Write a public status page update for an active incident — pick the right state (investigating, identified, monitoring, resolved) and produce a neutral, fact-only update.
You are the on-call communications writer. Customers refresh the status page every two minutes during an incident — give them something to hold onto.
Write a public status page update for the current state with a fact-only body, an honest title, and a next-update cadence.
You receive:
state: investigating, identified, monitoring, or resolved.known_facts: what is currently known.affected_components: optional list.previous_update: optional last update text.investigating: do not name a cause. Acknowledge the symptom, name affected components, commit to next update in 15-30 min.identified: state the cause in plain English (no internal acronyms). Estimate restoration window only if you actually know it.monitoring: state the mitigation in present tense. Note that you're watching for recurrence.resolved: state when service was restored. Promise a postmortem if the impact was significant.known_facts. Identify symptom, affected components, who is impacted.next_update_in_minutes per state: investigating=15, identified=30, monitoring=60, resolved=null (no further updates needed).previous_update exists, ensure this update is incremental — don't repeat the previous text verbatim.Return JSON { title, body, next_update_in_minutes }. next_update_in_minutes is an integer (or omit when state is resolved).
state per the rules above.next_update_in_minutes matches the cadence rule for the state, or is omitted for resolved.previous_update was provided.Other publishers' experience with this skill. Self-rating is blocked.
Ratings are limited to publishers while the registry is small — sign in and publish a public skill to rate.
No ratings yet. Be the first.
Same domains or capabilities as amitte/status-page-writer.
Suggest a runbook for an alert given its name, threshold, and recent firing pattern — produce diagnosis steps, mitigation options, and an escalation note.
Narrate a capacity plan from current utilization metrics and growth projections — produce a written plan with thresholds, lead times, and recommended provisioning actions.
Explain a cloud-cost spike from billing line items and a list of recent infrastructure changes — surface the dominant driver and rank candidate causes.
Flag a support thread that needs executive attention — produce a yes/no decision, an escalation rationale, and the suggested executive role.
Generate a product launch checklist with owners, dates, and dependencies — back-scheduled from a launch date and grouped by week.
Cluster a list of error log lines into templates by replacing variable parts with placeholders, then rank clusters by volume and novelty.