New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Li Human

by Jakeschincariol in Jakeschincariol/linkedin-agent-skill

Strip the machine fingerprint out of any draft - em dashes, AI slop words, invisible watermark characters - and score it against a five-check detection panel before it goes out.

MITAuto-check passedWriting & Content

Install Li Human

skills CLI
$ npx skills add Jakeschincariol/linkedin-agent-skill --skill li-human -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Jakeschincariol/linkedin-agent-skill li-human --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Jakeschincariol/linkedin-agent-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/li-human .claude/skills/li-human && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
li-human
GitHub stars
1.7k
Token cost
~1.1k tokens
SKILL.md length
594 words
Files
4
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Strip the machine fingerprint out of any draft - em dashes, AI slop words, invisible watermark characters - and score it against a five-check detection panel before it goes out.

  • Works in 5 steps: humanize.py draft.txt -o clean.txt… → Read the structural flags. Rewrite those… → detect.py draft.txt clean.txt to show… → …
  • Text needs to sound human
  • SKILL.md covers What gets fixed automatically, What does NOT get fixed…, The five checks and Say this honestly, plus 1 more section
  • Runs Python scripts from its folder; calls python3

What it does

Li Human is an agent skill from Jakeschincariol/linkedin-agent-skill. Strip the machine fingerprint out of any draft - em dashes, AI slop words, invisible watermark characters - and score it against a five-check detection panel before it goes out. Use whenever text needs to sound human, when the user says humanize, "does this sound like AI", "remove the em dashes", "de-slop this", "will this get flagged", or before any LinkedIn post, comment, reply or DM is shown to the user.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `detect.py`, `humanize.py` and `slop.json`).

It sits in Writing & Content, covering Humanizing AI text and Social media posts. It works with LinkedIn. The repository describes itself as: Eleven free Claude skills that run a LinkedIn account: posts off 21 hook formulas, comments, replies, profile score, weekly plan, and a humanizer that strips the AI fingerprint… The licence is MIT.

When your agent uses it

  • Text needs to sound human
  • The user says humanize
  • Does this sound like AI
  • Remove the em dashes

Example prompts

  • “does this sound like AI”
  • “remove the em dashes”
  • “de-slop this”
  • “/li-human”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. humanize.py draft.txt -o clean.txt --report
  2. Read the structural flags. Rewrite those lines yourself.
  3. detect.py draft.txt clean.txt to show the before and after.
  4. If the verdict is not PASS, fix the weakest check named in the output and
  5. Show the user the cleaned text and the score. Never the score alone.

What it can do on your machine

Read from SKILL.md and the folder at commit add2c23. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Li Human loads about 1.1k tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 594 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~105
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Jakeschincariol/linkedin-agent-skill at commit add2c23, republished under its MIT licence (© Jakeschincariol). 594 words, ~1,130 tokens.

Download SKILL.mdSave it as .claude/skills/li-human/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
li-human
description
Strip the machine fingerprint out of any draft - em dashes, AI slop words, invisible watermark characters - and score it against a five-check detection panel before it goes out. Use whenever text needs to sound human, when the user says humanize, "does this sound like AI", "remove the em dashes", "de-slop this", "will this get flagged", or before any LinkedIn post, comment, reply or DM is shown to the user.

li-human

Two tools live in this folder and they both actually run. Use them. Do not eyeball this.

bash
python3 humanize.py draft.txt --report        # clean it, show what changed
python3 detect.py draft.txt                    # score it, five checks
python3 detect.py before.txt after.txt         # prove the delta

Both read slop.json, which is the lexicon: 100+ stock words and phrases with plain-English replacements, 17 invisible character classes, 11 typographic substitutions, and 11 structural tells. It is meant to be edited. If the user has a word they always use that the lexicon strips, remove it from the file.

What gets fixed automatically

1. Invisible characters. Zero-width spaces and joiners, word joiners, soft hyphens, byte-order marks, Unicode tag characters, non-breaking and narrow spaces. A keyboard does not produce these. They survive copy-paste, they are invisible in every editor, and they are the single most mechanical thing in generated text. humanize.py deletes every one, including any remaining Unicode format character it does not have a name for.

2. Typography. Em dash to comma, en dash to hyphen, curly quotes to straight, ellipsis to three dots, bullet character to hyphen. The em dash pass is the one that matters: it collapses — to , and then cleans up the double punctuation that leaves behind.

