outcome-review

Analyze post-release feature metrics and create Jira follow-up tickets.

6|Updated Feb 13, 2026
One-click install
npx skills add https://github.com/damianpapadopoulos/auto-claude-skills --skill outcome-review-damianpapadopoulos
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: outcome-review
Source: https://github.com/damianpapadopoulos/auto-claude-skills/tree/main/skills/outcome-review
Command: npx skills add https://github.com/damianpapadopoulos/auto-claude-skills --skill outcome-review-damianpapadopoulos

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires posthog, atlassian-rovo, pandas, requests, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables a thorough post-release review of features by analyzing real-world outcomes, checking adoption, error, or experiment metrics, and creating follow-up work as needed.

Core Features & Use Cases

  • Post-Release Analysis: Evaluate the performance of shipped features by querying metrics like adoption, errors, and experiment results.
  • Follow-Up Work: Automatically create Jira tickets for follow-up work based on the analysis findings.
  • Use Case: After shipping a feature, use this Skill to analyze its real-world performance, synthesize an outcome report, and decide on necessary follow-up actions.

Quick Start

Use the outcome-review skill to analyze the outcome of the 'new_feature' release, considering adoption and error metrics.

Frequently Asked Questions about outcome-review

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

FAQPage Schema
How do I analyze post-release feature adoption and error metrics from PostHog?

Post-release feature analysis queries PostHog adoption and error metrics using Python to synthesize real-world performance outcomes. It evaluates shipped features by gathering experiment results and calculating adoption rates to determine if release goals were met.

Can I automatically create Jira follow-up tickets based on feature review findings?

Jira follow-up ticket creation is supported through Atlassian Rovo and Jira API interactions. Based on synthesized post-release analysis findings like unexpected error rates, the Skill automatically generates required follow-up work items directly in Jira.

What's the best way to run a post-release experiment analysis and generate an outcome report?

Running a post-release experiment analysis requires PostHog access to query experiment results and Python libraries like pandas for data synthesis. The Skill processes these metrics to generate a comprehensive outcome report detailing adoption rates and errors.

Do I need Atlassian Rovo access to create follow-up work from post-release metrics?

Atlassian Rovo access is required alongside Jira API interactions to automatically create follow-up work. The Skill depends on this integration to translate analyzed post-release metrics and error findings into actionable tickets within your project tracking environment.

What data do I need to review shipped features for adoption rates and experiment results?

Reviewing shipped features requires connected PostHog data for querying adoption rates, error metrics, and experiment results. The Skill uses Python libraries including pandas and requests to gather and synthesize these post-release metrics for analysis.