Telemetry to product insights
Skill alexzhu0/agent-ready-skills/skills/telemetry-to-product-insights
Ten practical AI-agent skills for turning messy work into clear context, evals, reviews, and launch-ready artifacts.
npx -y skills add alexzhu0/agent-ready-skills --skill telemetry-to-product-insightsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when reviewing product telemetry, funnel notes, event exports, dashboard screenshots, or metric summaries to produce grounded insights, hypotheses, experiments, and data caveats.
SKILL.md
1.4 KB, 256 tokens by cl100k_base, as published. Nobody here has run it
Telemetry To Product Insights
Purpose
Convert product metrics into usable product insight without pretending the data proves more than it does.
Fit
- Use when telemetry needs to inform a product decision, experiment, or follow-up analysis.
- Do not use when metrics definitions, time window, and source are completely unknown.
Inputs
- Event exports, dashboard screenshots, funnel notes, or metric summaries.
- Product context, time window, cohorts, and tracking definitions if available.
- The decision the metrics should inform.
Workflow
- Restate the metric source, time window, and known limitations.
- Identify signal, noise, anomalies, and missing breakdowns.
- Convert observed patterns into hypotheses.
- Recommend experiments or follow-up analysis.
- Mark any data quality issues that weaken confidence.
Output
Produce Markdown with:
- Data Snapshot
- Key Observations
- Product Insights
- Hypotheses
- Experiments
- Data Caveats
- Next Questions
Validation
- Insights are tied to observed data.
- Correlation is not presented as causation.
- Missing definitions or windows are called out.
- Experiments include a measurable success signal.
- Caveats are visible, not buried at the end.