3. The slop lexicon. delve, leverage, robust, seamless, crucial, tapestry, testament to, moreover, "in today's fast-paced world", "let that sink in" and the rest, each swapped for a plain word, with capitalisation preserved and URLs left untouched.

What does NOT get fixed automatically

Structural tells get flagged, not rewritten, because changing the shape of a sentence needs judgement:

  • "It's not just X, it's Y" and "not only X but also Y"
  • Rule-of-three triads
  • Rhetorical one-word question lines: "The result?"
  • Rocket, fire, bulb, sparkle and dart emoji
  • Hashtag walls
  • Reflex engagement bait: "Thoughts?", "Agree?", "Who else?"
  • Uniform sentence length and uniform bullet length

That list is your job. Rewrite each flagged line by hand, keeping the meaning, then re-run detect.py. This is the part that moves the score from REVIEW to PASS, and it is the part a script cannot do.

Show full SKILL.md (275 more words)Show less

The five checks

detect.py scores five signals 0-100, higher is more human:

checkwhat it measuresmachine looks like
BURSTINESSsentence-length variationevery sentence the same length
SPECIFICITYnumbers, names, concrete markers per 100 wordsabstract nouns, no figures
SLOP DENSITYlexicon hits per 100 wordsstock vocabulary
FINGERPRINTinvisible chars, em dashes, curly quotes per 1k charstypographically perfect
VOICEcontractions, person, structural tellsno contractions, staged reveals

The verdict weights the mean at 60% and the weakest single check at 40%, because a detector only needs one signal to fire. PASS needs an overall of 70+ with no check below 55.

Say this honestly

These are five local heuristics modelled on the signals public detectors key on. They run entirely on the user's machine and nothing is uploaded. They are not GPTZero, Originality, Copyleaks, Winston or Turnitin, they do not call those APIs, and they cannot promise those verdicts. Fixing what they measure does tend to move those numbers, because they are measuring the same underlying things. That is the claim. Do not make a bigger one on the user's behalf, and do not tell a user their text is undetectable.

Order of operations

  1. humanize.py draft.txt -o clean.txt --report
  2. Read the structural flags. Rewrite those lines yourself.
  3. detect.py draft.txt clean.txt to show the before and after.
  4. If the verdict is not PASS, fix the weakest check named in the output and go again. Two rounds is normal. Five means the draft was written by formula, and the fix is a different draft, not more passes.
  5. Show the user the cleaned text and the score. Never the score alone.

© Jakeschincariol, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files in skills/li-human of Jakeschincariol/linkedin-agent-skill.

  • SKILL.md
  • detect.py
  • humanize.py
  • slop.json

Open the folder on GitHubat commit add2c23

Compare with similar skills

Li Human next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Li Human compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Li Human this skillJakeschincariol/linkedin-agent-skill1.7k—~1.1kAutomated safety check: PassMIT
Linkedin Humanizersergebulaev/linkedin-skills4.4k1 repos~5kAutomated safety check: PassMIT
Linkedin Post Writersergebulaev/linkedin-skills4.4k1 repos~3.6kAutomated safety check: PassMIT
Linkedin Repurposersergebulaev/linkedin-skills4.4k1 repos~1.7kAutomated safety check: PassMIT
Ig Repurposersergebulaev/instagram-skills347—~2.2kAutomated safety check: PassMIT
Writewaynesutton/markdown-site627—~3kAutomated safety check: PassMIT

Similar skills

  • Linkedin Humanizer

    sergebulaev/linkedin-skills

    Remove AI tells from LinkedIn posts/comments: 2026 vocabulary density, reveal bridges, staccato fragments, stacked triads, performed sincerity.

    4.4k GitHub starsUsed in 1 repo~5k tokens
    Writing & ContentAuto-check passed

  • Linkedin Post Writer

    sergebulaev/linkedin-skills

    Draft a new LinkedIn post from scratch using one of 20 2026 hook formulas (anaphora, R.I.P., time-anchor, curiosity-gap, contrarian, controlled A/B, false-binary, and more) plus a founders-edition…

    4.4k GitHub starsUsed in 1 repo~3.6k tokens
    Writing & ContentAuto-check passed

  • Linkedin Repurposer

    sergebulaev/linkedin-skills

    Repurpose existing content into a native LinkedIn post. An agent skill from sergebulaev/linkedin-skills.

    4.4k GitHub starsUsed in 1 repo~1.7k tokens
    Writing & ContentAuto-check passed

  • Ig Repurposer

    sergebulaev/instagram-skills

    Repurpose existing content into a native Instagram post. An agent skill from sergebulaev/instagram-skills.

