + format + depth, when it's conversational/exploratory, when mid-execution on a defined task, or when prefixed with `raw:` or `go:` (explicit bypass). Err toward triggering — the cost of one clarifying turn is low; a misaimed deliverable is high.