reverse-engineer-to-learn
Skill1 starsChanged 3 days agoMITView on GitHub
Studies how existing apps solve problems to inform new builds. Performs strategic teardowns for learning, scoping features, and finding packages. Reverse-engineers macOS app bundles, npm/pypi packages, GitHub repos, and web apps (via browser), then applies the strategic questions. Triggers — "teardown", "reverse engineer", "how does X work", "study this app/package".
1 other project uses a version of this.
Adopted by
Most recently taken up by
- LucasCooperBey/claude-skillsword for word, first seen Oct 20, 2026
Other versions1 project uses a version of this.
Word for word · 1
- LucasCooperBey/claude-skills★ 1100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository53 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/deep-recon/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- adversarial-researchSkill
- algorithmic-artSkill
- api-integrationSkill
- breakdownSkill
- c4-architectSkill
- canvas-designSkill
- coding-agentsSkill
- compound-engineeringSkill
- context-budgetSkill
- counterfactualSkill
- critiqueSkill
- d3js-visualizationSkill
- data-analyst-agentSkill
- database-migrationsSkill
- deep-reconSkill
- design-tasteSkill
- e2b-sandboxSkill
- ecosystem-auditSkill
- executing-plansSkill
- frontend-designSkill
- fullstack-agentSkill
- grillSkill
- kickoffSkill
- mcp-builderSkill
- model-migrationSkill
- naming-the-machineSkill
- full-output-enforcementSkill
- package-researchSkill
- pdf-generationSkill
- pp2pSkill
- pp3pSkill
- prompt-engineerSkill
- prompt-groundingSkill
- redesignSkill
- requesting-code-reviewSkill
- review-changesSkill
- scratchpadSkill
- shipSkill
- slack-gif-creatorSkill
- sprint-architectSkill
- techdebtSkill
- test-and-fixSkill
- threat-modelSkill
- verification-before-completionSkill
- visual-verdictSkill
- webapp-testingSkill
- web-asset-generatorSkill
- whatdidimissSkill
- wiki-writeSkill
- writing-plansSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
After running /teardown [AppName] macos, ask these questions — they're the core value:
- Distinctive: line 73
Don't rebuild solved problems: If a $100B company uses a package, you should too.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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:
- Build vs. Buy? — Which parts are custom code vs. third-party packages? Reveals where they invested effort.
- What did they prioritize? — Where's the complexity budget? What's native vs. web vs. off-the-shelf?
- What's the 80/20? — Which 20% of tech choices deliver 80% of value? (Spotify: web everywhere except audio)
- What packages can I adopt? — Solved problems I'd otherwise build. Finding the right package = 3 days → 3 hours.
- 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] macos3. Apply the 5 Questions
Transform raw output into strategic intelligence. Save to your project:
./teardowns/[app-name]-macos.mdSee 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
| Skill | Role |
app-teardown | Technical methods (plutil, otool, strings) |
deep-recon | Code Analyzer uses teardown library |
writing-plans | Teardowns inform scope |
Source
Inspired by Kevin Chen (https://kevinchen.co/blog/rewind-ai-app-teardown/). The skill also names Yash Poojary's methodology; that source was not located.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

