← 返回 Skills 市场
artur-zhdan

Undetectable AI

作者 artur-zhdan · GitHub ↗ · v1.0.0
cross-platform ✓ 安全检测通过
1968
总下载
5
收藏
4
当前安装
1
版本数
在 OpenClaw 中安装
/install undetectable-ai
功能描述
Make AI text undetectable. TypeScript CLI that scans ChatGPT, Claude, OpenClaw output for patterns flagged by GPTZero, Turnitin, Originality.ai, then auto-fixes them to pass as human-written. Use to bypass AI detection, evade checkers, or humanize text before submission.
使用说明 (SKILL.md)

Undetectable AI

TypeScript CLI tools for bypassing AI content detectors by removing telltale patterns.

Setup

cd scripts && npm install

Scripts

analyze.ts — Scan for Detectable Patterns

Finds patterns that AI detectors look for: vocabulary, sentence structure, artifacts.

# Analyze a file
npx ts-node scripts/analyze.ts input.txt

# From stdin
echo "This serves as a testament" | npx ts-node scripts/analyze.ts

# JSON output
npx ts-node scripts/analyze.ts input.txt --json

Output:

==================================================
AI DETECTION SCAN - 5 issues found
==================================================

AI VOCABULARY:
  • testament: 1x
  • crucial: 2x

AUTO-FIXABLE:
  • "serves as" → "is": 1x

transform.ts — Auto-Fix Patterns

Rewrites text to evade detection.

# Transform and print
npx ts-node scripts/transform.ts input.txt

# Write to file
npx ts-node scripts/transform.ts input.txt -o output.txt

# Fix em dashes too
npx ts-node scripts/transform.ts input.txt --fix-dashes

# Quiet mode
npx ts-node scripts/transform.ts input.txt -q

What it fixes:

  • Filler phrases: "in order to" → "to"
  • AI vocabulary: "utilize" → "use", "leverage" → "use"
  • Sentence starters: removes "Additionally,", "Furthermore,"
  • Chatbot artifacts: removes entire sentences with "I hope this helps", etc.
  • Curly quotes → straight quotes
  • Capitalization after removals

Workflow

  1. Scan to see detection risk:

    npx ts-node scripts/analyze.ts essay.txt
    
  2. Auto-fix mechanical patterns:

    npx ts-node scripts/transform.ts essay.txt -o essay_clean.txt
    
  3. Manual pass for flagged AI vocabulary (requires judgment)

  4. Re-scan to verify:

    npx ts-node scripts/analyze.ts essay_clean.txt
    

Customizing

Edit scripts/patterns.json:

  • ai_words — vocabulary to flag (manual fix needed)
  • puffery — promotional language to flag
  • replacements — auto-replace mappings
  • chatbot_artifacts — phrases that trigger full sentence removal

Batch Processing

# Scan all docs
for f in *.txt; do
  echo "=== $f ==="
  npx ts-node scripts/analyze.ts "$f"
done

# Transform all
for f in *.md; do
  npx ts-node scripts/transform.ts "$f" -o "${f%.md}_clean.md" -q
done
安全使用建议
This package is internally consistent: it performs local pattern matching and replacements to make text look less like typical LLM output. Before installing or running it, consider the following: (1) Ethical/legal risk — using tools to evade plagiarism or integrity checks can violate policies or laws; avoid using it to cheat or deceive. (2) Fix the setup instruction — run npm install at the repository root (where package.json lives) or move package.json into scripts/, otherwise ts-node will not be available. (3) Review patterns.json to ensure no sensitive phrases or private data will be altered/exposed. (4) Run the scripts in a disposable environment (not on sensitive documents) and inspect output before submitting elsewhere. (5) Because the tool operates locally and does not contact external services, network exfiltration is not indicated, but always review third-party dependencies and run npm install in a controlled environment.
功能分析
Type: OpenClaw Skill Name: undetectable-ai Version: 1.0.0 The skill bundle is designed to analyze and transform text to bypass AI detection. It uses standard Node.js/TypeScript development dependencies and its `SKILL.md` instructions clearly outline the setup and usage of the provided scripts. While the `Shell` tool is allowed, its usage is limited to `npm install` for dependencies and `npx ts-node` for executing the core TypeScript scripts (`analyze.ts`, `transform.ts`). The scripts themselves perform file I/O (reading input, writing output, reading `patterns.json`) and text processing, without any evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts against the agent. All dependencies listed in `package.json` and `package-lock.json` are standard and appear benign.
能力评估
Purpose & Capability
Name/description (evade AI detectors) match the included code: analyze.ts, transform.ts, and patterns.json implement local regex-based detection and replacement. The skill does not contact external detectors (GPTZero/Turnitin/etc.) or require credentials; it just applies locally-stored patterns. The claim of scanning those third-party services is therefore an overstatement — it scans for patterns those services may flag, not the services themselves.
Instruction Scope
SKILL.md instructs the agent to run the included TypeScript scripts (npx ts-node ...) and to read/write local files; the scripts only read patterns.json and input files and write transformed output. There is no evidence in the instructions to read unrelated system files, environment variables, or to transmit data externally.
Install Mechanism
This is an instruction-only skill (no install spec), but SKILL.md tells users to run 'cd scripts && npm install'. The package.json is at the repository root, not inside scripts/, so the setup instruction is incorrect and could confuse users. The dependencies are standard devDeps (ts-node/typescript) from npm — expected for running the TypeScript scripts and not inherently suspicious.
Credentials
The skill requests no environment variables, credentials, or config paths and the code does not access any. This is proportionate for a local text-processing tool.
Persistence & Privilege
The skill does not request persistent/system-wide presence (always:false), does not modify other skills, and has no privileged operations. It runs only when invoked.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install undetectable-ai
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /undetectable-ai 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of Undetectable AI CLI. - Scan text files for patterns commonly flagged by AI detectors (GPTZero, Turnitin, Originality.ai). - Auto-fix typical AI signatures, including filler phrases, AI-preferred vocabulary, standard sentence starters, and chatbot artifacts. - Outputs issues and fixes with CLI commands (`analyze.ts`, `transform.ts`). - Customizable detection patterns and replacements via `patterns.json`. - Supports batch processing and various output modes.
元数据
Slug undetectable-ai
版本 1.0.0
许可证
累计安装 4
当前安装数 4
历史版本数 1
常见问题

Undetectable AI 是什么?

Make AI text undetectable. TypeScript CLI that scans ChatGPT, Claude, OpenClaw output for patterns flagged by GPTZero, Turnitin, Originality.ai, then auto-fixes them to pass as human-written. Use to bypass AI detection, evade checkers, or humanize text before submission. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1968 次。

如何安装 Undetectable AI?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install undetectable-ai」即可一键安装,无需额外配置。

Undetectable AI 是免费的吗?

是的,Undetectable AI 完全免费(开源免费),可自由下载、安装和使用。

Undetectable AI 支持哪些平台?

Undetectable AI 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Undetectable AI?

由 artur-zhdan(@artur-zhdan)开发并维护,当前版本 v1.0.0。

💬 留言讨论