Advanced anti-corruption investigation system for analyzing chat logs and communications to detect suspicious patterns, corruption indicators, and relationship networks. Supports Chinese and English chat logs in JSON/TXT formats, handles million-scale datasets, and provides human-friendly relationship analysis with evidence-backed conclusions.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
The command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
File Explorer
20 files
Showing SKILL.md
SKILL.md
Source instructions · Read-only preview
name
anti-corruption-investigation
description
Advanced anti-corruption investigation system for analyzing chat logs and communications to detect suspicious patterns, corruption indicators, and relationship networks. Supports Chinese and English chat logs in JSON/TXT formats, handles million-scale datasets, and provides human-friendly relationship analysis with evidence-backed conclusions.
Anti-Corruption Investigation v7.0
What's New in v7.0
Multi-Language Pattern Detection
Chinese Patterns: Financial corruption, power abuse, secret meetings, collusion
English Patterns: Evidence destruction, insider trading, pressure manipulation, enterprise fraud
from anti_corruption import ChatAnalyzer
# Analyze chat data
messages = [...] # Load your messages
analyzer = ChatAnalyzer(messages)
results = analyzer.analyze()
# View resultsprint(f"Risk Level: {results['risk_level']}")
print(f"Suspicious Messages: {len(results['suspicious_messages'])}")
Multi-Language Pattern Detection
from multi_lang_patterns import analyze_text, analyze_email
# Analyze text in any language
result = analyze_text("We need to delete these documents before audit")
print(f"Risk Score: {result['risk_score']}")
print(f"Categories: {result['categories']}")
# Analyze email with enterprise fraud detection
email_data = {
'sender': 'john@company.com',
'receiver': 'jane@company.com',
'subject': 'Q4 Results',
'content': 'We need to hit the target number.',
'title': 'CFO'
}
result = analyze_email(email_data)
print(f"Risk Level: {result['risk_level']}")
