feature-outcome-review

Name: feature-outcome-review
Availability: InStock
Author: aurora-atoms

Evaluate delivered features against intended outcomes using leading and lagging indicators.

Updated Jun 1, 2026

Search Tags:#metrics #evidence-based #product-management #decision-support #feature-delivery #outcome-review

Ready to run

npx skills add https://github.com/aurora-atoms/lattice --skill feature-outcome-review

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: feature-outcome-review
Source: https://github.com/aurora-atoms/lattice/tree/main/skills/feature-outcome-review
Command: npx skills add https://github.com/aurora-atoms/lattice --skill feature-outcome-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill addresses the common disconnect between shipping features and achieving actual business outcomes by providing a structured framework to evaluate performance against original goals.

Core Features & Use Cases

Outcome Validation: Compares intended user or business outcomes with observed evidence to prevent the fallacy of equating release with success.
Decision Support: Generates actionable recommendations (continue, adjust, expand, pause, or stop) based on confidence limits and evidence quality.
Use Case: After a new checkout flow has been live for two weeks, use this Skill to analyze adoption metrics and guardrails to determine if the feature should be expanded to other regions or paused for refinement.

Quick Start

Use the feature-outcome-review skill to analyze the performance of the recent checkout-optimization feature against its original success criteria and assumptions.

Frequently Asked Questions about feature-outcome-review

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

FAQPage Schema

How do I evaluate feature success against intended product outcomes?▼

To evaluate feature success, compare intended outcomes against observed leading and lagging indicators within a Feature Delivery Case. This evidence-based approach requires explicit success criteria, observation windows, and guardrails to identify invalidated assumptions and prevent equating release with success.

What is evidence-based product management for feature delivery?▼

Evidence-based product management uses observed metrics to evaluate delivered features against original assumptions. It identifies invalidated hypotheses by comparing leading and lagging indicators against predefined success criteria, generating evidence-backed recommendations like continue, adjust, expand, pause, or stop.

How do I generate product recommendations from feature adoption metrics?▼

Generate product recommendations by analyzing adoption metrics against confidence limits and evidence quality. The evaluation produces actionable decisions to continue, adjust, expand, pause, or stop the feature based on observed performance and guardrail violations within the observation window.

Can I use outcome review for features without predefined success criteria?▼

Outcome review requires explicit definitions of success criteria, observation windows, and guardrails to ensure high-fidelity decision-making. Without predefined success criteria, the framework cannot compare intended outcomes against observed evidence or identify invalidated assumptions effectively.

When do I need to run a feature outcome review?▼

Run a feature outcome review after a delivered feature has been live for its defined observation window, such as two weeks for a new checkout flow. It analyzes adoption metrics and guardrails to determine if the feature should be expanded, paused, or refined.

What is the best way to validate feature assumptions using leading and lagging indicators?▼

Validate feature assumptions by comparing intended outcomes against observed leading and lagging indicators within a Feature Delivery Case. This evidence-based evaluation detects invalidated assumptions and provides decision support based on confidence limits and evidence quality.