facticity-ai
Complete Facticity.AI integration - fact-check claims, extract claims from content, transcribe links, check link reliability, check credits, and monitor task status
- License 许可
- MIT
- 最近更新
- 2026-06-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- facticity-ai
- metadata
- { "openclaw": { "emoji": "🔍", "homepage": "https://app.facticity.ai", "requires": { "env": [ "FACTICITY_API_KEY" ] }, "primaryEnv": "FACTICITY_API_KEY" } }
- description
- Complete Facticity.AI integration - fact-check claims, extract claims from content, transcribe links, check link reliability, check credits, and monitor task status
- command-tool
- http.request
- user-invocable
- true
- command-arg-mode
- raw
- command-dispatch
- tool
03 SKILL.md 正文
Facticity.AI Complete Integration
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.
API Base URL
Base URL: https://api.facticity.ai
All API endpoints use this base URL. References to {BASE_URL}.
Behavior
First, check if FACTICITY_API_KEY is set and not empty. If it is missing or empty, return this onboarding message:
⚠️ API Key Not Configured
To use this skill, you need to set up your Facticity.AI API key:
1. Visit https://app.facticity.ai/api to get your API key
2. Set the key as an environment variable:
export FACTICITY_API_KEY=your_api_key_here
Or add it to your OpenClaw config (~/.openclaw/openclaw.json):
{
"skills": {
"entries": {
"facticity-ai": {
"enabled": true,
"apiKey": "your_api_key_here"
}
}
}
}
3. Restart OpenClaw after configuration
Get your API key at: https://app.facticity.ai/api
If the API key is present, determine the operation based on the command and proceed:
1. Fact-Check (/fact-check)
When the command starts with /fact-check or the input is a claim to fact-check:
Endpoint: POST {BASE_URL}/fact-check
Headers:
X-API-KEY: ${FACTICITY_API_KEY}Content-Type: application/json
Body:
{
"query": "<raw command input (remove /fact-check prefix if present)>",
"timeout": 60,
"mode": "sync"
}
Return the JSON response verbatim. The response includes:
Classification: "True" or "False"overall_assessment: Detailed assessment textevidence: Array of evidence sourcessources: Detailed source assessmentsbias: Bias metrics (if available)task_id: Task ID for async tracking
Usage:
/fact-check "Vaccines contain microchips"
/fact-check "The unemployment rate dropped in 2023"
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.
2. Extract Claims (/extract-claim)
When the command starts with /extract-claim or the input is a URL or text to extract claims from:
Endpoint: POST {BASE_URL}/extract-claim
Headers:
X-API-KEY: ${FACTICITY_API_KEY}Content-Type: application/json
Body:
{
"input": "<raw command input (remove /extract-claim prefix if present)>",
"content_type": "text",
"timestamp": false,
"audio_transcript_enabled": false,
"language_code": "en"
}
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.
Return the JSON response verbatim.
Usage:
/extract-claim "The Earth is flat and NASA is lying about it"
/extract-claim https://youtube.com/watch?v=abc123
/extract-claim https://tiktok.com/@user/video/123
/extract-claim https://instagram.com/p/abc123
Supported Content Types:
- Text: Direct text input
- Video URLs: YouTube, TikTok, Instagram (auto-transcribes)
- Language: Set
language_codefor non-English content (default: "en")
Response Format:
status: "ok" on successtranscript: Transcribed content (for video URLs)title: Video/article title (if available)description: Content description (if available)claims: Array of extracted claim stringsoverall_assessment: Summary of extraction
3. Get Credits (/get-credits)
When the command is /get-credits or user wants to check API credits:
Endpoint: GET {BASE_URL}/get-credits
Headers:
X-API-KEY: ${FACTICITY_API_KEY}
No request body required.
Return the JSON response verbatim. The response includes:
email: User email associated with the API keyapi_key: The API key (masked)credits_left: Number of credits remainingduration_seconds: Duration period (typically 3600 seconds)
Usage:
/get-credits
Response Format:
{
"email": "user@example.com",
"api_key": "your_api_key_here",
"credits_left": 1482,
"duration_seconds": 3600
}
4. Check Task Status (/check-task-status)
When the command starts with /check-task-status or the input is a task ID:
Endpoint: GET {BASE_URL}/check-task-status?task_id=<task_id>
Headers:
X-API-KEY: ${FACTICITY_API_KEY}
The raw command input should be the task_id from a previous async fact-check request (remove /check-task-status prefix if present).
