← ClaudeAtlas

product-teardownlisted

Analyze external products, websites, apps, APIs, documentation, and source repositories to extract evidence-backed, transferable, implementable product and engineering patterns rather than generic competitor summaries. Use when the user asks to teardown, reverse-engineer at a product/architecture level, benchmark, study, or learn from another product/repo; asks what workflows, UX mechanics, architecture, onboarding, monetization, developer experience, operations, reliability, or implementation ideas are worth adapting; asks "what can we borrow/learn/implement from X" or Polish equivalents such as "przeanalizuj produkt/repo", "wyciagnij wzorce", or "co warto wdrozyc". Also use for multi-product pattern synthesis and source-to-target adaptation. Do not use as the primary skill for ongoing competitor monitoring/delta analysis, broad competitor dossiers, external-facing comparison pages, or a roadmap of the user's own repo with no external/reference target.
MaciejZet/agent-skills · ★ 1 · AI & Automation · score 74
Install: claude install-skill MaciejZet/agent-skills
# Product Teardown v2 Turn external observation into a defensible implementation decision. The unit of work is a **transferable pattern**, not a feature list, screenshot inventory, technology list, or competitor profile. ## Core contract Preserve this chain for every material recommendation: `source evidence -> source observation -> mechanism hypothesis -> destination problem evidence -> transfer conditions -> adaptation option -> implementation path -> validation -> action` Never collapse the stages. - Seeing UI proves only visible behavior/state, not backend architecture, rationale, adoption, or outcome. - Seeing code proves implementation in the inspected version, not production use, customer value, or causal impact. - Seeing a successful company use a pattern does not prove the pattern caused success. - Seeing the same pattern across several products proves prevalence, not effectiveness. Use claim states consistently: - `OBSERVED` - directly supported by inspectable evidence. - `INFERRED` - interpretation derived from observed evidence. - `HYPOTHESIS` - proposed rationale, causal mechanism, expected effect, or transfer claim requiring validation. - `UNKNOWN` - material point not established by available evidence. Read `references/evidence-model.md` whenever building or judging the evidence ledger. ## Two independent axes ### Teardown shape Choose one: - `SOURCE_ONLY` - inspect a source and produce a pattern library. Never emit `ADOPT` without destination evid