GSD: Extract Learnings

What it does

This skill automates extraction of structured learnings from completed project phase artifacts (e.g., PLAN.md, SUMMARY.md, VERIFICATION.md, UAT.md, STATE.md) and writes them into a single LEARNINGS.md. It captures decisions made, lessons learned, recurring patterns, and unexpected surprises so teams can review and iterate on outcomes. The output is intended for project retrospectives, documentation, and future planning.

When to use it

Use this skill at the end of a project phase, after verification or UAT completes, or whenever you want a concise summary of what happened during a phase. Ideal for maintainers who want to preserve institutional knowledge, spin up retrospectives, or generate post-mortem inputs quickly.

What's included

• Scripts: none bundled with the SKILL (has_scripts=false).
• References: none detected.
• Instructions: the SKILL.md body defines an objective and an execution_context pointing to a workflow at ${CLAUDE_PLUGIN_ROOT}/workflows/extract_learnings.md. The procedural guidance is: locate phase artifacts, parse decisions/patterns/surprises, and compose a LEARNINGS.md following the repository's extract_learnings workflow.

Compatible agents

Designed for Claude Code plugin environments (references to CLAUDE_PLUGIN_ROOT and GSD workflows). It uses file read/write and shell-style tooling, so any agent supporting Read/Write/Bash/Grep/Glob toolsets can run it.