Query Parameter:
task_id: The unique ID of the task to check (from the raw command input)
Return the JSON response verbatim.
Usage:
/check-task-status 1234567890abcdef
Or with the task_id from a previous async fact-check:
/fact-check "Long claim..." --mode async
# Returns task_id: abc123
/check-task-status abc123
Response Format:
For completed tasks:
{
"status": "Completed",
"input_query": "Original Input query",
"classification": "False",
"overall_assessment": "This claim is inaccurate.",
"evidence_sources": ["Source 1", "Source 2"],
"disambiguation": "Clarifies the context...",
"detailed_source_reports": ["Detailed source report 1", "Detailed source report 2"],
"task_id": "1234567...",
"bias_quality_metrics": [
{
"source": "https://www.politico.com",
"bias": -5.238666666666666,
"quality": 46.45
}
]
}
For in-progress tasks, returns current status and progress information.
5. Transcribe Link (/transcribe-link)
When the command starts with /transcribe-link or the input is a URL to transcribe:
Endpoint: POST {BASE_URL}/transcribe-link
Headers:
X-API-KEY: ${FACTICITY_API_KEY}Content-Type: application/json
Body:
{
"url": "<raw command input (remove /transcribe-link prefix if present)>"
}
The raw command input should be the URL to transcribe (remove /transcribe-link prefix if present).
Return the JSON response verbatim.
Usage:
/transcribe-link https://youtube.com/watch?v=abc123
/transcribe-link https://tiktok.com/@user/video/123
/transcribe-link https://instagram.com/p/abc123
Response Format:
status: "ok" on successtranscript: Transcribed content from the linktitle: Video/article title (if available)description: Content description (if available)duration: Duration of the content (if available)
6. Check Link Reliability (/link-reliability/check)
When the command starts with /link-reliability/check or /check-link-reliability or the input is a URL to check for source reliability:
Endpoint: POST {BASE_URL}/link-reliability/check
Headers:
X-API-KEY: ${FACTICITY_API_KEY}Content-Type: application/json
Body:
{
"url": "<raw command input (remove /link-reliability/check or /check-link-reliability prefix if present)>"
}
The raw command input should be the URL to check (remove /link-reliability/check or /check-link-reliability prefix if present).
Return the JSON response verbatim. The response includes:
url: The processed URLbias: Bias score (-42 to +42)quality: Quality score (0 to 64)bias_label: Human-readable bias categoryquality_label: Human-readable quality categoryfound: Whether the URL was found in MediaBias database
Usage:
/link-reliability/check https://www.example.com/article
/check-link-reliability https://www.bbc.com/news
/link-reliability/check https://www.politico.com/story
Response Format:
{
"url": "https://www.example.com/article",
"bias": -5.24,
"quality": 46.45,
"bias_label": "Left-Center Bias",
"quality_label": "High Quality",
"found": true
}
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.
Command Routing
Determine which operation to perform based on the command prefix:
/fact-checkor input looks like a claim → Fact-Check endpoint/extract-claimor input is a URL → Extract Claims endpoint/get-credits→ Get Credits endpoint/check-task-statusor input is a task ID → Check Task Status endpoint/transcribe-linkor input is a URL → Transcribe Link endpoint/link-reliability/checkor/check-link-reliabilityor input is a URL → Check Link Reliability endpoint
API Token Usage
- Fact-Check: Each request consumes 1 API token
- Extract Claims: Consumes 1 API token per 1 million characters processed
- Get Credits: Free, does not consume tokens
- Check Task Status: Free, does not consume tokens
- Transcribe Link: Consumes 1 API token per transcription request
- Check Link Reliability: Consumes 1 API token per request
Monitor usage with /get-credits.
Configuration
Set FACTICITY_API_KEY in your OpenClaw config under skills.entries.facticity-ai.apiKey or as an environment variable.
Example config:
{
"skills": {
"entries": {
"facticity-ai": {
"enabled": true,
"apiKey": "YOUR_API_KEY_HERE"
}
}
}
}
Or set as environment variable:
export FACTICITY_API_KEY=your_api_key_here
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
ceaser
Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).
ceaser-send
Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
moldium
Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.