linkedin-humanizer Checked

Name: linkedin-humanizer
Author: sergebulaev

Remove the AI tells human readers and LinkedIn's AI-slop filter react to in a post or comment: 20…

🛠️ Developer Tools skills By sergebulaev Version v1.0.0 Updated 2026-09-15

9.1Overall rating

Installation

🤖 Install via AI

Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.

Install the "linkedin-humanizer" skill by following the instructions at https://skill123.me/install/linkedin-humanizer.

⌨️ Command line install

Run in your terminal — downloads and installs to ~/.claude/skills/.

curl -fsSL https://skill123.me/install/linkedin-humanizer.sh | bash

📦 Download ZIP

Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.

⬇ Download v1.0.0 · 71 KB

About this skill

Overview

Remove the AI tells human readers and LinkedIn's AI-slop filter react to in a post or comment: 2026 vocabulary by paragraph density, reveal bridges, staccato fragments, stacked triads, performed sincerity. Tiered rewriter (forensic / strict / aesthetic / all) plus --mode audit pass-fail review and --mode profile voice profile builder. Not for beating AI detectors (no edit reliably does). Keywords: humanize, de-AI, reads like ChatGPT, AI slop, scrub AI tells, review this draft, audit before posting.

Source

Repo: https://github.com/sergebulaev/linkedin-skills
Path: skills/linkedin-humanizer

Score breakdown

Trigger

9.5

Rich keyword-loaded description with explicit Not-For (does not beat detectors) boundary.

Structure

8.0

175-line dense SKILL.md plus 10 references and 6 sub-skills; well mapped but heavy, with rules-explainer duplicated across locations.

Workflow

9.2

Tiered modes, four named passes, over-correction guard, no-fabrication rule, offline demo mode; audit mode gives pass-fail verification.

Content

10.0

Exceptional specificity with citations and evidence tiers; precise writing.

Engineering

9.0

Correct frontmatter, script runs offline via --demo, deps declared at bundle root.

Security

9.0

Detector API upload is opt-in, key-gated and prominently disclosed; endpoints are known detector vendors; no credential harvesting.

Deep, evidence-cited AI-tell scrubber with tiered modes, four-pass pipeline and a self-check over-correction guard. Detector tester uploads drafts to five detector APIs but only with user-supplied keys and is flagged in SKILL.md as the sole third-party-sending code; offline --demo mode exists.