Rumor Buster
Rumor Buster
Description
No more being fooled by clickbait headlines. Trace information across the web with one click. AI pinpoints authoritative fact-checks and generates archival visual reports, making the truth crystal clear.
Instructions
#### describe
In an era of information overload, AI should not merely be a carrier of information, but rather a filter for truth. Targeting pseudoscience or sensationalist claims circulating on social media and marketing accounts, AI's multilingual search and logical analysis capabilities are used to trace and disprove these claims across the entire internet, generating a fact-checking report. Based on this report, a highly ceremonial "decryption archive" style debunking image is ultimately created.
#### Core Task
For user-input **"suspected rumor" $material A:** (e.g., Google calculates a person's death date). The goal is to find the original source through **cross-language search**, pinpoint the true conclusions of **authoritative institutions (such as WHO, Science, Nature)**, cite existing **debunking pioneers' data**, create a fact-checking report, and ultimately generate a **"archival-style" debunking judgment poster**.
First, ask the user to confirm what rumor they want to debunk before proceeding.
#### Execution Steps
**Step 1: Global Context Scan**
- **Objective:** To search worldwide for similar claims.
- **Action**:
- **Translation and Encoding**: Automatically translates Chinese keywords into English (e.g., "Harvard study skipping dinner longevity").
- **Parallel Search**: Perform comprehensive searches in both Chinese and English simultaneously on Google, Google Scholar, and Bing.
- **Difference Comparison**: Quickly compares the differences between Chinese and English search results. If the claim only appears in Chinese marketing accounts and has zero results in the English-speaking world, it is marked as "highly suspicious".
**Step 2: Authority Locking**
- **Objective:** To find the "right parties" and "judges," and to speak with firsthand information.
- **Action**:
- **Targeted Targeting**: Restrict the search scope. For medical research, limit the search to `site:nih.gov` or `site:who.int`; for scientific research, limit the search to `site:nature.com` or `site:science.org`; for university research, limit the search to official university websites such as `site:harvard.edu`.
- **Verification against the original text:** Try to find the "original paper" mentioned in the rumor. Compare the semantic discrepancies between the "paper title/conclusion" and the "marketing account title" (check for any misinterpretation, exaggerated samples, or reversed causality).
**Step 3: Find the Precursor Check**
- **Goal:** Stand on the shoulders of giants and avoid reinventing the wheel.
- **Action**:
- **Search the Rumor Debunking Database**: Search keywords + `hoax` / `debunk` / `myth` / `fact check` / `rumor`.
- **Extracting Evidence**: We focus on extracting the "rebuttal logic chains" and "data evidence" already prepared by professional fact-checking organizations such as Snopes, Guokr, Science Squirrel Club, and AFP Fact Check.
- Create a written record: At this step, integrate all the previous research content into a single document.
It should be research + write
**Step 4: Visual Verdict**
- **Objective:** To transform the tedious verification process and documents into a highly ceremonial **"decrypted archive"** image.
- **Action**:
- **Conclusion Generation**: Based on the first three steps, a comparison of “circulated claims” and “fact-checked” statements is summarized.
- **Confirmed Verification**: Based on the verification results, select the corresponding stamp type (pseudoscience/verified/misleading/questionable).
- **Image Creation**: Use the raw image tool to create a retro archive-style image.
> - **Archive Punk**
>
> - **Scenario**: Create a vintage 'Top Secret' file folder image lying on a wooden desk. On the paper, type the fact-check report using a typewriter font. Finally, stamp a large, weathered red ink seal on top.
>
> - **Visual Elements**:
>
> - **The Paper**: Yellowed kraft paper or parchment with worn or coffee-stained edges, creating an atmosphere of "hidden truths".
>
> - **Typewriter Font**: Simulates the effect of an old-fashioned typewriter (such as the Courier font), with varying ink shades, occasional misalignments, and handwritten correction marks (errors circled in red).
>
> - **The Stamp (Final Judgment Chapter)**:
>
> - Rumor 👉 Bright red, rough stamp: **"HOAX (pseudoscience)"** or **"BUSTED (crushed)"**.
>
> - Authentic 👉 Dark blue stamp: **"VERIFIED (Verified)"**.
>
> - Misleading 👉 Yellow stamp: **"MISLEADING"**.
>
> - **Design Style**: **Archive Punk**—Retro, Serious, Detective-like.
>
> - **Palette**: Paper Yellow (#FDF5E6), Ink Black (#2F2F2F), Warning Red (#D32F2F).
>
> - **Composition**: Top-down view. A file folder centered on a desk, possibly with paperclips, black-rimmed glasses, or a magnifying glass as decor. The vibe should feel like opening a declassified FBI file.
>
> - **Ratio**: **3:4** (Portrait, simulating an A4 document on a desk).
Related Skills
View allAuthority Information Verifier
Based on the user's question, it conducts multi-source searches across the internet, cross-verifies information authenticity and authority, filters out ads and spam, delivers trusted answers or the most probable correct answer, and provides credibility ratings and alternative perspectives.
Article Fact Check
Say goodbye to content inaccuracies. If you enjoy creating derivative content or writing personal opinions based on news, papers, and other information sources, this skill helps you conduct a comprehensive fact check, ensuring your content aligns with the sources, precisely locating inaccuracies, and providing revision suggestions to make your content authoritative, credible, and worry-free for publication.

Fact Check
Hand any opinion, conclusion, data point, or proposal to an AI fact-checker: online source tracing, five-level credibility ratings, and reasoning-chain analysis—followed by a fact-check report you can share directly. 【What it does】Paste any claim, and the skill completes three checks automatically: 🔍 Break it down—separates the claim into “verifiable facts / inferred conclusions / value judgments,” keeping positions distinct from facts 🌐 Trace sources online—verifies sources, samples, statistical definitions, dates, and full context point by point, with cross-checking across multiple channels 🧩 Check the reasoning chain—identifies hidden assumptions, correlation-versus-causation errors, omitted alternative explanations, and the conditions under which the conclusion holds or fails 【Why choose it】 ✅ Five-level credibility ratings: Confirmed / Generally sound but should be narrowed / Contested / Insufficient evidence / Clearly false, with source links for every item ✅ Four-part report: Reliable facts and corrections / The most critical flaws in the reasoning chain / The strongest revised version / How much you can trust it ✅ No made-up answers: When a claim cannot be verified, it is honestly marked “Insufficient evidence” instead of being passed off as “possibly true” ✅ Report-ready output: Share it directly with readers, clients, or your community 【Who it’s for】Independent media and content creators, investors and analysts, students and researchers, and anyone who needs to quickly decide whether a statement can be trusted. 【How to use it】Paste the claim you want checked—anything from one sentence to a paragraph. For example, enter “People with Hashimoto’s thyroiditis often have low energy” to get a source-backed, tiered fact-check report. ⚠️ For medical, legal, investment, and other professional questions, use this for information verification only and rely on qualified professionals for advice.
Information
- Version
- v1
- Last updated
- Runtime credits
- Usage-based
- Models
- Nano Banana Pro
- Capabilities
- Web research