gds-retrospective

Facilitates post-epic retrospectives extracting lessons and action items from completed stories.

Updated Mar 14, 2026
One-click install
npx skills add https://github.com/ArchaonHW/MingGoRTS --skill gds-retrospective-archaonhw
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gds-retrospective
Source: https://github.com/ArchaonHW/MingGoRTS/tree/main/.agents/skills/gds-retrospective
Command: npx skills add https://github.com/ArchaonHW/MingGoRTS --skill gds-retrospective-archaonhw

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? After finishing an epic, teams often skip structured reflection, losing lessons buried in story files and repeating the same mistakes in the next epic. This Skill runs a guided, no-blame retrospective that mines story records, checks follow-through on prior action items, and prepares the team for the next epic. ## Core Features & Use Cases - Epic Discovery and Verification: Detects the completed epic from sprint-status.yaml, verifies all stories are done, and warns before running a partial retrospective. - Deep Story Analysis: Reads every story file to extract dev notes, review feedback patterns, technical debt, and recurring struggles across the epic. - Continuity Tracking: Loads the previous epic's retrospective and scores each prior action item as completed, in progress, or not addressed. - Next Epic Preparation: Previews the upcoming epic, maps dependencies on completed work, and lists preparation gaps and technical prerequisites. - Use Case: After closing Epic 4 of a game project, ask for a retrospective; the Skill facilitates a multi-agent team discussion (Product Owner, Senior Dev, QA) with you as Project Lead, then produces a retrospective document with lessons learned and owned action items. ## Quick Start Ask the AI to run a retrospective for the epic we just finished.

Frequently Asked Questions about gds-retrospective

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

FAQPage Schema
How do I run a retrospective after completing an epic?

Say "run a retrospective" or "let's retro the epic" and the Skill detects the completed epic from sprint-status.yaml, verifies story completion, then facilitates a two-part session covering epic review and next epic preparation.

How does the retrospective find which epic was completed?

It reads sprint-status.yaml first to find the highest epic with stories marked done, asks you to confirm, and falls back to scanning story filenames in the implementation artifacts folder if detection fails.

Can I run a retrospective if some stories are not done?

Yes, but the Skill warns that the epic is incomplete, lists pending stories, and asks for confirmation. A partial retrospective is flagged since lessons from unfinished stories will be missing.

Does the retrospective check whether previous action items were completed?

Yes. It loads the prior epic's retrospective and marks each committed action item as completed, in progress, or not addressed, cross-referencing evidence in the current epic's story records.

What inputs does the retrospective workflow need?

It needs sprint-status.yaml, the epic and story markdown files, the agent manifest, and optionally architecture, GDD, narrative, and PRD documents, plus the previous epic's retrospective for continuity analysis.