\r \r

Facticity.AI Complete Integration\r

\r A comprehensive skill for interacting with the Facticity.AI API. Supports fact-checking claims, extracting claims from text/video, transcribing links, checking link reliability using MediaBias data, checking API credits, and monitoring async task status.\r \r

API Base URL\r

\r Base URL: https://api.facticity.ai\r \r All API endpoints use this base URL. References to {BASE_URL}.\r \r

Behavior\r

\r First, check if FACTICITY_API_KEY is set and not empty. If it is missing or empty, return this onboarding message:\r \r

⚠️ API Key Not Configured\r
\r
To use this skill, you need to set up your Facticity.AI API key:\r
\r
1. Visit https://app.facticity.ai/api to get your API key\r
2. Set the key as an environment variable:\r
   export FACTICITY_API_KEY=your_api_key_here\r
   \r
   Or add it to your OpenClaw config (~/.openclaw/openclaw.json):\r
   {\r
     "skills": {\r
       "entries": {\r
         "facticity-ai": {\r
           "enabled": true,\r
           "apiKey": "your_api_key_here"\r
         }\r
       }\r
     }\r
   }\r
\r
3. Restart OpenClaw after configuration\r
\r
Get your API key at: https://app.facticity.ai/api\r
```\r
\r
**If the API key is present, determine the operation based on the command and proceed:**\r
\r
### 1. Fact-Check (`/fact-check`)\r
\r
When the command starts with `/fact-check` or the input is a claim to fact-check:\r
\r
**Endpoint:** `POST {BASE_URL}/fact-check`\r
\r
**Headers:**\r
- `X-API-KEY: ${FACTICITY_API_KEY}`\r
- `Content-Type: application/json`\r
\r
**Body:**\r
```json\r
{\r
  "query": "\x3Craw command input (remove /fact-check prefix if present)>",\r
  "timeout": 60,\r
  "mode": "sync"\r
}\r
```\r
\r
Return the JSON response verbatim. The response includes:\r
- `Classification`: "True" or "False"\r
- `overall_assessment`: Detailed assessment text\r
- `evidence`: Array of evidence sources\r
- `sources`: Detailed source assessments\r
- `bias`: Bias metrics (if available)\r
- `task_id`: Task ID for async tracking\r
\r
**Usage:**\r
```\r
/fact-check "Vaccines contain microchips"\r
/fact-check "The unemployment rate dropped in 2023"\r
```\r
\r
**Async Mode:** For long-running fact-checks, set `mode: "async"` in the request body. The API will return a `task_id` that can be checked with `/check-task-status`.\r
\r
### 2. Extract Claims (`/extract-claim`)\r
\r
When the command starts with `/extract-claim` or the input is a URL or text to extract claims from:\r
\r
**Endpoint:** `POST {BASE_URL}/extract-claim`\r
\r
**Headers:**\r
- `X-API-KEY: ${FACTICITY_API_KEY}`\r
- `Content-Type: application/json`\r
\r
**Body:**\r
```json\r
{\r
  "input": "\x3Craw command input (remove /extract-claim prefix if present)>",\r
  "content_type": "text",\r
  "timestamp": false,\r
  "audio_transcript_enabled": false,\r
  "language_code": "en"\r
}\r
```\r
\r
**Note:** For video URLs (YouTube, TikTok, Instagram), the API will auto-detect and transcribe. If you need transcription explicitly enabled, set `audio_transcript_enabled: true` in the request body.\r
\r
Return the JSON response verbatim.\r
\r
**Usage:**\r
```\r
/extract-claim "The Earth is flat and NASA is lying about it"\r
/extract-claim https://youtube.com/watch?v=abc123\r
/extract-claim https://tiktok.com/@user/video/123\r
/extract-claim https://instagram.com/p/abc123\r
```\r
\r
**Supported Content Types:**\r
- **Text**: Direct text input\r
- **Video URLs**: YouTube, TikTok, Instagram (auto-transcribes)\r
- **Language**: Set `language_code` for non-English content (default: "en")\r
\r
**Response Format:**\r
- `status`: "ok" on success\r
- `transcript`: Transcribed content (for video URLs)\r
- `title`: Video/article title (if available)\r
- `description`: Content description (if available)\r
- `claims`: Array of extracted claim strings\r
- `overall_assessment`: Summary of extraction\r
\r
### 3. Get Credits (`/get-credits`)\r
\r
When the command is `/get-credits` or user wants to check API credits:\r
\r
**Endpoint:** `GET {BASE_URL}/get-credits`\r
\r
**Headers:**\r
- `X-API-KEY: ${FACTICITY_API_KEY}`\r
\r
No request body required.\r
\r
Return the JSON response verbatim. The response includes:\r
- `email`: User email associated with the API key\r
- `api_key`: The API key (masked)\r
- `credits_left`: Number of credits remaining\r
- `duration_seconds`: Duration period (typically 3600 seconds)\r
\r
**Usage:**\r
```\r
/get-credits\r
```\r
\r
**Response Format:**\r
```json\r
{\r
  "email": "[email protected]",\r
  "api_key": "your_api_key_here",\r
  "credits_left": 1482,\r
  "duration_seconds": 3600\r
}\r
```\r
\r
### 4. Check Task Status (`/check-task-status`)\r
\r
When the command starts with `/check-task-status` or the input is a task ID:\r
\r
**Endpoint:** `GET {BASE_URL}/check-task-status?task_id=\x3Ctask_id>`\r
\r
**Headers:**\r
- `X-API-KEY: ${FACTICITY_API_KEY}`\r
\r
The raw command input should be the task_id from a previous async fact-check request (remove `/check-task-status` prefix if present).\r
\r
