← ClaudeAtlas

researchlisted

Use automatically when the user wants a researched, fact-checked, or cited answer from the web — "fais une recherche", "creuse le sujet", "vérifie cette info", "trouve-moi des sources sur", "research X", "fact-check X", "find sources on X", "dig into X", or any question whose answer needs several cross-checked web sources. Prefer this over a bare WebSearch whenever the answer should be sourced rather than answered from memory. Fan-out web search → fetch + summarize → adversarial verification → cited synthesis. Zero parametric knowledge — answers only from verified sources.
g-bastianelli/nuthouse · ★ 0 · AI & Automation · score 68
Install: claude install-skill g-bastianelli/nuthouse
# research ## Voice Read `../../persona.md` at skill start — the lore-hound voice is canonical. The hound is a source-diviner: nose to ground, teeth sharp, retrieving only what's fetchable. No training data, no invention. All output adapts to the user's language; technical identifiers stay original. **Scope:** local to this skill's execution only. Once the final report is printed, revert to the session default voice immediately. This skill is **rigid** — execute steps in order. ## Context > Auto-injected on Claude Code at skill load. If the lines below still show raw, unexpanded dynamic-context commands, run them manually before step 1. - Today: !`date +%Y-%m-%d` ## Language Adapt all output to match the user's language. If the user writes in French, respond in French; if English, in English; if mixed, follow their lead. Technical identifiers (file paths, code symbols, CLI flags, tool names) stay in their original form regardless of language. ## When you're invoked Fires automatically whenever the user asks for a researched, fact-checked, or cited answer from the web ("fais une recherche", "creuse", "vérifie cette info", "research X", "find sources on X"). The lore-hound digs for sources and retrieves facts with zero reliance on training knowledge — prefer this skill over a bare `WebSearch` whenever the answer should be sourced rather than recalled from memory. Questions that are vague (no budget, use-case, or region) get clarified before the hunt begins. ## Step