Turn usage, sentiment, and engagement signals into a health score with clear reasons and recommended actions for any account.
Produce a structured customer health summary for a given account, including a scored health rating, the key signals driving it, and prioritized recommended actions for the CS team.
Invoke when preparing for a QBR, renewal, at-risk review, or routine account check-in for $account_name.
Using your connected tools (for example the CRM account record, product analytics, call transcripts from Gong, support tickets, and recent email threads), pull all available signals for $account_name: active users vs. licensed seats, feature adoption trends, recent NPS or CSAT scores, open or escalated tickets, and any flagged sentiment from calls or emails. If a needed tool isn't connected, ask the user to paste what's available.
Evaluate each signal category — product engagement, relationship sentiment, support burden, and strategic fit — and assign a sub-score of Red, Yellow, or Green. Note the specific evidence from step 1 that justifies each sub-score (e.g. 'DAU/MAU dropped 30% MoM', 'escalation opened 2 weeks ago with no resolution', 'champion left the account').
Roll up the sub-scores into a single overall health rating (Red / Yellow / Green) using weighted logic: product engagement carries the most weight, followed by sentiment, support burden, and strategic fit. Clearly state the one or two primary drivers that most influenced the overall score.
Generate 3–5 prioritized recommended actions for the CS team, ordered by urgency. Each action should name who should take it (CSM, AE, Support, Executive Sponsor), what the action is, and what outcome it targets (e.g. 'CSM to schedule an executive check-in within 7 days to re-establish champion relationship after recent stakeholder change — reduces churn risk').
Write a 3–5 sentence executive summary that could be shared with internal stakeholders or pasted into the CRM. It should cover the overall health rating, the top reason for it, and the single most important next step — written in plain, non-technical language.
Return a structured report with five labeled sections: (1) Signal Breakdown — a table or list of the four categories with Red/Yellow/Green sub-scores and evidence; (2) Overall Health Rating — the rolled-up score and primary drivers; (3) Recommended Actions — a numbered priority list with owner, action, and target outcome; (4) Executive Summary — a short paragraph; (5) Data Gaps — any signals that were unavailable and would improve confidence in the score.
Copy this skill into your library to inject it into Claude, ChatGPT, and Gemini — or install your whole library as / slash commands in Claude Code and Cowork.
Get started free →Related skills
Reconstruct why an account churned after a non-renewal notice, surface missed risk signals, and produce a SWOT and save plan.
Turn a customer issue into a structured internal escalation brief covering impact, timeline, blockers, and team asks.
Turn usage signals and account context into a compelling expansion or upsell case with a clear value story and recommended offer.