Summarize a release's customer-facing impact for an executive update, combining metric movements with qualitative customer quotes.
Takes a release's KPI movements plus a feed of customer quotes from the release window and produces a one-page exec update: lead with the headline metric, support with quote evidence, close with risks and the ask.
release_label: e.g., payments-2026-Q2.metrics_path: CSV with metric_name, baseline, current, target? rows over the release window.quotes_path: a list of {quote, customer_id, source, sentiment} (Slack, support tickets, surveys).risks: explicit list of known risks.current - baseline) and percent change. Tag each as improved, regressed, or flat (within +/- 2%).time-to-checkout metric.risks plus any regressed metrics.exec-update-<release>.md containing the five sections above. Stdout prints word count and the headline metric with delta.
Recompute deltas from raw metrics and confirm they match. For each quote, locate its source in quotes_path and confirm verbatim. Read the document with the question "would a busy exec know what changed and what to decide?" — if not, tighten. The "Ask" section must exist and be specific (a vague "let us know" is not an ask).
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/release-impact-summarizer.
Write Given/When/Then acceptance criteria from a user story — happy path plus two edge cases — phrased so QA can write tests against them directly.
Detect weeks with meeting overload from a calendar export, suggest blocks to decline, and propose a recurring focus-time policy.
Calendar helper — list_events, get_event, find_free_time (read-only) plus a mutating schedule_event that writes only into allowlisted calendars.
Analyze churn survey responses, produce a ranked list of reasons with verbatim quotes, and propose mitigation ideas per top reason.
Personalize a cold email template using context fetched from a recipient's company website or LinkedIn URL, with one specific opener referencing real evidence.
Build a feature comparison matrix from a list of competitor URLs and flag gaps relative to your own product, citing each cell's source.