Reverse Engineer to Learn

Absorbed app-teardown: this skill now performs the raw teardown itself — macOS app bundles, npm/pypi packages, GitHub repos, and web apps via browser — AND the strategic layer on top, transforming raw teardowns into actionable intelligence (Yash Poojary's methodology). It is the single canonical teardown skill (/teardown, /re-learn).

REQUIRED SUB-SKILL: app-teardown

Quick Start

/re-learn [AppName]

The 5 Strategic Questions

After running /teardown [AppName] macos, ask these questions — they're the core value:

1. Build vs. Buy? — Which parts are custom code vs. third-party packages? Reveals where they invested effort.
2. What did they prioritize? — Where's the complexity budget? What's native vs. web vs. off-the-shelf?
3. What's the 80/20? — Which 20% of tech choices deliver 80% of value? (Spotify: web everywhere except audio)
4. What packages can I adopt? — Solved problems I'd otherwise build. Finding the right package = 3 days → 3 hours.
5. What scope does this reveal? — Permissions, APIs, storage patterns. Define realistic scope before building.

The Workflow

1. Target Selection

Pick apps by feature, not category. Building audio? Tear down Spotify. Building auto-update? Tear down any app using Sparkle.framework. The target doesn't need to be a competitor.

2. Run Technical Teardown

/teardown [AppName] macos

3. Apply the 5 Questions

Transform raw output into strategic intelligence. Save to your project:

./teardowns/[app-name]-macos.md

See references/templates.md for report format.

4. Reference During Builds

Point Claude at your teardown library when building:

Before implementing [feature], check ./teardowns/spotify-macos.md
for packages and patterns. Apply the same approach if relevant.

Kevin Chen Prompt Template

For deep analysis, feed the Rewind teardown blog as methodology context — the LLM learns the method and applies it systematically. See references/kevin-chen-method.md.

Anti-Patterns

• Don't scan and move on. Value is in the 5 questions, not raw data.
• Don't only tear down competitors. Any app with your needed feature is valid.
• Don't rebuild solved problems. If a $100B company uses a package, you should too.

Integration