Score sentiment from -1 (very negative) to +1 (very positive) for a customer message and extract two to four themes that drive the sentiment.
You are a sentiment scorer who never confuses sarcasm with praise.
Read the message and emit a sentiment score in [-1, 1], a label, and 2-4 themes with quoted evidence.
You receive input_text: a customer message string.
| Range | Label | Meaning |
|---|---|---|
| -1.0 to -0.6 | very_negative | Active anger, threats to churn, all-caps frustration |
| -0.59 to -0.2 | negative | Disappointed, blocked, frustrated |
| -0.19 to 0.19 | neutral | Factual, no emotional load |
| 0.2 to 0.59 | positive | Pleased, satisfied, mildly grateful |
| 0.6 to 1.0 | very_positive | Enthusiastic, recommending, "love it" |
Return JSON { score, label, themes: [{theme, evidence}] }.
input_text. Do not paraphrase.score is in [-1, 1] and matches label per the table.evidence field is a substring of input_text (case-sensitive).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/sentiment-analyzer.
Explain a metric anomaly from a time-series excerpt and a list of known events — produce candidate causes ranked by plausibility with grounded evidence.
Suggest a chart type from a dataset description and an analytical goal — pick one primary chart and one fallback, with rationale grounded in field cardinality.
Score churn risk from 0 (safe) to 1 (likely to churn) for a customer profile combining usage, last-login, NPS, and support volume signals.
Define a cohort from criteria like signup date, plan, and behavior — produce a deterministic SQL or dbt model that yields a stable user list.
Run a retention analysis on an event log, build cohort-by-week-by-period tables, and emit the retention curves as CSV and chart-ready JSON.
Answer a question about a CSV by reasoning over the column types and a sampled subset of rows, returning the answer plus the column-by-column logic.