| name | source-finder |
| description | Finds credible primary or authoritative sources that verify, challenge, or strengthen the claims in selected or visible text, weighing each for authority, recency, and whether it actually supports the claim. Use when the user says "find a source", "back this up", "is there evidence for this", "cite this", "find references", or asks for citations, primary sources, or proof for a statement. |
| author | surfmind |
| metadata | {"icon":"TextSearch","tags":["research"]} |
Source Finder
Find credible primary or authoritative sources that verify, challenge, or strengthen the claims in the selected or visible text. Never invent sources, URLs, titles, authors, or dates, present a summary or commentary as a primary source, or inflate a weak source into proof.
- Identify the specific claims or questions that need stronger sourcing, and note the numbers, dates, names, or quotes a source would have to match.
- Prefer primary, official, standards-body, academic, legal, regulatory, or original-data sources over summaries and commentary. Use web search or any browser/MCP tool available, and treat each result as evidence to inspect rather than automatic truth.
- Weigh each candidate for authority, recency, specificity, and whether it actually supports the exact claim, not just the general topic. Before citing a source, confirm it exists and says what you think — open the link or search the exact title or DOI — rather than trusting a recalled reference.
- Flag claims that need a source but can't be verified from the available context, and say what kind of source would settle them.
Report each claim with its best source candidates, why each one is stronger, what it actually supports, and any caveats or gaps. Preserve exact names, numbers, links, dates, and currencies, and don't cite a source unless it directly supports the claim.
Example
Source text: "Intermittent fasting boosts metabolism by 14%."
Claim: Intermittent fasting raises metabolic rate by 14%.
Best source candidates: A peer-reviewed metabolic-ward study in a journal such as The American Journal of Clinical Nutrition, or a systematic review of fasting and resting energy expenditure.
Why each is stronger: Both are primary or pooled measured data, not a press summary; the original study reports the actual measurement and the conditions behind a figure like "14%."
What it supports: Whether a metabolic change of that size was measured, in whom, and over what window — the specific 14% figure, not just "fasting affects metabolism."
Caveats or gaps: The visible text gives no citation, sample, or timeframe, so the 14% can't be traced yet. A single small trial wouldn't settle it; a systematic review would carry more weight.
