linkedin-humanizer
能系统化降低 AI 文本信号，适合对外发布前把关。
可能无法完全规避平台检测或存在误报，需人工复核。
审计或重写草稿以去除 AI 痕迹，支持分级规则与纯检测模式。
把草稿里那些会被算法判定为 AI 写作的痕迹去掉，或者按 2026 年 LinkedIn 的启发式清单审计成品并给出通过/不通过结论。可以选择不同严格度的重写策略（取证、严格、美学等），也能只做检测不改写。还支持跑多种检测器（如 GPTZero、Originality.ai、Copyleaks）和表情/模式探测，发布前把关更稳妥。
▸ 展开 SKILL.md 英文原文
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".
帮我安装这个 skill：https://raw.githubusercontent.com/sergebulaev/linkedin-skills/main/skills/linkedin-humanizer/SKILL.mdcurl -fsSL "https://raw.githubusercontent.com/sergebulaev/linkedin-skills/main/skills/linkedin-humanizer/SKILL.md"# LinkedIn Humanizer V2 Rewrites any text to remove AI tells. Based on Wikipedia's "Signs of AI writing" taxonomy plus 2026 LinkedIn-specific patterns. **V2 (2026-04-27):** rules now split into 3 tiers so you can pick which signals you trust. ## What changed in V2 The previous version applied every rule equally. We learned that some rules catch real AI output and some catch good human writing. So: - **Forensic** rules catch real AI signals nobody else produces. Always on. - **Strict** rules catch corporate-speak that's bad style regardless of who wrote it. On by default. - **Aesthetic** rules catch patterns that AI uses but humans also use legitimately (em dashes, rule of three, "robust"