fact-checker

# Fact-Check: Multimodal News Verification Skill

## When to Use
- User asks to verify a news article, claim, tweet, or social media post
- User asks "is this true?" about any statement
- User mentions fake news, misinformation, or disinformation
- User provides a URL and asks to check its truthfulness
- User asks to verify an image (is it real, AI-generated, photoshopped, manipulated, out-of-context)
- User asks to verify a video (is it deepfake, manipulated, real footage)
- User shares an image or video and asks if it is authentic
- User asks to fact-check content in any language

---

## Stage 0: Input Parsing

### 1. Detect input modality

Determine what the user provided. Check in this order:

- **Image file**: The user attached or provided an image (JPEG, PNG, WebP, GIF, etc.). Set `modality = image`.
- **Video file**: The user attached or provided a video (MP4, MOV, AVI, WebM, etc.). Set `modality = video`.
- **URL**: The input starts with `http://` or `https://`.
  - If the URL points directly to an image file (ends in `.jpg`, `.png`, `.webp`, etc.) → download it and set `modality = image`.
  - If the URL points directly to a video file (ends in `.mp4`, `.mov`, `.webm`, etc.) → download it and set `modality = video`.
  - Otherwise → use WebFetch to retrieve the page content. Extract only the main article body. Set `modality = text`.
- **Plain text**: None of the above. Set `modality = text`.

If the user provides **both an image/video AND a text claim** (e.g., "Is this photo from the 2024 earthquake?"), record both. Both branches will run and results will be combined in the report.

### 2. Detect language
Identify the language the user is writing in. This determines the report language and search query language.

### 3. Handle long text input (over 500 words / 1000 Chinese characters)
Only applies when `modality = text`.
- Ask the user: "This article is quite long. Would you like me to fact-check the entire article, or is there a specific claim you'd like me...

# fact-checker ✅

**Open-source multimodal fact-checking for OpenClaw — verify news, claims, images, and videos in any language. Zero config.**

## Install

```bash
claw install fact-checker
```

That's it. No Python, no pip install, no API keys required beyond what you already have in OpenClaw.

## What it does

- Fact-check news articles, social media posts, and claims
- Verify images — detect AI-generated, manipulated, or out-of-context photos
- Verify videos — extract keyframes, transcribe audio, detect deepfakes
- Detect misinformation and disinformation in any language
- Cross-reference claims against 100+ global fact-checking organizations
- Decompose articles into atomic claims and verify each independently
- Search the web for evidence and cite sources for every verdict
- Extract and analyze image/video metadata (EXIF) and content credentials (C2PA)
- Output structured verdicts with confidence scores
  - **Text:** TRUE / FALSE / PARTIALLY_TRUE / MISLEADING / UNVERIFIED
  - **Image/Video:** AUTHENTIC / MANIPULATED / AI_GENERATED / OUT_OF_CONTEXT / DEEPFAKE_SUSPECTED / UNVERIFIED

## Usage

Just ask your agent:

```
Fact-check this: "NASA announced that Earth will stop rotating by 2030."
```

```
Fact-check this news: "Elon Musk announced Tesla will stop producing EVs entirely by 2027."
```

```
Is this true? https://example.com/suspicious-article
```

```
Is this image real or AI-generated? [attach image]
```

```
Is this video a deepfake? [attach video]
```

## How It Works

The skill auto-detects input modality (text, image, or video) and routes to the appropriate pipeline:

**Text Pipeline** (4 stages):
1. **Existing Fact-Check Lookup** — Searches 100+ global fact-checkers (Snopes, PolitiFact, AFP, etc.)
2. **Claim Extraction & Triage** — Decomposes text into atomic claims, filters out opinions and vague statements
3. **Deep Verification** — Searches the web for evidence, analyzes sources, assigns verdicts
4. **Report Generation** — Structured report wit...