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.

Review this before installing if you care about authorship transparency. Use it only for editing where it is appropriate to change style, not to conceal AI involvement in schoolwork, hiring materials, compliance filings, legal documents, or other contexts where authorship matters. Avoid enabling the always-on prompt templates unless you intentionally want a persistent style policy and know how to remove it. When analyzing untrusted text, prefer JSON output or a cautious terminal environment until terminal-control escaping is fixed.

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.