gather-learnings

Scan memory/learnings to generate a Gotchas table for PRD/PRP sections.

50|9|Updated Oct 15, 2025
One-click install
npx skills add https://github.com/jpoley/flowspec --skill gather-learnings
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gather-learnings
Source: https://github.com/jpoley/flowspec/tree/main/.claude/skills/gather-learnings
Command: npx skills add https://github.com/jpoley/flowspec --skill gather-learnings

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams quickly extract, synthesize, and organize lessons learned from past projects to populate PRDs and PRPs with actionable Gotchas and risk insights.

Core Features & Use Cases

  • Scan memory/learnings for relevant lessons based on file paths, keywords, and tags.
  • Prioritize findings by direct file matches and relevance to current work.
  • Produce a ready-to-insert Gotchas/Prior Failures table for PRDs and PRPs.

Quick Start

Invoke the gather-learnings skill with inputs describing the feature, involved files, relevant keywords, and tags. It returns a markdown table suitable for PRD/PRP insertion.

Frequently Asked Questions about gather-learnings

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

FAQPage Schema
How do I extract lessons learned from past projects to avoid PRD pitfalls?

Gather-learnings identifies and curates relevant lessons from your memory and learnings repositories based on file paths, keywords, and tags, then generates a structured Gotchas table with Impact, Mitigation, and Source columns ready to insert into PRDs and PRPs.

What's the best way to populate a Gotchas section in a PRD or PRP?

Invoke gather-learnings with your feature context, involved file paths, relevant keywords, and tags. It matches against past learnings by direct file reference and contextual relevance, returning a prioritized top-5-8 markdown table ordered by match strength.

Can I use past project failures to inform risk sections in feature documents?

Yes. Gather-learnings scans memory for documented failures and risks tagged with keywords matching your current work, synthesizes them into actionable gotchas with mitigation strategies, and links back to original sources for reference.

How does gather-learnings prioritize which lessons to include?

The Skill ranks findings by direct file path matches first, then by contextual relevance to your supplied keywords and tags, ensuring the most applicable lessons appear at the top of the output table.

What input do I need to provide to generate a Gotchas table?

Describe your feature, supply the file paths involved in development, provide relevant keywords and tags from your domain, and gather-learnings matches these against stored learnings to produce the table.

Does gather-learnings work for team-based feature development workflows?

Yes. It's designed for feature development contexts where teams need to extract institutional knowledge from shared memory and learnings repositories to populate risk and gotchas sections in collaborative PRDs and PRPs.