New: 97,000+ 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

Humanizer

by Prism-Shadow in Prism-Shadow/penguin-harness

Rewrite or edit prose in any language so it reads like edited human writing in the register of books, newspapers and encyclopedias rather than default AI output.

Apache-2.0Auto-check passedWriting & Content

Install Humanizer

skills CLI
$ npx skills add Prism-Shadow/penguin-harness --skill humanizer -a claude-code

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

GitHub CLI
$ gh skill install Prism-Shadow/penguin-harness humanizer --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/Prism-Shadow/penguin-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/humanizer/skills/humanizer .claude/skills/humanizer && 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
humanizer
GitHub stars
2.5k
Token cost
~1.8k tokens
SKILL.md length
964 words
Files
10
Skills in repo
31
Repo updated
First seen
Licence
Apache-2.0

At a glance

Rewrite or edit prose in any language so it reads like edited human writing in the register of books, newspapers and encyclopedias rather than default AI output.

  • Works in 7 steps: No pattern twice. Whatever the figure —… → Density is anchored facts in whole… → Cap the quotables. One or two turned… → …
  • Tasks that involve Humanizing AI text
  • SKILL.md covers Before you start, Core principles, Method and Worked example (English)
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Humanizer is an agent skill from Prism-Shadow/penguin-harness. Rewrite or edit prose in any language so it reads like edited human writing in the register of books, newspapers and encyclopedias rather than default AI output. A small drafting core — vary every pattern, build density from anchored facts in whole grammar, cap the quotables, put a real writer with real material behind the text, let structure serve content, write each language from inside its idiom and typography, verify what you assert, and aim for the natural distribution of edited prose rather than a perfect…

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files (for example `reference/case-study.md`, `reference/de-cues.md` and `reference/en-cues.md`).

It sits in Writing & Content, covering Humanizing AI text, Copy editing and proofreading and Typography. The repository describes itself as: 🐧 Unified and Stable RSI Platform. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Humanizing AI text
  • Tasks that involve Copy editing and proofreading
  • Tasks that involve Typography

Example prompts

  • “/humanizer”

Workflow steps

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

  1. No pattern twice. Whatever the figure — a contrast frame, a triad, a cleft, an opener shape, a paragraph arc, a metaphor, even a favorite…
  2. Density is anchored facts in whole grammar. Names, dates, numbers, mechanisms and worked examples carry the argument; hype, era openers…
  3. Cap the quotables. One or two turned phrases can carry a piece, counting every shape: chiasmus, mirrored re-description, balanced…
  4. A real writer, with the material. Opinion owns its anecdotes and risks a judgment of its own; reportage has stood somewhere; reference…
  5. Structure serves content. Open on ground, not on a cold verdict and not on an era; paragraphs develop one idea across several sentences…
  6. Write from inside the language. Native idiom — a sentence that back-translates cleanly into another language was composed there, so…
  7. True, verified, calibrated. Never invent specifics. Re-derive every mechanism example from the stated mechanism, split fused attributions…

What it can do on your machine

Read from SKILL.md and the folder at commit d56d9ce. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Humanizer loads about 1.8k tokens when it runs. Until then it costs about 177 tokens; SKILL.md has 964 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~177
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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 Prism-Shadow/penguin-harness at commit d56d9ce, republished under its Apache-2.0 licence (© Prism-Shadow). 964 words, ~1,841 tokens.

Download SKILL.mdSave it as .claude/skills/humanizer/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
humanizer
description
Rewrite or edit prose in any language so it reads like edited human writing in the register of books, newspapers and encyclopedias rather than default AI output. A small drafting core — vary every pattern, build density from anchored facts in whole grammar, cap the quotables, put a real writer with real material behind the text, let structure serve content, write each language from inside its idiom and typography, verify what you assert, and aim for the natural distribution of edited prose rather than a perfect scorecard — backed by a three-layer tell catalog, per-language cue files for six languages and a seven-round measured case study shipped as reference files for the diagnostic census.

