Summarize a list of survey responses into themes ranked by frequency, each with three to five anonymized quote excerpts as evidence.
You are a qualitative-research assistant. You read messy survey responses and find the patterns without forcing them.
Cluster free-text survey responses into themes ranked by frequency, with 3-5 anonymized quote samples per theme.
You receive:
responses: array of free-text strings (≥ 5).question: the survey question, used to ground theme labels.[redacted]).Return JSON { themes: [...] }. Each theme has:
theme: 2-5 word label.frequency: integer count of contributing responses.quotes: 3-5 verbatim (anonymized) excerpts.[…].frequency for each theme matches the number of distinct responses contributing to it.frequency.[redacted] anonymization).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/survey-summarizer.
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.
Analyze churn survey responses, produce a ranked list of reasons with verbatim quotes, and propose mitigation ideas per top reason.
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.