What do I need to use Screenshot Teardown?

The screenshots; Your product and angle.

Is Screenshot Teardown free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Screenshot Teardown

Q: How do I know the Screenshot Teardown output is good?

The skill verifies itself against its own quality checks: Every observation cites its screenshot; every inference is labelled `[inference]`; Copy is quoted verbatim where it carries the point, not paraphrased; The friction count is actual (fields/steps visible), not vibes; The teardown states what the screenshots *cannot* show.

🔵 Stable🕐 updated 2026-10-06 ✅ 3.3/5 🔷 SkillSpec L3 pm-vision

Tear down a competitor's product from screenshots of its actual UI — onboarding, pricing page, core flows. Use when given screenshots of a rival's app or website and asked what they're doing, how their flow works, or what to learn/steal/avoid. Produces a UX-and-strategy teardown grounded in what is visibly on screen, with an inferences-vs-observations split. Requires image input. For a market-level teardown without screenshots use competitor-teardown.

▶ Run it free — no key needed 📝 Grade your existing draft 📱 Use as an app View SKILL.md ↗ What changed

🗣 Say this to your agent

“Tear down this competitor's onboarding from these screenshots.”“How does their flow work?”“What should we learn, steal or avoid from their pricing page?”“Here are screenshots of their app: what are they doing?”

What to give it

▸The screenshots — (up to ~5 per pass; more → ask which flow matters most). If none attached, ask — never tear down from memory of the product.

▸Your product and angle — (ask if missing): who's analysing, and for what decision (pricing? onboarding redesign? battlecard?)

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Every observation cites its screenshot; every inference is labelled `[inference]`

✓Copy is quoted verbatim where it carries the point, not paraphrased

✓The friction count is actual (fields/steps visible), not vibes

✓The teardown states what the screenshots *cannot* show

✓Recommendations name what to change when stealing a pattern — context transplants fail

⚠️ What it refuses to do

Do not analyse a product from training-data memory when screenshots are provided — the pixels are the source of truth, and the product has probably changed

Do not proceed without images — that's `competitor-teardown`'s job

Do not present inferences as facts — "they're struggling with churn" is a reading, not a screenshot

Do not sneer — "cluttered" is not analysis; name what the clutter costs and whom it serves

Do not extrapolate a whole strategy from one screen — say when the evidence is thin

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y -p pm-claude-skills pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="screenshot-teardown"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Screenshot Teardown is one of 1307 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog