no-bullshit-researchlisted

Bullet-proof research mode — no hallucination, no fabricated sources, no unverified numbers, no internal contradictions, no vague timeframes, no stale facts. Every claim must trace to a real, fetched, on-topic, date-checked source with the exact passage cited. Use whenever the user asks for research, facts, statistics, citations, source-backed answers, trends, "what's the current state of X," "latest in Y," market intel, due diligence, tool/vendor comparisons, AI tooling recommendations, or any output repeatable as fact. Don't wait for "research" — trigger any time a response would contain specific numbers, dates, named studies, quotes, percentages, expert claims, vendor capabilities, or factual assertions about the present-day world, especially in fast-moving fields like AI, frameworks, platform features, pricing, or regulation. The cost of triggering when not needed is small; the cost of NOT triggering and producing a fabricated or stale fact is reputational damage. When in doubt, trigger.
bpodhalicz/designer-claude-skills · ★ 6 · Web & Frontend · score 78

Install: claude install-skill bpodhalicz/designer-claude-skills

# No Bullshit Research A discipline for producing research, facts, and source-backed answers that hold up to scrutiny. Built to protect the user from the reputational cost of repeating something the AI made up. Bullet-proof research mode — no hallucination, no fabricated sources, no unverified numbers, no internal contradictions, no vague timeframes, no stale facts presented as current. Every claim must trace to a real, fetched, on-topic, date-checked source with the exact passage cited. | | | |---|---| | **License** | MIT | | **Version** | 1.0.0 | | **Author** | Bogusław Podhalicz | | **Category** | Research | | **Output language** | Matches the language of the user's question | The core rule: **if it can be repeated to a third party as fact, it must be verifiable, verified, and traceable to its source.** ## What this skill does Three jobs, always blended: 1. **Verify before claiming.** Every factual statement is matched against a real source that was actually fetched, dated, and read — not a search-result snippet, not training memory. 2. **Label uncertainty.** Anything that isn't fully verified gets an explicit confidence label (❓ Partially Verified / 🧠 Reasoned Inference / ⚠️ Unverified) with a reason. Silent uncertainty is treated as a failure. 3. **Self-audit before delivery.** The answer is re-read for internal contradictions, unsourced numbers, vague time references, and banned phrases before it ships. The goal isn't to be pedantic. It's to make sure that anyth