telemetry-to-product-insights
Skill0 starsChanged 5 months agoMITView on GitHub
Use when reviewing product telemetry, funnel notes, event exports, dashboard screenshots, or metric summaries to produce grounded insights, hypotheses, experiments, and data caveats.
In this repository19 other files it gives its agents.
- agent-handoff-briefSkill
- api-doc-to-tool-specSkill
- architecture-rfc-reviewSkill
- bug-report-to-reproSkill
- changelog-to-upgrade-planSkill
- competitive-research-briefSkill
- customer-call-to-prdSkill
- database-migration-risk-reviewSkill
- dependency-upgrade-risk-reviewSkill
- incident-log-to-postmortemSkill
- messy-notes-to-decision-logSkill
- privacy-data-flow-mapSkill
- prompt-to-eval-rubricSkill
- repo-launch-readiness-reviewSkill
- roadmap-to-release-planSkill
- security-review-checklistSkill
- support-ticket-to-evalSkill
- tool-permission-auditSkill
- workflow-automation-scoutSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Use when telemetry needs to inform a product decision, experiment, or follow-up analysis.
- Distinctive: line 15
Do not use when metrics definitions, time window, and source are completely unknown.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

