Skill 与 AgentSKILLS & AGENTS· CLAUDE-SKILL
conorbronsdon/avoid-ai-writing
一个技能,能扫描并改写文字,去掉AI写作腔调,让内容更像人写的。Audit and rewrite content to remove AI writing patterns, for use with Claude Code, OpenClaw, Codex, and Hermes.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
让 AI 写的东西读起来像人写的
给文章打分,标出 AI 痕迹的位置和类型
在 Git 提交前自动检查文章有没有 AI 腔
保留作者个人风格的同时去掉 AI 套话
Detect 34 categories of AI writing patterns
Rewrite text to remove AI-isms
Preserve the writer's voice during rewriting
Edit local files to clean AI patterns
Interpret false-positive flags from the detector
上手GET STARTED
git clone https://github.com/conorbronsdon/avoid-ai-writing ~/.claude/skills/avoid-ai-writing选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
未知Unknown
静态扫描STATIC SCAN
在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.
The static scan found no known risk patterns, but this does not guarantee the tool is completely safe.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
15 NOV 202615 NOV 2026
增长GROWTH
+1.9%+1.9%
5.7k → 5.8k stars · 6 个快照5.7k → 5.8k stars · 6 snapshots
讨论DISCUSSION
1 SOURCES1 SOURCES
1 条外部提及1 external mentions
状态STATUS
持续活跃Active
质量 AQuality A
能一键扫描并改写文本,去掉AI写作痕迹,适合需要让文字更像人写的场景。Has 5,677 stars on GitHub
HN_STORY · 1 points · 0 comments
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude-plugin/"
},
{
"agent": "claude-ai",
"evidence": "readme: …pository-instructions)) | | **Claude.ai Projects** | paste `dist/avoi…"
},
{
"agent": "codex",
"evidence": "readme: …* [Hermes](#hermes) * [OpenAI Codex](#openai-codex) * [Native…"
},
{
"agent": "cursor",
"evidence": "readme: …ted rule into your project's `.cursor/rules/`: ```bash mkdir -p .cursor/…"
},
{
"agent": "windsurf",
"evidence": "readme: …-----------|------------| | **Windsurf** | clone the skill directory…"
},
{
"agent": "cline",
"evidence": "readme: …t in `.windsurf/rules/` | | **Cline** | `.clinerules/avoid-ai-wri…"
},
{
"agent": "vscode",
"evidence": "readme: …les)) | | **GitHub Copilot** (VS Code) | paste into `.github/copilo…"
},
{
"agent": "copilot",
"evidence": "readme: …/features/cline-rules)) | | **GitHub Copilot** (VS Code) | paste into `.gi…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 5,
"dev-tools": 0,
"indie-web": 0,
"skill-agent": 3,
"productivity": 0
},
"primary": "skill-agent",
"secondary": "claude-skill"
},
"localRuntime": null,
"skillMdTotal": 9,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 1,
"design": 0,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "9 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 13 markdown files",
"weight": 0.75
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "Claude Code plugin manifest",
"weight": 0.7
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"SKILL.md",
"plugins/avoid-ai-writing/skills/avoid-ai-writing/SKILL.md",
"skills/ai-writing-detector/SKILL.md",
"skills/avoid-ai-writing-router/SKILL.md",
"skills/avoid-ai-writing/SKILL.md",
"skills/false-positive-reviewer/SKILL.md",
"skills/file-edit-in-place/SKILL.md",
"skills/preservation-verifier/SKILL.md",
"skills/voice-preserving-rewriter/SKILL.md"
],
"skillMdFetched": 9
}