skilld
All skills
sergebulaev avatar

/linkedin-humanizer

@14d332b
by Serge Bulaevsergebulaev/linkedin-skills3.8k stars
641

Remove AI tells from LinkedIn posts/comments: 2026 vocabulary density, reveal bridges, staccato fragments, stacked triads, performed sincerity. Tiered rewriter plus `--mode audit` LinkedIn post auditor and `--mode profile` voice builder. Not for drafting from scratch (use linkedin-post-writer) or beating AI detectors. Keywords: humanize, de-AI, post audit, post auditor, audit before posting.

Ask your Agent

Use this Skill: https://skilld.dev/gh/sergebulaev/linkedin-skills/linkedin-humanizer

This session only. Nothing lands on disk.

referencesexamples.md

≈361 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Examples — LinkedIn Humanizer

Example

Input: "In today's fast-paced landscape, businesses must fundamentally leverage AI to unlock robust ROI. It's not just about adoption, it's about transformation. As of my last update in January 2024, the trends are clear — here's what I've learned."

Output (default mode = forensic + strict): "businesses need AI to cut costs. adoption is the easy part. transformation is the actual work. here's what we learned running 35k LinkedIn profiles through our system daily."

Diff:

  • FORENSIC: removed "As of my last update in January 2024" disclaimer
  • STRICT: paragraph scored 5 markers (fast-paced landscape, fundamentally, leverage, unlock, robust) = rewrite the paragraph, not word-by-word
  • STRICT: removed "It's not just X, it's Y" negative parallelism (single-hit rule), replaced with paired declaratives
  • PASS 1: the one em dash was under the cap (~1 per 100 words); it went only because the sentence around it was rewritten. It was not replaced with a period
  • PASS 3: added a number with a referent (35k LinkedIn profiles, daily) from the user's own input; nothing fabricated, no hedge, no "let me be honest" frame
  • PASS 4: two fragments in the output ("adoption is the easy part." "transformation is the actual work.") are within the 2-per-post cap and are paired declaratives, not a "The result?" reveal; left as is
  • AESTHETIC was NOT applied

Source: SKILL.md on GitHub

Third-party checks

No alertstoday3 checks · Risk SAFE
  • Gen Agent Trust Hubtoday

    The skill is a LinkedIn post humanizer that rewrites text to avoid AI detection signatures. It includes tools for auditing drafts, testing against third-party detectors, and generating illustrations. Security analysis found that the skill transmits user data to external AI detection services and fetches profile information from social platforms. It also possesses a surface for indirect prompt injection as it processes untrusted user input without explicit sanitization markers.

  • Sockettoday

    No alerts

  • Snyktoday

    Risk: LOW · No issues

Provenance

Signed by skilld at 14d332b. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 3 days ago

README badge

README badge for sergebulaev/linkedin-skills/linkedin-humanizer