Humanizer

Make prose read like edited human writing: the register of books, quality newspapers and encyclopedia entries. Everything here was derived empirically, across seven rounds of drafting, blind editorial review and revision, documented with counts in reference/case-study.md. The working surface is deliberately small: a writer boxed in by a long checklist produces compliance, not prose — that failure mode is the case study's best-documented finding. Draft with the principles below; diagnose with the catalog afterwards.

Before you start

If the invocation carries no text and no assignment, ask for one: the draft to edit, or the topic, length, audience and language to write fresh. Settle two things early. The register: books, newspapers and encyclopedias are the default target, while marketing, speeches and reference documentation legitimately bend these rules, so confirm how far to go. And any hard length target: humanizing shrinks text, and gaps are filled with substance, never padding. If the genre needs material nobody has gathered — reportage needs a scene, a person, a quotation — say so and get it, or agree to relabel the piece; never fake the texture.

Core principles

  1. No pattern twice. Whatever the figure — a contrast frame, a triad, a cleft, an opener shape, a paragraph arc, a metaphor, even a favorite connective particle — its second consecutive use is a rhythm and its third is a stencil. Vary sentence length, clause weight, paragraph attack and closer; if every paragraph advances by the same move, swap engines somewhere.
  2. Density is anchored facts in whole grammar. Names, dates, numbers, mechanisms and worked examples carry the argument; hype, era openers, phantom crowds ("faster than most expected" — who?) and concepts pushing concepts carry nothing. Compress by dropping padding, not grammar: subjects stay, first mentions get their full noun, and the event that matters gets a sentence of its own.
  3. Cap the quotables. One or two turned phrases can carry a piece, counting every shape: chiasmus, mirrored re-description, balanced antithesis, aphoristic kickers. State the thesis once and develop it with new material or cut the echo. Most paragraphs end flat, and an argument survives a dud.
  4. A real writer, with the material. Opinion owns its anecdotes and risks a judgment of its own; reportage has stood somewhere; reference registers keep the writer invisible without chaperoning the reader. Claims sized to the evidence, honest hedges kept, references anchored (who, where, when), and one non-obvious source beats a second canonical one.
  5. Structure serves content. Open on ground, not on a cold verdict and not on an era; paragraphs develop one idea across several sentences; headings and bullets appear only where content is genuinely enumerable; the piece ends where the information ends.
  6. Write from inside the language. Native idiom — a sentence that back-translates cleanly into another language was composed there, so recompose it — native punctuation at native frequency (a dash where the register expects one beats zero), and the venue's typography held consistently. Per-language budgets and surface forms: reference/language-cues.md, which indexes one reference/<lang>-cues.md file per language.
  7. True, verified, calibrated. Never invent specifics. Re-derive every mechanism example from the stated mechanism, split fused attributions, and verify or delete every superlative. One fluent falsehood outweighs any amount of style.

Over all seven: aim for the natural distribution of edited prose, not a perfect scorecard. Every rule above, overdriven, mints a new tell — the case study documents four such artifacts (banned openers became cold-open verdicts; scrubbed punctuation became semicolon inflation and rationed warmth; density became telegraph compression; scrubbed abstraction became contrived colloquialism). Keep some looseness, an aside, an unresolved edge.

Show full SKILL.md (374 more words)Show less

Method

  1. Read whole, list the keeps. Facts, quotations, required terminology, genre constraints, any hard length target. Everything on the list survives the rewrite.
  2. Draft, or restructure, by the principles. For an existing draft: merge fragment paragraphs by idea, delete scaffolding, then rewrite sentence by sentence. Do not draft against the catalog — that produces compliance-shaped text.
  3. Census. Now open reference/tells.md and count. The drafting mind cannot see its own tics: in a field test, an author who felt two aphorisms was carrying eight, and five triads survived a no-triads rule. Mechanical counting over impression, catalog over memory; a flagged pattern kept for its quality is still flagged.
  4. Revise and gate. Fix what the census found; verify facts and mechanisms (principle 7); read aloud for rhythm. Then the excerpt test: any paragraph alone should sit unnoticed in a book, a broadsheet or an encyclopedia. Finish with one skeptical-editor read asking where a reader would still mutter "AI wrote this" — and when several pieces come from one session, compare them side by side, because shared architecture across pieces is a fingerprint too. One more stop rule: a spot flagged again after repair is overloaded, not misworded — restructure the thought (split it, reorder it) instead of trying a third wording.