**Query Parameter:**\r
- `task_id`: The unique ID of the task to check (from the raw command input)\r
\r
Return the JSON response verbatim.\r
\r
**Usage:**\r
```\r
/check-task-status 1234567890abcdef\r
```\r
\r
Or with the task_id from a previous async fact-check:\r
```\r
/fact-check "Long claim..." --mode async\r
# Returns task_id: abc123\r
/check-task-status abc123\r
```\r
\r
**Response Format:**\r
\r
For completed tasks:\r
```json\r
{\r
  "status": "Completed",\r
  "input_query": "Original Input query",\r
  "classification": "False",\r
  "overall_assessment": "This claim is inaccurate.",\r
  "evidence_sources": ["Source 1", "Source 2"],\r
  "disambiguation": "Clarifies the context...",\r
  "detailed_source_reports": ["Detailed source report 1", "Detailed source report 2"],\r
  "task_id": "1234567...",\r
  "bias_quality_metrics": [\r
    {\r
      "source": "https://www.politico.com",\r
      "bias": -5.238666666666666,\r
      "quality": 46.45\r
    }\r
  ]\r
}\r
```\r
\r
For in-progress tasks, returns current status and progress information.\r
\r
### 5. Transcribe Link (`/transcribe-link`)\r
\r
When the command starts with `/transcribe-link` or the input is a URL to transcribe:\r
\r
**Endpoint:** `POST {BASE_URL}/transcribe-link`\r
\r
**Headers:**\r
- `X-API-KEY: ${FACTICITY_API_KEY}`\r
- `Content-Type: application/json`\r
\r
**Body:**\r
```json\r
{\r
  "url": "\x3Craw command input (remove /transcribe-link prefix if present)>"\r
}\r
```\r
\r
The raw command input should be the URL to transcribe (remove `/transcribe-link` prefix if present).\r
\r
Return the JSON response verbatim.\r
\r
**Usage:**\r
```\r
/transcribe-link https://youtube.com/watch?v=abc123\r
/transcribe-link https://tiktok.com/@user/video/123\r
/transcribe-link https://instagram.com/p/abc123\r
```\r
\r
**Response Format:**\r
- `status`: "ok" on success\r
- `transcript`: Transcribed content from the link\r
- `title`: Video/article title (if available)\r
- `description`: Content description (if available)\r
- `duration`: Duration of the content (if available)\r
\r
### 6. Check Link Reliability (`/link-reliability/check`)\r
\r
When the command starts with `/link-reliability/check` or `/check-link-reliability` or the input is a URL to check for source reliability:\r
\r
**Endpoint:** `POST {BASE_URL}/link-reliability/check`\r
\r
**Headers:**\r
- `X-API-KEY: ${FACTICITY_API_KEY}`\r
- `Content-Type: application/json`\r
\r
**Body:**\r
```json\r
{\r
  "url": "\x3Craw command input (remove /link-reliability/check or /check-link-reliability prefix if present)>"\r
}\r
```\r
\r
The raw command input should be the URL to check (remove `/link-reliability/check` or `/check-link-reliability` prefix if present).\r
\r
Return the JSON response verbatim. The response includes:\r
- `url`: The processed URL\r
- `bias`: Bias score (-42 to +42)\r
- `quality`: Quality score (0 to 64)\r
- `bias_label`: Human-readable bias category\r
- `quality_label`: Human-readable quality category\r
- `found`: Whether the URL was found in MediaBias database\r
\r
**Usage:**\r
```\r
/link-reliability/check https://www.example.com/article\r
/check-link-reliability https://www.bbc.com/news\r
/link-reliability/check https://www.politico.com/story\r
```\r
\r
**Response Format:**\r
```json\r
{\r
  "url": "https://www.example.com/article",\r
  "bias": -5.24,\r
  "quality": 46.45,\r
  "bias_label": "Left-Center Bias",\r
  "quality_label": "High Quality",\r
  "found": true\r
}\r
```\r
\r
**Note:** If the URL is not found in the MediaBias database, `found` will be `false` and bias/quality scores may be null or default values.\r
\r
## Command Routing\r
\r
Determine which operation to perform based on the command prefix:\r
- `/fact-check` or input looks like a claim → Fact-Check endpoint\r
- `/extract-claim` or input is a URL → Extract Claims endpoint\r
- `/get-credits` → Get Credits endpoint\r
- `/check-task-status` or input is a task ID → Check Task Status endpoint\r
- `/transcribe-link` or input is a URL → Transcribe Link endpoint\r
- `/link-reliability/check` or `/check-link-reliability` or input is a URL → Check Link Reliability endpoint\r
\r
## API Token Usage\r
\r
- **Fact-Check**: Each request consumes 1 API token\r
- **Extract Claims**: Consumes 1 API token per 1 million characters processed\r
- **Get Credits**: Free, does not consume tokens\r
- **Check Task Status**: Free, does not consume tokens\r
- **Transcribe Link**: Consumes 1 API token per transcription request\r
- **Check Link Reliability**: Consumes 1 API token per request\r
\r
Monitor usage with `/get-credits`.\r
\r
## Configuration\r
\r
Set `FACTICITY_API_KEY` in your OpenClaw config under `skills.entries.facticity-ai.apiKey` or as an environment variable.\r
\r
**Example config:**\r
```json\r
{\r
  "skills": {\r
    "entries": {\r
      "facticity-ai": {\r
        "enabled": true,\r
        "apiKey": "YOUR_API_KEY_HERE"\r
      }\r
    }\r
  }\r
}\r
```\r
\r
Or set as environment variable:\r
```bash\r
export FACTICITY_API_KEY=your_api_key_here\r
```\r