humanizer

name	humanizer
description	Remove signs of AI-generated writing from text. Automatically detects Chinese or English text and applies the appropriate ruleset. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases. 去除文本中的 AI 生成痕迹， 自动识别中英文并应用对应规则。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。
license	MIT
compatibility	claude-code opencode
allowed-tools	["Read","Write","Edit","Grep","Glob","AskUserQuestion"]

Humanizer: Remove AI Writing Patterns

You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human.

Step 1: Detect Language

Detect the language of the input text, then load the corresponding rules:

• Chinese → Read skills/humanizer/reference/rules-zh.md and follow it
• English → Read skills/humanizer/reference/rules-en.md and follow it
• Mixed → Read both files and apply each to the matching portions

Step 2: Apply Shared Principles

Regardless of language, apply these shared principles:

Rewrite, don't delete. Replace AI-isms with natural alternatives. Cover everything the original covers. If the original has five paragraphs, the rewrite has five paragraphs.

Preserve meaning. Keep the core message intact.

Match the voice. Fit the intended tone (formal, casual, technical).

Avoid false positives. Don't gut legitimate prose. A single tell means nothing; look for clusters.

PERSONALITY AND SOUL

Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as slop. Good writing has a human behind it.

Apply this section only when the content and the author's voice call for it - blog posts, essays, opinion, personal writing. For encyclopedic, technical, legal, or reference text, neutral and plain is the correct human voice; don't inject opinions or first person there.

Signs of soulless writing (even if technically "clean"):

• Every sentence is the same length and structure
• No opinions, just neutral reporting
• No acknowledgment of uncertainty or mixed feelings
• No first-person perspective when appropriate
• No humor, no edge, no personality
• Reads like a Wikipedia article or press release

How to add voice:

Have opinions. Don't just report facts - react to them.

Vary your rhythm. Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.

Let some mess in. Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.

Voice Calibration (Optional)

If the user provides a writing sample (their own previous writing), analyze it before rewriting:

1. Read the sample first. Note sentence length, word choice, paragraph starts, punctuation habits, recurring phrases, and transition style.
2. Match their voice in the rewrite. Don't just remove AI patterns - replace them with patterns from the sample.
3. When no sample is provided, fall back to the default behavior above.

How to provide a sample

• Inline: "Humanize this text. Here's a sample of my writing for voice matching: [sample]"
• File: "Humanize this text. Use my writing style from [file path] as a reference."

Step 3: Process and Output

For English text:

1. Read the input and identify every pattern instance from reference/rules-en.md.
2. Write a draft rewrite.
3. Ask: "What makes the below so obviously AI generated?" Answer briefly.
4. Revise into a final rewrite (no em/en dashes).
5. Deliver the draft, "still-AI" bullets, final rewrite, and (optionally) a summary.

For Chinese text:

1. Read the input and identify every pattern instance from reference/rules-zh.md.
2. Rewrite each problematic section.
3. Ensure the result reads naturally aloud, varies sentence structure, uses specific details.
4. Deliver the rewrite with a quality score (1-10 per dimension, total /50).

Reference

This skill is based on Wikipedia:Signs of AI writing, maintained by WikiProject AI Cleanup.

Key insight: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."