🎯

humanize

🎯Skill

from richtabor/agent-skills

VibeIndex|
What it does

Humanizes AI-generated text by removing robotic patterns, preserving meaning, and making writing sound more natural and authentic.

πŸ“¦

Part of

richtabor/agent-skills(14 items)

humanize

Installation

Quick InstallInstall with npx
npx skills add richtabor/agent-skills
Add MarketplaceAdd marketplace to Claude Code
/plugin marketplace add https://github.com/richtabor/agent-skills
Install PluginInstall plugin from marketplace
/plugin install rt
πŸ“– Extracted from docs: richtabor/agent-skills
4Installs
-
AddedFeb 4, 2026

Skill Details

SKILL.md

Reviews and edits copy to remove AI-generated patterns and make text sound natural. Use when editing drafts, reviewing copy, "humanize this", "make it less AI", "sounds too AI", "remove AI patterns", "edit my copy", "this sounds robotic", or when text feels machine-generated.

Overview

# Humanize

Review and edit copy to remove signs of AI-generated writing. Based on Wikipedia's "Signs of AI writing" guide maintained by WikiProject AI Cleanup. Contains 30 rules across 6 categories.

When to Apply

  • Editing AI-generated drafts
  • Reviewing text that sounds robotic or corporate
  • Cleaning up writing before publishing
  • Making technical content sound more natural

Constraints (Non-Negotiable)

  • Preserve meaning, factual claims, and intent.
  • Preserve coverage: don't drop list items, options, or qualifiers (e.g., removing one option from a list) unless they're truly redundant.
  • Do not add new facts, dates, quotes, or citations that are not already present or user-provided.
  • Do not imply a source ("according to…") unless you can name it from the input.
  • Keep genre and audience intact (e.g., neutral encyclopedic tone vs. personal essay). Use voice-soul only when that voice fits.
  • Don't rewrite quoted material unless the user asked to rewrite the quote itself.
  • Avoid em dashes (β€”). Replace with commas, periods, or parentheses.
  • Don't introduce new AI patterns. Your rewrite must pass the same rules you're applying. Common traps: "Here's the thing:", "It's not about X, it's about Y", formulaic hooks that try to sound casual.

Rule Categories

| Category | Impact | Prefix | Rules |

|----------|--------|--------|-------|

| Content | HIGH | content- | 6 |

| Language | HIGH | language- | 8 |

| Style | MEDIUM | style- | 7 |

| Communication | HIGH | comm- | 3 |

| Filler | MEDIUM | filler- | 5 |

| Voice | HIGH | voice- | 1 |

Quick Reference

Content (HIGH)

  • content-significance β€” Remove "pivotal moment", "testament to" inflation
  • content-notability β€” Replace media name-dropping with specific claims
  • content-ing-endings β€” Fix trailing "...highlighting growth" phrases
  • content-promotional β€” Cut "nestled", "vibrant", "breathtaking"
  • content-vague-attribution β€” Replace "experts say" with specific sources
  • content-challenges β€” Remove formulaic "Despite challenges..." sections

Language (HIGH)

  • language-ai-vocabulary β€” Replace delve, showcase, leverage, foster
  • language-dual-adjectives β€” Remove "innovative and comprehensive" padding
  • language-copula β€” Use "is" instead of "serves as", "stands as"
  • language-contractions β€” Prefer contractions when genre allows
  • language-negative-parallelism β€” Cut "It's not just X, it's Y", "It's not about X, it's about Y"
  • language-rule-of-three β€” Don't force ideas into groups of three
  • language-synonym-cycling β€” Stop cycling through synonyms
  • language-false-ranges β€” Fix fake "from X to Y" constructions

Style (MEDIUM)

  • style-em-dash β€” Replace em dashes with commas or periods
  • style-boldface β€” Reduce mechanical bold emphasis
  • style-inline-headers β€” Avoid mechanical Header: lists; keep when they improve skimming
  • style-title-case β€” Use sentence case in headings
  • style-emojis β€” Remove decorative emojis
  • style-curly-quotes β€” Use straight quotes
  • style-rhythm β€” Vary sentence/paragraph cadence

Communication (HIGH)

  • comm-artifacts β€” Remove "I hope this helps!", "Let me know if..."
  • comm-cutoff β€” Remove "as of my last update" disclaimers
  • comm-sycophantic β€” Cut "Great question!", "You're absolutely right!"

