retro

Analyze AIDLC guardrail events and generate advisory suggestions from manifest.json files.

2|Updated Jan 29, 2026
One-click install
npx skills add https://github.com/mikev10/olympus --skill retro-mikev10
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: retro
Source: https://github.com/mikev10/olympus/tree/main/resources/skills/retro
Command: npx skills add https://github.com/mikev10/olympus --skill retro-mikev10

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps identify recurring issues and areas for improvement in your AI-driven development (AIDLC) workflows by analyzing guardrail events and workflow data.

Core Features & Use Cases

  • Guardrail Retrospective: Analyzes gate rejections, trust changes, and CI failures.
  • Pattern Identification: Groups similar rejection reasons and tracks trust level changes.
  • Suggestion Generation: Creates a checklist of advisory recommendations for future workflows.
  • Use Case: After a complex development cycle, use /retro to understand why certain gates were repeatedly rejected, helping to refine the process for the next iteration.

Quick Start

Run the retro skill to analyze the current AIDLC workflow for guardrail events and generate improvement suggestions.

Frequently Asked Questions about retro

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

FAQPage Schema
How do I analyze AIDLC guardrail events for continuous workflow improvement?

To analyze AIDLC guardrail events for continuous workflow improvement, run a retrospective on gate audits and trust state changes. This identifies recurring rejection patterns and generates advisory checklists for future iterations.

How do I identify recurring gate rejection patterns in AI-driven development pipelines?

You identify recurring gate rejection patterns by scanning aidlc-docs/ for manifest.json files and analyzing validation reports. This retrospective analysis groups similar rejection reasons to pinpoint workflow bottlenecks.

What is the best way to track trust state changes during a development cycle retrospective?

The best way to track trust state changes during a development cycle retrospective is to analyze gate audit events within your AIDLC manifest files. This highlights workflow compliance issues and generates improvement checklists.

Do I need manifest.json files to perform AIDLC workflow analysis?

Yes, you need manifest.json files stored in the aidlc-docs/ directory to perform AIDLC workflow analysis. The retrospective requires scanning these files to access gate audit, trust state, and validation reports.

When should I run a retrospective analysis on my AI development workflows?

You should run a retrospective analysis on your AI development workflows after completing a complex development cycle. This post-workflow analysis identifies why gates were repeatedly rejected and generates suggestions for the next iteration.