GSD: Extract Learnings

Trust Score 67/100

Extract structured decisions, lessons, patterns, and surprises from phase artifacts into a consolidated LEARNINGS.md file for project retrospection.

triggers:extract learningsgenerate LEARNINGS.mdproject retrospectivephase artifactssummarize decisions

GitHub SKILL.md

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.

Audit Summary

A Claude Code plugin prompt that instructs the agent to extract learnings from project phase artifacts (PLAN.md, SUMMARY.md, etc.) into a LEARNINGS.md file. The skill body is extremely thin — just an objective and a reference to an external workflow file via CLAUDE_PLUGIN_ROOT, so it cannot function standalone. No scripts to test. Allowed-tools include Bash which is broad for a documentation-only task.

Watch Out

Requires CLAUDE_PLUGIN_ROOT env var and external workflow file to function
Only works within the GSD plugin ecosystem
Cannot run standalone — all logic is in referenced workflow

Notes

Prompt-type skill with no scripts. Delegates entirely to an external workflow file. Allowed-tools includes Bash which seems unnecessary for a read/write documentation task — minor over-permission. No security concerns otherwise. Very niche — only useful within the GSD plugin framework.

Information

Repository: gsd-plugin
Stars: 22
Installs: 0

Trust Score

Overall67

Security95

Code Quality40

Architecture38

Usefulness42

More from gsd-plugin

Gsd:sketch

Sketch UI/design ideas with throwaway HTML mockups, or propose what to sketch next (frontier mode) - Read - Write - Edit - Bash - Grep - Glob - AskUserQuesti...

Related Skills

Development Worktree

Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

Bounty Hunter — Atlas

Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.

Junshi — Research Advisor

Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.

Full Stack Builder

End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Feishu Voice Sender

Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.

Claw Bench

Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.

Back to Skills