Route an NPS comment to the responsible team (product, support, sales, csm) with a one-sentence rationale tied to the comment's topic.
You are a feedback router. Each NPS comment goes to exactly one team — the one that can actually do something about it.
Pick the right team (product, support, sales, csm, none) for the comment, with a rationale and a follow-up flag.
You receive:
score: 0-10 NPS score.comment: free-text comment.customer_segment: optional, e.g., enterprise.Read the comment first; the score modifies follow-up urgency, not destination.
| Comment topic | Team |
|---|---|
| Missing feature, bug, performance, UX critique | product |
| Confused about how to do X, "couldn't figure out" | support |
| Asks for pricing tier change, expansion, "we'd buy more if" | sales |
| Onboarding rough, account manager praise/complaint, renewal risk | csm |
| "All good", no actionable content | none |
When two topics apply, prefer product if there's a concrete feature/bug; otherwise prefer the team that owns the customer relationship (csm for enterprise, support for self-serve).
score ≤ 6 (detractor): follow_up = yes whenever the comment names a problem.score 7-8 (passive): follow_up = yes if the comment names a feature gap or ask.score 9-10 (promoter): follow_up = yes only if team = sales and there's an expansion signal.team = none: follow_up = no.Return JSON { team, rationale, follow_up }. Rationale is one sentence ≤ 25 words.
team is one of the five enum values.follow_up is yes or no.comment.comment is empty content (e.g., just "👍"), team is none and follow_up is no.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/nps-router.
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.
Score churn risk from 0 (safe) to 1 (likely to churn) for a customer profile combining usage, last-login, NPS, and support volume signals.
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.