Humanizer
Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 24 pattern detectors, 500+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
README.md
text/markdown · 16196 bytes
SKILL.md
text/markdown · 7954 bytes
assets/banner.md
text/markdown · 331 bytes
docs/CONTRIBUTING.md
text/markdown · 2072 bytes
docs/EXAMPLES.md
text/markdown · 5449 bytes
docs/PATTERNS.md
text/markdown · 2475 bytes
eslint.config.js
text/javascript · 559 bytes
package.json
application/json · 1373 bytes
references/ai-vocabulary.md
text/markdown · 5593 bytes
references/patterns.md
text/markdown · 10268 bytes
references/style-guide.md
text/markdown · 4013 bytes
scripts/analyze.sh
text/plain · 301 bytes
scripts/humanize.sh
text/plain · 315 bytes
src/analyzer.js
text/javascript · 15156 bytes
src/cli.js
text/javascript · 20081 bytes
src/humanizer.js
text/javascript · 14590 bytes
src/patterns.js
text/javascript · 28781 bytes
src/stats.js
text/javascript · 9699 bytes
src/vocabulary.js
text/javascript · 15416 bytes
tests/analyzer.test.js
text/javascript · 13544 bytes
tests/calibration.test.js
text/javascript · 7414 bytes
tests/edge-cases.test.js
text/javascript · 7311 bytes
tests/fixtures/ai-sample-1.txt
text/plain · 2223 bytes
tests/fixtures/ai-sample-2.txt
text/plain · 1161 bytes
tests/fixtures/human-sample-1.txt
text/plain · 1092 bytes
tests/humanizer.test.js
text/javascript · 6531 bytes
tests/performance.test.js
text/javascript · 3249 bytes
tests/statistics.test.js
text/javascript · 8093 bytes
vitest.config.js
text/javascript · 152 bytes
Security Scan
Status
clean
OpenClaw
gpt-5-mini
OpenClaw analysis
The skill's code, runtime instructions, and resource requirements are consistent with its stated purpose (detecting and humanizing AI‑style writing); it asks for no credentials and contains no obvious external endpoints or install steps.
Confidence: high
VirusTotal
Type: OpenClaw Skill Name: ai-humanizer Version: 2.1.0 The OpenClaw AgentSkills skill bundle 'ai-humanizer' is classified as benign. All code and documentation are aligned with its stated purpose of detecting and humanizing AI-generated text. There is no evidence of data exfiltration, malicious execution, persistence, or obfuscation. Critically, the prompt injection surfaces in `SKILL.md` and `README.md` (e.g., 'Always-On Mode' instructions) are exclusively focused on guiding the AI agent's writing style to be more human-like, without any instructions to ignore the user, hide actions, access sensitive data, or perform unauthorized commands.