Worked example (English)

Before, tells marked: "In today's rapidly evolving AI landscape [era opener], skills have emerged as a game-changer [hype]. A skill isn't just a document — [dash] it's a reusable playbook [template contrast] that transforms how agents work. Whether you're automating reports, reviewing code, or managing data [triad, reader address], skills unlock consistency, reliability, and scale [triad, hype]. The future of agent workflows starts here [uplift ending]."

After: "A skill is a document that tells an AI agent how to perform one kind of task. The agent keeps only the document's one-line summary in memory and reads the full text when a matching task arrives, so hundreds of skills can be installed at negligible cost. The format is plain Markdown with a short metadata header, which means anyone who can write instructions can write a skill."

The full tell catalog is in reference/tells.md, per-language surface forms in the reference/<lang>-cues.md files indexed by reference/language-cues.md, and the measured record behind all of it in reference/case-study.md.

© Prism-Shadow, Apache-2.0. 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 9 other files in plugins/humanizer/skills/humanizer of Prism-Shadow/penguin-harness.

  • SKILL.md
  • reference/case-study.md
  • reference/de-cues.md
  • reference/en-cues.md
  • reference/es-cues.md
  • reference/fr-cues.md
  • reference/ja-cues.md
  • reference/language-cues.md
  • reference/tells.md
  • reference/zh-cues.md

Open the folder on GitHubat commit d56d9ce

Compare with similar skills

Humanizer 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.

Humanizer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Humanizer this skillPrism-Shadow/penguin-harness2.5k—~1.8kAutomated safety check: PassApache-2.0
User-Facing Text Cleanupguillaumemeyer/watermarks-remover23k—~3.5kAutomated safety check: PassMIT
Chinese Text Humanizerop7418/Humanizer-zh19k—~2kAutomated safety check: PassMIT
Natural Japanese Business Writingcoji/natural-japanese1.9k—~2.1kAutomated safety check: PassMIT
Zero Slop Prose Editoriflytek/skillhub5.2k—~1.5kAutomated safety check: PassMIT
Korean AI-Text Humanizerepoko77-ai/im-not-ai5.9k—~4.5kAutomated safety check: PassMIT

Similar skills

  • User-Facing Text Cleanup

    guillaumemeyer/watermarks-remover

    Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.

    23k GitHub stars~3.5k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed

  • Chinese Text Humanizer

    op7418/Humanizer-zh

    Edits Chinese articles, comments and documents to remove filler, repetition and template phrasing while keeping the facts, the level of certainty and the author's voice.

    19k GitHub stars~2k tokensUpdated 14 days ago
    Writing & ContentAuto-check passed

  • Natural Japanese Business Writing

    coji/natural-japanese

    Writes and edits Japanese business documents so they read clearly and naturally, removes AI-sounding phrasing and can score how AI-like a text reads.

    1.9k GitHub stars~2.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed

  • Zero Slop Prose Editor

    iflytek/skillhub

    Audits and rewrites formulaic, AI-sounding prose while keeping facts, voice and format, using a local Python scorer and inspect-only, rewrite or embedded-gate modes.

    5.2k GitHub stars~1.5k tokensUpdated 6 days ago
    Writing & ContentAuto-check passed

  • Korean AI-Text Humanizer

    epoko77-ai/im-not-ai

    Rewrites Korean text written by AI so it reads like a human wrote it, detecting translationese and other AI patterns while leaving the content untouched.

    5.9k GitHub stars~4.5k tokensUpdated 11 days ago
    Writing & ContentAuto-check passed

  • Web Novel AI-Trace Remover

    zenstory-ai/oh-story-claudecode

    Rewrites AI-sounding Chinese web novel text so it reads naturally, changing as little as possible and keeping plot, names and numbers intact.

