metrics-definer
Skill152 starsChanged 9 months agoMITView on GitHub
Primary Metric - Name, exact definition, measurement method, target, timeframe Secondary Metrics (2-3) - Name, definition, why it matters Guardrail Metrics (2-3) - What should NOT get worse. Current baseline and acceptable range. Leading Indicators - What to measure in week 1 that predicts long-term success Anti-Metrics - What metric going UP would actually be bad Bad metrics (vague, unmeasurable): Good metrics (precise, measurable, useful):
1 other project uses a version of this.
Adopted by
Most recently taken up by
- WilliamWJHuang/ab-test-causal-inference-skillstheir own version, first seen Apr 18, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- WilliamWJHuang/ab-test-causal-inference-skills★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- competitive-analysisSkill
- launch-checklistSkill
- prd-writerSkill
- sprint-plannerSkill
- user-researchSkill
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 63
Every metric needs a precise definition.
- Distinctive: line 65
Always specify the data source.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Metrics Definer
Trigger
Activate on "define metrics", "what should I measure", "success metrics for [feature]", "KPIs for [initiative]".
Behavior
Step 1: Get Context
Ask:
- What feature or initiative?
- What's the goal?
- What can we currently measure?
Step 2: Define Metrics
Primary Metric
- Name, exact definition, measurement method, target, timeframe
Secondary Metrics (2-3)
- Name, definition, why it matters
Guardrail Metrics (2-3)
- What should NOT get worse. Current baseline and acceptable range.
Leading Indicators
- What to measure in week 1 that predicts long-term success
Anti-Metrics
- What metric going UP would actually be bad
Example
Bad metrics (vague, unmeasurable):
Primary Metric: Engagement
Secondary: User satisfaction
Guardrail: PerformanceGood metrics (precise, measurable, useful):
Primary Metric:
- Name: 7-day feature activation rate
- Definition: % of users who complete at least one [action] within
7 days of first exposure to the feature
- Measurement: Event tracking via Mixpanel. Event: "feature_action_completed"
- Baseline: N/A (new feature)
- Target: 30% within 90 days of launch
- Timeframe: Measured weekly, evaluated at 90 days
Guardrail Metrics:
- Overall page load time stays under 2s (p95). Currently: 1.4s.
Acceptable range: up to 2.0s. Beyond 2.0s = performance regression, pause rollout.
- Support ticket volume for this feature area stays below 50/week.
Anti-Metric:
- Daily active usage going UP could be bad if it means users are
confused and returning to retry failed actions. Cross-reference
with task completion rate — high DAU + low completion = friction.Rules
- Every metric needs a precise definition. "Engagement" without defining what counts is not a metric.
- Flag metrics requiring new instrumentation with [NEEDS INSTRUMENTATION]
- Always specify the data source. No metric exists without a measurement method.
- Anti-metrics are mandatory. If you cannot identify one, you have not thought hard enough about perverse incentives.
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.