    347 GitHub stars~2.2k tokensUpdated 4 days ago
    Writing & ContentAuto-check passed

  • Write

    waynesutton/markdown-site

    Writing style guide for technical content, social media, blog posts, READMEs, git commits, and developer documentation.

    627 GitHub stars~3k tokensUpdated 4 mo ago
    Writing & ContentAuto-check passed

  • X Repurposer

    sergebulaev/x-skills

    Repurpose existing content into a native X (Twitter) post or thread.

    124 GitHub starsUsed in 1 repo~1.7k tokens
    Writing & ContentAuto-check passed

More from Jakeschincariol/linkedin-agent-skill

All 11 skills in this repo

  • Li Audit

    Jakeschincariol/linkedin-agent-skill

    Post-mortem on what the user has already published - which posts actually worked, why, and what to stop doing.

    1.7k GitHub stars~854 tokensUpdated 23 days ago
    Auto-check passed

  • Li Carousel

    Jakeschincariol/linkedin-agent-skill

    Build a LinkedIn document post (carousel) - slide-by-slide copy, the cover that earns the swipe, and the PDF to upload.

    1.7k GitHub stars~715 tokensUpdated 23 days ago
    Auto-check passed

  • Li Comment

    Jakeschincariol/linkedin-agent-skill

    Write comments on other people's LinkedIn posts that read as a person with an opinion, not a bot.

    1.7k GitHub stars~1k tokensUpdated 23 days ago
    Auto-check passed

  • Li Dm

    Jakeschincariol/linkedin-agent-skill

    Write connection notes and DM follow-ups that get replies - the 200-character invite, the first message, and the two follow-ups.

    1.7k GitHub stars~780 tokensUpdated 23 days ago
    Auto-check passed

  • Li Inbox

    Jakeschincariol/linkedin-agent-skill

    Triage the LinkedIn inbox - sort connection requests and DMs into leads, recruiters, peers and spam, and draft the replies worth sending.

    1.7k GitHub stars~723 tokensUpdated 23 days ago
    Auto-check passed

  • Li Plan

    Jakeschincariol/linkedin-agent-skill

    Build the week on LinkedIn - what to post, when to post it, and who to engage with.

    1.7k GitHub stars~905 tokensUpdated 23 days ago
    Auto-check passed

Works with

Categories

Questions about Li Human

What does Li Human do?

Strip the machine fingerprint out of any draft - em dashes, AI slop words, invisible watermark characters - and score it against a five-check detection panel before it goes out. Li Human is an agent skill from Jakeschincariol/linkedin-agent-skill. Strip the machine fingerprint out of any draft - em dashes, AI slop words, invisible watermark characters - and score it against a five-check detection panel before it goes out.

When should I use Li Human?

Li Human fits situations like: text needs to sound human; the user says humanize; does this sound like AI; remove the em dashes.

How do I install Li Human in Claude Code?

Run `npx skills add Jakeschincariol/linkedin-agent-skill --skill li-human -a claude-code`. Or copy the skill folder (skills/li-human in Jakeschincariol/linkedin-agent-skill) into .claude/skills/li-human in your project. Claude Code loads it when a task matches its description.

How do I install Li Human in Codex?

Run `npx skills add Jakeschincariol/linkedin-agent-skill --skill li-human -a codex`. Or copy the skill folder (skills/li-human in Jakeschincariol/linkedin-agent-skill) into .agents/skills/li-human in your project. Codex loads it when a task matches its description.

Can I use Li Human in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Jakeschincariol/linkedin-agent-skill --skill li-human -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/li-human, .gemini/skills/li-human, .github/skills/li-human and .opencode/skills/li-human in your project.

What does Li Human need to run?

Going by SKILL.md and its folder, Li Human needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Li Human access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Li Human safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Li Human use?

Li Human is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Li Human use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Li Human?

Skills that share tags, products or a category with Li Human: Linkedin Humanizer (sergebulaev/linkedin-skills, 4.4k stars), Linkedin Post Writer (sergebulaev/linkedin-skills, 4.4k stars), Linkedin Repurposer (sergebulaev/linkedin-skills, 4.4k stars) and Ig Repurposer (sergebulaev/instagram-skills, 347 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Li Human?

Jakeschincariol (a GitHub user) maintains it in Jakeschincariol/linkedin-agent-skill, which has 1,688 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 17, 2026.

Source: Jakeschincariol/linkedin-agent-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.