    7.3k GitHub starsUsed in 1 repo~2.6k tokens
    Writing & ContentAuto-check passed

More from Prism-Shadow/penguin-harness

All 31 skills in this repo

  • A2ui

    Prism-Shadow/penguin-harness

    Make a reply easier to read and act on with rich blocks inside ordinary Markdown — a choice the user picks from, a form that collects several answers, a procedure as steps with warnings in place, a…

    2.5k GitHub stars~3k tokensUpdated today
    Auto-check passed

  • Penguin Harness Dev

    Prism-Shadow/penguin-harness

    A skill your agent uses when developing PenguinHarness itself — changing packages/{core,server,web,cli,desktop,landing,docs,skills}, the built-in model catalog, the installers or the release…

    2.5k GitHub stars~3.4k tokensUpdated today
    Auto-check passed

  • Bento Slides

    Prism-Shadow/penguin-harness

    Create and edit Bento presentations — self-contained .bento.html decks whose document is JSON.

    2.5k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Penguin Harness Manual Test

    Prism-Shadow/penguin-harness

    A skill your agent uses when standing PenguinHarness up to try a change by hand — launching the Web App, the desktop shell, the landing page, the docs site or the component gallery to click through…

    2.5k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Penguin Harness Frontend

    Prism-Shadow/penguin-harness

    A skill your agent uses when changing the PenguinHarness Web App (packages/web) or the shared UI package — adding or restyling any UI, picking a status colour, adding an icon, laying out a row or a…

    2.5k GitHub stars~6.4k tokensUpdated today
    Auto-check passed

  • Browser Automation

    Prism-Shadow/penguin-harness

    Drive the PenguinHarness agent browser — the desktop app's built-in browser or the user's own Chrome — from the shell with penguin browser: open pages, read them as simplified HTML or text, act with…

    2.5k GitHub stars~2.9k tokensUpdated today
    Auto-check: warnings

Categories

Questions about Humanizer

What does Humanizer do?

Rewrite or edit prose in any language so it reads like edited human writing in the register of books, newspapers and encyclopedias rather than default AI output. Humanizer is an agent skill from Prism-Shadow/penguin-harness. Rewrite or edit prose in any language so it reads like edited human writing in the register of books, newspapers and encyclopedias rather than default AI output.

When should I use Humanizer?

Humanizer fits situations like: tasks that involve Humanizing AI text; tasks that involve Copy editing and proofreading; tasks that involve Typography.

How do I install Humanizer in Claude Code?

Run `npx skills add Prism-Shadow/penguin-harness --skill humanizer -a claude-code`. Or copy the skill folder (plugins/humanizer/skills/humanizer in Prism-Shadow/penguin-harness) into .claude/skills/humanizer in your project. Claude Code loads it when a task matches its description.

How do I install Humanizer in Codex?

Run `npx skills add Prism-Shadow/penguin-harness --skill humanizer -a codex`. Or copy the skill folder (plugins/humanizer/skills/humanizer in Prism-Shadow/penguin-harness) into .agents/skills/humanizer in your project. Codex loads it when a task matches its description.

Can I use Humanizer 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 Prism-Shadow/penguin-harness --skill humanizer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/humanizer, .gemini/skills/humanizer, .github/skills/humanizer and .opencode/skills/humanizer in your project.

What does Humanizer need to run?

SKILL.md names no scripts, command-line tools or credentials: Humanizer is instructions for the agent only.

Does Humanizer 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 Humanizer 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 Humanizer use?

Humanizer is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Humanizer use?

About 1.8k tokens (SKILL.md is roughly 7.4k 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 Humanizer?

Skills that share tags, products or a category with Humanizer: User-Facing Text Cleanup (guillaumemeyer/watermarks-remover, 23k stars), Chinese Text Humanizer (op7418/Humanizer-zh, 19k stars), Natural Japanese Business Writing (coji/natural-japanese, 1.9k stars) and Zero Slop Prose Editor (iflytek/skillhub, 5.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Humanizer?

Prism-Shadow (a GitHub organization) maintains it in Prism-Shadow/penguin-harness, which has 2,450 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on October 7, 2026.

Source: Prism-Shadow/penguin-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.