A specialized tool for identifying psychological manipulation tactics and influence patterns in written communication.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install manipulation-detector
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 manipulation-detector 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 Manipulation Detector?
The Manipulation Detector is a critical addition to the library of Openclaw Skills designed to help users and AI agents identify subtle patterns of influence. It analyzes text for common red flags like artificial urgency, unsubstantiated authority claims, and divisive framing.
By providing a structured way to evaluate suspicious content, this skill helps users maintain a healthy level of skepticism without succumbing to paranoia. It is particularly valuable for ensuring a more secure and objective interaction with digital media, social messages, and automated communications, effectively serving as a diagnostic layer for information integrity.
Manipulation Detector Use Cases
- Evaluating suspicious social media posts or news articles for bias and manipulation patterns.
- Analyzing messages from unknown agents or automated systems to detect potential social engineering attempts.
- Screening marketing copy for artificial pressure, false scarcity, or deceptive social proof.
- Calibrating the skepticism levels of AI agents during automated research tasks to prevent bias absorption.
How Manipulation Detector Works
- The user provides text input to the skill via the command line or by referencing a local file path.
- The script scans the content against a comprehensive library of known manipulation patterns including FUD, grandiosity, and us-vs-them framing.
- A numerical score is calculated based on the frequency and intensity of the detected linguistic triggers.
- The skill outputs a categorized risk assessment ranging from Low to High risk based on the final score.
Manipulation Detector Setup
To get started with this entry in the Openclaw Skills collection, ensure you have Python 3 installed on your system. Use the following commands to analyze your content:
# Analyze direct text input via pipe
echo "Your text here" | python3 scripts/detect.py
# Analyze a specific text file
python3 scripts/detect.py path/to/file.txt
Manipulation Detector Data Schema & Taxonomy
The Manipulation Detector organizes its analysis into a structured output based on eight primary psychological patterns and a risk hierarchy.
| Pattern Key | Description of Indicator |
|---|---|
| urgency | Artificial time pressure and scarcity |
| authority_claims | Unsubstantiated claims of expertise or trust |
| fear_uncertainty | FUD tactics and warnings of regret |
| risk_score | Numerical value (0-5: Low, 5-15: Moderate, 15+: High) |
Manipulation Detector Advanced Features
- Multi-pattern detection engine covering eight distinct psychological triggers including dominance assertions and emotional appeals.
- Flexible CLI integration allowing for rapid batch processing of large text datasets or individual messages.
- Calibrated risk scoring system designed to differentiate between minor rhetorical flair and high-stakes psychological manipulation.
- Specifically optimized for agent safety and social engineering defense within the broader Openclaw Skills ecosystem.
SKILL.md
Loading
Related Openclaw Skills
Clarity Vote
A specialized tool for AI agents to participate in scientific consensus by voting on protein folding hypotheses via the Clarity Protocol.
Clarity Variant
A powerful tool for retrieving detailed protein variant data, AI-generated structural summaries, and multi-agent clinical findings from Clarity Protocol.
Clarity Submit
A specialized tool for submitting protein variant hypotheses to the Clarity Protocol for automated validation and structural prediction.
Clarity Research
A powerful tool for searching and exploring community-driven protein mutation analysis and AlphaFold2 folding results.
Competitor Analyzer
The Competitor Analyzer provides instant, structured market intelligence reports for any company using Openclaw Skills.
JSON Toolkit
A comprehensive zero-dependency Python utility for formatting, validating, and querying JSON data through a powerful CLI.
Featured*
