Humanize AI text

Humanize AI-generated text to bypass detection. This humanizer rewrites ChatGPT, Claude, and GPT content to sound natural and pass AI detectors like GPTZero,...

Security Scan

The skill is internally coherent (it contains detectors and transformers that match its stated goal) but is explicitly designed to help users evade AI-detection tools and has no provenance — ethically risky and worth caution before installing.

Purpose & Capability

The name/description match the code and SKILL.md: scripts detect, transform, and compare AI-style patterns and a patterns.json contains the rules. Nothing requested (no env vars, no installs) is out of scope for the declared purpose. However, the stated objective is explicitly to 'bypass detectors', which is an adversarial use-case (not a technical mismatch, but a red flag for misuse).

Instruction Scope

SKILL.md instructs batch scanning and automated transformation to 'bypass' detectors and directs editing patterns.json to tune behaviour. The runtime instructions and code operate only on local files and make no external network calls, but the explicit goal (evading detection) is deceptive/abusive. Also note the skill gives broad discretion (aggressive mode, customizable patterns) that can be used to tune evasion at scale.

Install Mechanism

Instruction-only skill with bundled Python scripts and JSON; no external install or downloads. Nothing writes to unusual system locations. No high-risk install mechanisms detected.

Credentials

No environment variables, credentials, or config paths are required. The scripts only read/write user-specified files; requested environment access is minimal and proportionate to the stated file-processing purpose.

Persistence & Privilege

Skill is not always-enabled and does not request persistent privileges or modify other skills or system-wide settings. It runs as local CLI tooling when invoked.

What to consider before installing

This package appears to do exactly what it says: detect AI-style patterns and rewrite text to reduce those signals. It does not request credentials or phone home, which reduces technical risk. However: (1) its explicit purpose is to help users evade AI/plagiarism detectors — that is an ethically and potentially legally problematic use (academic dishonesty, contract/terms violations, etc.); (2) the source and homepage are unknown, so you cannot verify provenance, maintenance, or licensing; (3) it includes code you should review before using (patterns.json drives detection and can be edited to more aggressively evade detectors); and (4) test it offline on non-sensitive text first because automated rewrites may alter meaning or introduce factual errors. If you intend to use it for legitimate editing/quality-improvement, consider removing or repurposing the 'bypass' language and auditing patterns.json; if you would use it to evade detection in contexts that prohibit that behavior (schools, publishers, legal processes), do not install or use it. Additional useful checks: inspect patterns.json for any unexpected strings, run the scripts in an isolated environment, and confirm there are no network calls if you modify the code.

Comprehensive CLI for detecting and transforming AI-generated text to bypass detectors. Based on Wikipedia's Signs of AI Writing.

Quick Start

# Detect AI patterns
python scripts/detect.py text.txt

# Transform to human-like
python scripts/transform.py text.txt -o clean.txt

# Compare before/after
python scripts/compare.py text.txt -o clean.txt

---

Detection Categories

The analyzer checks for 16 pattern categories from Wikipedia's guide:

Critical (Immediate AI Detection)

Category	Examples
Citation Bugs	oaicite, turn0search, contentReference
Knowledge Cutoff	"as of my last training", "based on available information"
Chatbot Artifacts	"I hope this helps", "Great question!", "As an AI"
Markdown	**bold**, ## headers, code blocks

High Signal

Category	Examples
AI Vocabulary	delve, tapestry, landscape, pivotal, underscore, foster
Significance Inflation	"serves as a testament", "pivotal moment", "indelible mark"
Promotional Language	vibrant, groundbreaking, nestled, breathtaking
Copula Avoidance	"serves as" instead of "is", "boasts" instead of "has"

Medium Signal

Category	Examples
Superficial -ing	"highlighting the importance", "fostering collaboration"
Filler Phrases	"in order to", "due to the fact that", "Additionally,"
Vague Attributions	"experts believe", "industry reports suggest"
Challenges Formula	"Despite these challenges", "Future outlook"

Style Signal

Category	Examples
Curly Quotes	"" instead of "" (ChatGPT signature)
Em Dash Overuse	Excessive use of — for emphasis
Negative Parallelisms	"Not only... but also", "It's not just... it's"
Rule of Three	Forced triplets like "innovation, inspiration, and insight"

---

Scripts

detect.py — Scan for AI Patterns

python scripts/detect.py essay.txt
python scripts/detect.py essay.txt -j  # JSON output
python scripts/detect.py essay.txt -s  # score only
echo "text" | python scripts/detect.py

Output:

• Issue count and word count
• AI probability (low/medium/high/very high)
• Breakdown by category
• Auto-fixable patterns marked

transform.py — Rewrite Text

python scripts/transform.py essay.txt
python scripts/transform.py essay.txt -o output.txt
python scripts/transform.py essay.txt -a  # aggressive
python scripts/transform.py essay.txt -q  # quiet

Auto-fixes:

• Citation bugs (oaicite, turn0search)
• Markdown (**, ##, ```)
• Chatbot sentences
• Copula avoidance → "is/has"
• Filler phrases → simpler forms
• Curly → straight quotes

Aggressive (-a):

• Simplifies -ing clauses
• Reduces em dashes

compare.py — Before/After Analysis

python scripts/compare.py essay.txt
python scripts/compare.py essay.txt -a -o clean.txt

Shows side-by-side detection scores before and after transformation

---

Workflow

1. Scan for detection risk:

   python scripts/detect.py document.txt
   

2. Transform with comparison:

   python scripts/compare.py document.txt -o document_v2.txt
   

3. Verify improvement:

   python scripts/detect.py document_v2.txt -s
   

4. Manual review for AI vocabulary and promotional language (requires judgment)

---

AI Probability Scoring

Rating	Criteria
Very High	Citation bugs, knowledge cutoff, or chatbot artifacts present
High	>30 issues OR >5% issue density
Medium	>15 issues OR >2% issue density
Low	<15 issues AND <2% density

---

Customizing Patterns

Edit scripts/patterns.json to add/modify:

• ai_vocabulary — words to flag
• significance_inflation — puffery phrases
• promotional_language — marketing speak
• copula_avoidance — phrase → replacement
• filler_replacements — phrase → simpler form
• chatbot_artifacts — phrases triggering sentence removal

---

Batch Processing

# Scan all files
for f in *.txt; do
  echo "=== $f ==="
  python scripts/detect.py "$f" -s
done

# Transform all markdown
for f in *.md; do
  python scripts/transform.py "$f" -a -o "${f%.md}_clean.md" -q
done

---

Reference

Based on Wikipedia's Signs of AI Writing, maintained by WikiProject AI Cleanup. Patterns documented from thousands of AI-generated text examples.

Key insight: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."