whats-on-fire

原文涵盖的主题

• What's On Fire
• 1. Prerequisites
• 2. Pull all surfaces in parallel
• A. Production fires
• B. Stuck shipping + backlog heat
• C. Blind spots
• 3. Roster and rollup
• Coverage is counted, never assumed

One cross-product sweep of everything currently broken or stalled across a GitHub org, ranked, and routed to the repo that owns it. This skill is read-only. It pulls, correlates, ranks, and reports. It NEVER files issues, changes Sentry status, or mutates anything — which is what makes it safe to run on a loop or a schedule. Scope boundary. This decides which product deserves attention today. It deliberately does not decide what to do inside that product — no tech-debt scan, no next-bet synthesis, no backlog grooming. Those don't roll up meaningfully across a dozen products, and each repo's own survey-work already does them with repo-specific knowledge this skill has no business duplicating. Report the fire, name the repo, hand off. Run these probes. For each failure, label that surface skipped — in the output and continue. Never abort the whole sweep on one missing precondition. GitHub CLI — gh missing entirely (cloud/CCR routine sessions ship without it) is the one probe failure that does NOT skip its surfaces: route the section 2B pulls through the GitHub-MCP fallback in references/cloud-fallback.md instead. Three parts of that surface have no MCP equivalent at all — Dependabot

这里只展示节选，请以完整原文和当前要求为准。