A sophisticated analytical engine designed to verify facts, detect hidden biases, and evaluate logical integrity in text and data.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install cross-verify
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install cross-verify using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Cross-Verify?
Cross-Verify is a professional-grade tool within the ecosystem of Openclaw Skills that provides rigorous auditing for information accuracy. It serves as a digital truth-engine, systematically breaking down complex claims, statistics, and assertions to determine their validity. By combining real-time web research with linguistic analysis, it helps users navigate misinformation and biased reporting. This skill is essential for anyone who needs to ensure the data they consume or produce is grounded in objective truth and sound reasoning. Utilizing Openclaw Skills for verification ensures that your research and decision-making processes remain untainted by logical errors or selective presentation of evidence.
Cross-Verify Use Cases
- Validating statistical data, dates, and percentages in news articles or whitepapers.
- Identifying source bias and emotional manipulation in marketing copy or opinion pieces.
- Auditing technical documentation for logical consistency and evidence-based claims.
- Quick fact-checking of social media posts or academic summaries to identify inaccuracies.
How Cross-Verify Works
- The skill extracts all verifiable claims, such as specific data points, names, dates, and percentages from the provided text.
- It performs parallel web searches using authoritative sources like official records, academic journals, and reputable media outlets.
- It conducts a linguistic scan to identify source bias, selection bias, and the use of emotionally charged language.
- The engine analyzes the logical structure of the argument to detect common fallacies like correlation-causation confusion.
- A comprehensive report is generated, including a Credibility Score from 1 to 10 and specific evidence-based conclusions.
Cross-Verify Setup
To activate this skill within your environment, ensure you have the core Openclaw Skills framework installed. Use the following command to add Cross-Verify to your agent:
openclaw install cross-verify
Ensure your agent has active internet access permissions to enable the real-time fact-checking capabilities via web search hooks.
Cross-Verify Data Schema & Taxonomy
The skill generates a structured verification report with the following metadata taxonomy:
| Section | Description | Status Indicators |
|---|---|---|
| Fact Check | Specific claim verification results | ✅ Verified, ⚠️ Uncertain, ❌ Inaccurate |
| Bias Markers | Identification of skewed perspectives | Source Bias, Selective Presentation, Emotional Language |
| Logic Gaps | Structural errors in argumentation | Causal Confusion, Sample Bias, Logic Break |
| Source Audit | Evaluation of information origin | Source Name, Interest Alignment, Primary/Secondary Status |
| Score | Overall 1-10 reliability rating | Qualitative labels (e.g., Highly Reliable to Unreliable) |
Cross-Verify Advanced Features
- Parallel fact-checking across multiple high-authority domains simultaneously to ensure speed and accuracy.
- Sophisticated sentiment analysis that flags biased keywords designed to trigger emotional responses.
- Cross-referencing of stakeholder interests to identify potential financial or political conflicts of interest in the source material.
- Constructive feedback loops that suggest specific missing evidence needed to turn an uncertain claim into a verified fact.
SKILL.md
Loading
Related Openclaw Skills
MemPalace Skill
A persistent semantic memory layer using ChromaDB to enable advanced search and knowledge graph capabilities for AI agents.
Prompt Switchboard Compare Workflows
A specialized skill for teaching agents to install the Prompt Switchboard local MCP sidecar and execute compare-first workflows across multiple browser-based AI models.
Aoleme UI: Cyber-Xianxia & Neon Glassmorphism
A specialized design system for generating immersive, dark neon, and glassmorphism-based React interfaces with a cyber-xianxia aesthetic.
Natural Chinese Protocol
A specialized editing protocol for AI agents to identify and remove machine-generated linguistic patterns in Chinese text.
Longxia Zhipin
Longxia Zhipin is an intelligent orchestration assistant designed to transform company profiles into executable, one-click AI agent team installations.
Self-Evolution
An advanced closed-loop system enabling AI agents to learn from mistakes and evolve through automated rule distillation.
Featured*
