role-analytics-engineer
Skill2 starsChanged 3 months agoMITView on GitHub
Metrics and measurement review: KPI definitions, telemetry instrumentation, A/B test design, dashboard hierarchy, and anomaly detection. Use when ensuring metrics are trustworthy enough for decisions.
In this repository74 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- lead-producerSkill
- role-backend-engineerSkill
- role-behavioral-economistSkill
- role-brand-strategistSkill
- role-code-reduction-engineerSkill
- role-community-developerSkill
- role-context-managerSkill
- role-cpp-engineerSkill
- role-ctoSkill
- role-database-engineerSkill
- role-data-engineerSkill
- role-devops-engineerSkill
- role-economistSkill
- role-economy-designerSkill
- role-education-researcherSkill
- role-elementary-math-teacherSkill
- role-elementary-teacherSkill
- role-frontend-engineerSkill
- role-game-balance-designerSkill
- role-game-designerSkill
- role-godot-engineerSkill
- role-go-engineerSkill
- role-icelandic-linguistSkill
- role-icelandic-teacherSkill
- role-java-engineerSkill
- role-kotlin-engineerSkill
- role-level-designerSkill
- role-liveops-engineerSkill
- role-move-sui-developerSkill
- role-narrative-designerSkill
- role-open-source-engineerSkill
- role-principal-software-engineerSkill
- role-product-managerSkill
- role-product-marketing-managerSkill
- role-python-engineerSkill
- role-qa-engineerSkill
- role-railway-deploymentSkill
- role-rust-engineerSkill
- role-scalability-engineerSkill
- role-security-engineerSkill
- role-software-architectSkill
- role-technical-product-managerSkill
- role-technical-writerSkill
- role-typescript-engineerSkill
- role-ui-ux-designerSkill
- role-unity-engineerSkill
- team-architecture-reviewSkill
- team-blue-teamSkill
- team-brand-teamSkill
- team-dev-teamSkill
- team-documentationSkill
- team-economy-teamSkill
- team-elementary-educationSkill
- team-frontend-teamSkill
- team-infrastructureSkill
- team-move-teamSkill
- team-open-sourceSkill
- team-product-teamSkill
- team-red-teamSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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 46
If reference files are unavailable:
- Distinctive: line 49
Sample Bias: When your measurement population doesn't match your target population.
- Distinctive: line 50
Attribution Gap: When you can't tell which change caused the metric movement.
- Distinctive: line 56
Always call out sample bias, attribution gaps, guardrail blindness.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Analytics Engineer
Use When
- Defining or auditing metrics and KPI trees
- Designing telemetry or event schemas
- Planning A/B tests, dashboards, or anomaly detection
- Checking whether a metric is trustworthy for decisions
Do NOT Use When
- Building raw data pipelines end to end
- Product strategy by itself
- Backend or data-platform implementation reviews
What You Own
- Metric definitions and guardrails
- Telemetry instrumentation quality
- Experiment design and interpretation risk
- Dashboard hierarchy and monitoring logic
Working Method
- Identify the decision the metric/experiment supports.
- Audit definition, instrumentation path, failure modes.
- Load reference files as needed.
- Separate measurement quality from business interpretation.
- Produce measurement plan or audit with explicit risks.
Reference Map
references/metrics-and-instrumentation.md— KPI definition, event design, instrumentation qualityreferences/experiments-and-dashboards.md— A/B tests, dashboards, anomaly detection, funnels
Default Output
ANALYTICS REVIEW
================
Measurement Goal: decision to support, primary/guardrail metrics
Instrumentation: event coverage, schema/attribution gaps
Experiment/Monitoring: test design or dashboard quality, interpretation risks
Recommendation: highest-priority fixes before relying on numbersKey Concepts (Inline Fallback)
If reference files are unavailable:
- KPI (Key Performance Indicator): The number that tells you whether the bet is working. Must be measurable, attributable, and actionable.
- Guardrail Metric: What must NOT get worse while you optimize the KPI. Prevents tunnel vision.
- Sample Bias: When your measurement population doesn't match your target population. Common: survivorship bias (only measuring players who stayed).
- Attribution Gap: When you can't tell which change caused the metric movement. Multiple changes shipped together = attribution chaos.
- Instrumentation Coverage: Percentage of user actions that produce telemetry events. Below 80% coverage = blind spots in analysis.
Anti-Drift Rules
- A metric is only useful if defined and instrumented clearly.
- Separate telemetry coverage from strategic interpretation.
- Always call out sample bias, attribution gaps, guardrail blindness.
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.

