skills.rest
pisithrps
pisithrpsCOMMUNITY
Explore all skills by this author →
𝕏@pisithrpsGitHub

feature-metrics

Define primary metrics, guardrails, and kill criteria using the STEDII framework.

Updated Mar 11, 2026
Search Tags:#metrics#prd#guardrails#stedii#experiment-metrics#measurement-plan#primary-metric
One-click install
npx skills add https://github.com/pisithrps/yapzee --skill feature-metrics-pisithrps
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: feature-metrics
Source: https://github.com/pisithrps/yapzee/tree/main/.claude/skills/feature-metrics
Command: npx skills add https://github.com/pisithrps/yapzee --skill feature-metrics-pisithrps

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Many product teams struggle to choose a single, trustworthy success metric and complementary guardrails for new features or experiments; this Skill helps define clear, testable metrics so teams can make data-driven go/no-go decisions. It reduces ambiguity in PRDs and A/B test definitions by applying a repeatable evaluation framework that ties metrics to product and business context.

Core Features & Use Cases

  • STEDII evaluation: Walks through Sensitive, Timely, Easy to understand, Directional, Implementable, and Independent checks for candidate metrics.
  • Context-aware routing: Instructs the assistant to pull PRDs, business model notes, historical baselines, strategy, and meeting context to ground metric choices.
  • Templates & outputs: Produces a primary-metric definition, guardrails table, kill criteria, and a measurement plan formatted for PRDs and experiment records.
  • Use case: A PM preparing an A/B test uses this Skill to pick a single primary engagement metric with guardrails for performance and error rates, estimate detectability given traffic, and produce the MD to paste into the PRD.

Quick Start

Define metrics for the Smart Recommendations feature by providing the feature name, the user behavior it changes, and the expected business outcome so I can propose a primary metric, guardrails, and kill criteria.

Frequently Asked Questions about feature-metrics

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I define success metrics for a product feature launch?▼

To define success metrics for a feature launch, apply the STEDII framework to evaluate candidate metrics for sensitivity, timeliness, directionality, and independence, then select a single primary metric with supporting guardrails and kill criteria.

What is the STEDII framework for product measurement?▼

The STEDII framework is an evaluation model for selecting product metrics, checking that candidates are Sensitive, Timely, Easy to understand, Directional, Implementable, and Independent to ensure trustworthy A/B test results.

How do I choose a primary metric and guardrails for an A/B test?▼

Choose a primary metric and guardrails by evaluating candidate metrics against product context and historical baselines, ensuring the primary metric captures the target behavior change while guardrails protect against performance or error rate regressions.

What context do I need to write a PRD metric section?▼

Writing a PRD metric section requires access to PRDs, business model context, historical baselines, and stakeholder notes to ground metric choices and produce a formatted measurement plan with kill criteria.

Does this approach work for setting kill criteria in experiments?▼

Yes, this approach works for setting kill criteria by evaluating the independence and implementability of guardrail metrics, establishing thresholds that trigger the termination of an underperforming feature or A/B test.

Best way to evaluate if a metric is sensitive enough for an experiment?▼

The best way to evaluate metric sensitivity for an experiment is to analyze historical baselines and traffic estimates, checking if the candidate metric can detect meaningful behavioral changes within the expected test duration.

Related Skills

Explore More Product & Management Skills→
pisithrpspisithrps

metrics-framework

Design leading and lagging metric hierarchies with correlation validation and alert thresholds.

Community
Advanced
nexu-ionexu-io
8.2k

experiment-readout

Structure experiment results into product decisions with required sections.

Official
Advanced
StreamPilotOrgStreamPilotOrg
1

ice-scorer

Score growth experiments using the ICE framework and update experiment JSON.

Official
Basic
sunnypatneedisunnypatneedi
11

north-star-metrics

Define a North Star Metric and input metrics with owner assignments.

Community
Basic