← ClaudeAtlas

reverse-engineer-testslisted

Reverse engineer any test or exam from its real past papers into evidence-backed patterns — SAT, ACT, AP, GRE, GMAT, LSAT, state exams, school finals, mock papers, certification and licensing exams, any multiple-choice or short-answer set. Use whenever the user wants to crack a test, decode question patterns, find recurring traps or answer-choice tells, check whether a test-taking trick really works ("is the longest answer usually right?"), learn where the marks and the hard questions are, analyze an official question bank, build practice questions like the real ones, or make a strategy cheatsheet — even if they never say "reverse engineer". Input is PDFs (scanned ones too, via OCR) or pasted text. Every claim comes with counts, cited question ids and a held-out check of what it is worth in marks. This is document and pattern analysis; it is NOT for reverse engineering software, binaries, apps or APKs.
sub7an/reverse-engineer-tests · ★ 0 · Testing & QA · score 75
Install: claude install-skill sub7an/reverse-engineer-tests
# Reverse Engineer Any Test (RET) A test paper leaks its own construction. Every question is built to a template: one tested skill, a planted trap, and wrong choices picked to catch predictable mistakes. Recover the templates from real past papers, count them, and check each claim against papers it was not learned from. The skill's value is honesty. Most test-prep "tricks" fail when counted, and a student is better served by "this trick is a myth, here are the numbers" than by a confident rule that costs marks. Report busted myths as prominently as real signals. ## Two rules that hold everywhere 1. **Evidence, not vibes.** A pattern is real only when seen in 2+ questions with cited question ids (qids). One occurrence is an anecdote. Never estimate a frequency; the scripts count. Keep coverage separate from completeness: a pattern absent from the papers analyzed is not proven absent from the test. `references/evidence-model.md` defines the record format, unknowns and the mandatory footer; read it before Phase 2. 2. **No signal without its held-out value.** A p-value says a pattern exists; it does not say it earns marks. Phase 5 prices every answer-choice signal on papers it never saw. If that gain's interval includes 0, say "not established". ## Pick the lane first Run only the phases the request needs. | The user wants | Run | |---|---| | "Crack this test" with whole papers | Phases 1–5, then 7–8 if asked | | "Which topics / patterns matter" | P