ClawHubCN
@brandonwise

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.

镜像下载
当前版本
v2.1.0
54 2.5万总安装 235
说明文件版本对比

README.md

text/markdown · 16196 字节

SKILL.md

text/markdown · 7954 字节

assets/banner.md

text/markdown · 331 字节

docs/CONTRIBUTING.md

text/markdown · 2072 字节

docs/EXAMPLES.md

text/markdown · 5449 字节

docs/PATTERNS.md

text/markdown · 2475 字节

eslint.config.js

text/javascript · 559 字节

package.json

application/json · 1373 字节

references/ai-vocabulary.md

text/markdown · 5593 字节

references/patterns.md

text/markdown · 10268 字节

references/style-guide.md

text/markdown · 4013 字节

scripts/analyze.sh

text/plain · 301 字节

scripts/humanize.sh

text/plain · 315 字节

src/analyzer.js

text/javascript · 15156 字节

src/cli.js

text/javascript · 20081 字节

src/humanizer.js

text/javascript · 14590 字节

src/patterns.js

text/javascript · 28781 字节

src/stats.js

text/javascript · 9699 字节

src/vocabulary.js

text/javascript · 15416 字节

tests/analyzer.test.js

text/javascript · 13544 字节

tests/calibration.test.js

text/javascript · 7414 字节

tests/edge-cases.test.js

text/javascript · 7311 字节

tests/fixtures/ai-sample-1.txt

text/plain · 2223 字节

tests/fixtures/ai-sample-2.txt

text/plain · 1161 字节

tests/fixtures/human-sample-1.txt

text/plain · 1092 字节

tests/humanizer.test.js

text/javascript · 6531 字节

tests/performance.test.js

text/javascript · 3249 字节

tests/statistics.test.js

text/javascript · 8093 字节

vitest.config.js

text/javascript · 152 字节

Security Scan

状态

clean

打开 VirusTotal

OpenClaw

gpt-5-mini

clean

OpenClaw 分析

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.

置信度: 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.

元数据

  • 作者: @brandonwise
  • 创建时间: 2026/02/01
  • 更新时间: 2026/02/26
  • 版本数: 2
  • 评论数: 0
  • 扫描时间: 2026/02/11

运行要求

官方公开数据里暂未列出运行要求。