DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to strip AI tells from a draft and score it before posting with Linkedin Agent Skill

Clean invisible characters and stock phrases from any draft, then get a five-check human score.

Who it is forA writer or marketer who already has a draft from any source and wants a local check before it goes public.

The problemDrafts often carry invisible characters, em dashes and stock words like delve or leverage that make them read as machine-written.

The outcomeA cleaned draft with a report of every change, plus a five-check score that shows what still needs a human rewrite.

What you need first

  • Claude access, either Claude Code for installing the skills or a chat where you can paste a SKILL.md
  • A LinkedIn account you will post from yourself, since the skills never post for you
  • Python 3 for the humanizer scripts, which need no extra dependencies
  • Three of your own past posts, or a filled-in templates/voice.md, so drafts match your voice

Steps

  1. Run git clone https://github.com/Jakeschincariol/linkedin-agent-skill.git in a terminal.
  2. Run cp -r linkedin-agent-skill/skills/li-* ~/.claude/skills/ if you want the skill inside Claude as well.
  3. Save your draft as draft.txt, then run python3 humanize.py draft.txt --report from the li-human folder.
  4. Run python3 detect.py draft.txt to see the five-check score and the verdict.
  5. Rewrite any flagged structures by hand, save as after.txt, then run python3 detect.py before.txt after.txt to see the delta.

Prompt for your agent

Use the li-human scripts in https://github.com/Jakeschincariol/linkedin-agent-skill on <path to draft file>. Run humanize.py with --report, then detect.py, and return the cleaned text, the change report and the HUMAN SCORE. Verify that the score is shown for both the original and the cleaned file.

Caveat. The five checks are local heuristics and not a guarantee against GPTZero, Originality or any other detector, so the score is a guide for rewriting, not a pass certificate.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page