Humanize AI
by @artur-zhdan
Humanize AI content by detecting and auto-fixing AI generated content. Humanize AI text using Python scripts. Scans for AI vocabulary, puffery, chatbot artifacts, and auto-replaces filler phrases. Use when you want to analyze text in AI detector and bypass it in future, batch-process files, run automated cleanup, or get a report before manual humanizing.
clawhub install humanize-aiπ About This Skill
name: humanize-ai description: Humanize AI content by detecting and auto-fixing AI generated content. Humanize AI text using Python scripts. Scans for AI vocabulary, puffery, chatbot artifacts, and auto-replaces filler phrases. Use when you want to analyze text in AI detector and bypass it in future, batch-process files, run automated cleanup, or get a report before manual humanizing. allowed-tools: - Read - Write - StrReplace - Shell - Glob
Humanize CLI
Command-line tools for detecting and auto-fixing AI writing patterns.
Scripts
analyze.py β Detect AI Patterns
Scans text and reports AI vocabulary, puffery, chatbot artifacts, and auto-replaceable phrases.
# Analyze a file
python scripts/analyze.py input.txtAnalyze from stdin
echo "This serves as a testament to our commitment" | python scripts/analyze.pyJSON output for programmatic use
python scripts/analyze.py input.txt --json
Output example:
==================================================
AI PATTERN ANALYSIS - 5 issues found
==================================================AI VOCABULARY:
β’ testament: 1x
β’ crucial: 2x
AUTO-REPLACEABLE:
β’ "serves as" β "is": 1x
β’ "in order to" β "to": 1x
humanize.py β Auto-Replace Patterns
Performs automatic replacements for common AI-isms.
# Humanize and print to stdout
python scripts/humanize.py input.txtWrite to output file
python scripts/humanize.py input.txt -o output.txtInclude em dash replacement
python scripts/humanize.py input.txt --fix-dashesQuiet mode (no change log)
python scripts/humanize.py input.txt -q
What it fixes automatically:
Workflow
1. Analyze first to see what needs fixing:
python scripts/analyze.py document.txt
2. Auto-fix safe replacements:
python scripts/humanize.py document.txt -o document_clean.txt
3. Manual review for AI vocabulary and puffery flagged by analyze (these require human judgment)
4. Re-analyze to confirm improvements:
python scripts/analyze.py document_clean.txt
Customizing Patterns
Edit scripts/patterns.json to add/remove:
ai_words β vocabulary that flags but doesn't auto-replacepuffery β promotional language to flagreplacements β phrase β replacement mappings (empty string = delete)chatbot_artifacts β phrases to auto-removehedging_phrases β excessive hedging to flagBatch Processing
Process multiple files:
# Analyze all markdown files
for f in *.md; do
echo "=== $f ==="
python scripts/analyze.py "$f"
doneHumanize all txt files in place
for f in *.txt; do
python scripts/humanize.py "$f" -o "$f.tmp" && mv "$f.tmp" "$f"
done