LinkedIn Humanizer
技能 已验证 活跃Scrub AI tells from any text draft OR audit a finished post against the 2026 algorithm heuristic checklist. Tier-based rewriter (forensic / strict / aesthetic / all) plus `--mode audit` for detection-only pass-fail review covering length, hook, CTA, format penalties, AI vocab. Sub-tools: emoji-pattern detector, multi-detector spread tester (GPTZero, Originality.ai, ZeroGPT, Sapling, Copyleaks), rule explainer. Triggers on "humanize", "de-AI", "review this draft", "audit before posting", "is this ready".
To help users ensure their LinkedIn content sounds authentically human and passes modern algorithmic scrutiny, by scrubbing AI artifacts and adhering to specific stylistic rules.
功能
- Tiered AI text scrubbing (forensic, strict, aesthetic)
- AI detection auditing against a 2026 heuristic checklist
- Emoji pattern detection and analysis
- Multi-detector spread testing for AI text
- Rule explainer for stylistic justifications
使用场景
- Humanizing AI-drafted posts before publishing
- Auditing finished drafts for algorithmic compliance and AI tells
- Understanding why certain writing styles might be flagged as AI
- Ensuring content adheres to a specific brand voice
非目标
- Generating original content from scratch
- Providing factual content verification
- Acting as a general-purpose grammar checker
实践
- AI Text Analysis
- Content Auditing
- Style Rule Application
- Prompt Engineering
先决条件
- Claude Code environment
- Python 3 environment (for scripts)
- API keys for external AI detectors (optional, for full functionality)
安装
请先添加 Marketplace
/plugin marketplace add sergebulaev/linkedin-skills/plugin install linkedin-skills@linkedin-skills质量评分
已验证类似扩展
Unslop Review
100重写代码审查意见，使其听起来像人类同事所写。消除 "I noticed...", "I was wondering if perhaps...", "It might be worth considering..." 这类企业AI的套话。每条评论都直截了当：地点、问题、具体修复方案。用于用户说“人性化审查”、“减少PR评论中的废话”、“让反馈听起来更人性化”、“审查此PR”、“代码审查”、“/review”、“/unslop-review”时。在审查PR时自动触发。
Linkedin Reply Handler
98根据特定 LinkedIn 评论的 URL 起草回复。当用户希望回复任何帖子的评论，或在作者回复他们后进行跟进时使用。解析 commentUrn，解析正确的 parentComment 目标（LinkedIn 会将线程展平为 2 个级别），并在批准后通过 Publora 发布。不适用于顶级评论（请使用 linkedin-comment-drafter）。
Linkedin Post Writer
98使用 2026 年钩子公式（头韵、R.I.P.、年份枢轴、时间锚点、自证、付费与免费、好奇心缺口、奇数金钱、反常）从头开始起草新的 LinkedIn 帖子。在获得批准后通过 Publora 运行人工化流程并安排发布。在用户要求撰写帖子、需要钩子或想要经过验证的格式时使用。不适用于审阅现有草稿（请使用 linkedin-humanizer --mode audit）。
Avoid Ai Writing
100审计和重写内容以移除 AI 写作模式（“AI 腔”）。在收到“移除 AI 腔”、“清理 AI 写作”、“编辑写作中的 AI 模式”、“审计写作中的 AI 痕迹”或“让这段文字听起来不那么像 AI”等指令时使用此技能。支持仅检测模式，用于标记模式而不进行重写。
De Ai Ify
100Remove AI-generated jargon and restore human voice to text. Built from analyzing 1,000+ AI vs human content pieces.
Article Writing
100Write blog posts, guides, tutorials, and long-form content. Sounds like a real person, not AI. Use when the user wants polished written content.