reproduce-my-buglisted

Turns a vague bug report into a minimal, runnable reproduction BEFORE any fix is attempted: sweeps evidence (logs, stack traces, git history around first-seen, DB state), ranks hypotheses by evidence, builds the smallest failing automated test (or repro script) that demonstrates the bug on demand, minimizes it until every remaining step is load-bearing, handles intermittent/flaky bugs by forcing determinism and documenting the reproduction rate, and delivers a repro dossier that hands the fixer a ready-made regression test. Never fixes — reproduces. Use when the user reports a bug, says something breaks sometimes or only in production, asks to investigate, debug, or find the root cause of an issue, or mentions reproduce-my-bug or /reproduce-my-bug.
silkyland/reproduce-my-bug · ★ 0 · Code & Development · score 75

Install: claude install-skill silkyland/reproduce-my-bug

# Reproduce My Bug The most expensive words in debugging are "I think I fixed it." A fix without a reproduction is a guess with a commit message — nobody can prove it worked, and nothing stops the bug from coming back. This skill does the half everyone skips: it turns "it breaks sometimes" into a **failing test you can run on demand** — which makes the eventual fix provable and gives the repo a permanent regression guard for free. ## The Prime Directive (family rule) > **No fix without a failing reproduction.** This skill never patches the > bug — it proves the bug. If the bug "disappears" during investigation, > that is a finding (flaky, environment-dependent, heisenbug), not a > resolution. Every claim in the dossier carries evidence: `file:line`, > a log excerpt, a command output, or an explicit `UNVERIFIED` tag. ## Hard rules 1. **Read-only on app code.** The only writes are the repro artifacts (a test file, a repro script, seed data) in clearly marked locations. 2. **Never investigate against production.** Reproduce on local/dev with seeded data (the seed-ah skill is the companion for this). Production supplies evidence (logs, traces) — never the test bench. 3. **One variable at a time.** Change one thing per attempt and record the outcome — including failures to reproduce; an eliminated hypothesis is progress, and unrecorded attempts get repeated. 4. **The repro must fail.** Green is not a repro. The dossier includes the exact command and the exac