do-your-researchlisted

Re-anchor research and no-assumptions discipline mid-session, then self-audit and correct the current work. Use when: 'do your research', 'you're guessing', 'cite that', 'stop assuming', 'evidence, not vibes', 'you skipped verification', 'that's training-data recall', 'research this properly', 'fact-check', 'fact check this', 'make sure that's right', or at conversation start to set the posture. For a heavy verification fan-out — a typed full inventory of the session's claims verified at a configurable depth — use the sibling do-your-research-deep.
melodic-software/claude-code-plugins · ★ 13 · AI & Automation · score 73

Install: claude install-skill melodic-software/claude-code-plugins

# Do your research A drift corrector for research discipline. The method — re-anchor, audit the work in flight, correct forward, report, and the tone that firing this is not an accusation — lives in [`${CLAUDE_PLUGIN_ROOT}/context/re-anchor-audit-correct.md`](../../context/re-anchor-audit-correct.md). Read it; this file adds only what is specific to research discipline. ## The discipline this re-anchors Research and verification before assertion. Resolve its source of truth per the method doc's ladder: if the consuming project states a research/verification discipline in its own `CLAUDE.md` or `.claude/rules/`, re-anchor THAT. Otherwise re-anchor this portable baseline: - **Assert nothing you cannot point to a source for.** A claim labelled "known", "obvious", or "from memory" is unverified until a fetched source or the live environment backs it. - **Verify every concrete specific.** A path, filename, default, flag, signature, or any "standard/conventional X" is a claim — check it against an authoritative source or the actual environment before stating it as fact, most critically right before the user acts on it. - **Frame the problem before reaching for a solution.** Name what is actually being solved; do not let the first solution shape decide it. - **Never act on ambiguity.** Surface the unknown and resolve it rather than assuming a value. - **Training-data recall is a starting point, not an answer.** Treat it as unverified until confirmed from a curren