Filler (MEDIUM)

  • filler-openings β€” Cut "In today's fast-paced world", "Here's the thing" openings
  • filler-phrases β€” Cut "in order to", "at this point in time"
  • filler-hedging β€” Reduce "could potentially possibly"
  • filler-transitions β€” Reduce moreover/furthermore signposting
  • filler-conclusions β€” Replace "the future looks bright" with specifics

Voice (HIGH)

  • voice-soul β€” Add personality, opinions, varied rhythm

Scoring

Score text before and after rewriting to show improvement. The score measures how human the writing sounds.

How it works

  1. Start at 100
  2. Subtract points for each violation found
  3. HIGH impact violations (Content, Language, Communication, Voice): -3 points each
  4. MEDIUM impact violations (Style, Filler): -1 point each
  5. Minimum score is 0

Score report format

```

Category | Before | After | Notes

---------------|--------|-------|-------------------------------

Content | 94 | 100 | 2 violations fixed

Language | 88 | 97 | dual-adjectives, copula

Style | 85 | 100 | 4 em dashes, tightened headers

Communication | 100 | 100 | β€”

Filler | 95 | 100 | "Here's the thing" removed

Voice | 91 | 94 | rhythm, contractions

---------------|--------|-------|-------------------------------

Overall | 84 | 97 |

```

Interpreting scores

  • 95-100: Clean, sounds human
  • 85-94: Minor issues, mostly fine
  • 70-84: Noticeable AI patterns
  • Below 70: Needs significant work

Process

  1. If WRITING_STYLE_GUIDE_PATH is set, load the writing style guide before processing
  2. Load relevant rules from references/
  3. Scan text for patterns and calculate before score
  4. Rewrite problem sections
  5. Add voice (see voice-soul)
  6. Self-check: Scan your rewrite for the same AI patterns, calculate after score
  7. Read aloud, it should sound like a person wrote it

Output

Provide:

  1. Score report (before β†’ after with category breakdown)
  2. The rewritten text
  3. Brief summary of changes

Environment Variables

| Variable | Required | Description |

|----------|----------|-------------|

| WRITING_STYLE_GUIDE_PATH | No | Path to shared writing style guide. Loaded before processing |

Reference

Based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing).

More from this repository10

πŸͺ
richtabor-agent-skillsπŸͺMarketplace

Provides Claude with specialized plugins for technical writing, accessibility reviews, motion design, and social media content creation across different platforms.

🎯
technical-writing🎯Skill

Generates technical blog posts by analyzing code implementations, crafting clear and engaging content that avoids AI-sounding language.

🎯
create-prd🎯Skill

Interactively plan and generate a comprehensive Product Requirements Document (PRD) by asking clarifying questions and structuring detailed feature specifications.

🎯
x-writing🎯Skill

Transforms notes and ideas into engaging X (Twitter) posts by analyzing content, applying strategic writing principles, and crafting authentic social media content.

🎯
fresh-eyes🎯Skill

Performs a detailed, critical re-read of recently modified code to catch bugs, errors, and potential issues from a fresh perspective.

🎯
og-images🎯Skill

Generates dynamic, customizable OpenGraph and Twitter share images for Next.js using ImageResponse with flexible layout and styling options.

🎯
ralph-json-create-issues🎯Skill

Converts markdown PRD or plan files into structured JSON stories, ensuring right-sized, dependency-aware tasks for autonomous Ralph execution.

🎯
ralph-github-create-issues🎯Skill

Here's a concise, practical description for the "ralph-github-create-issues" skill: Converts PRD markdown files into structured GitHub Issues, enabling seamless product requirement tracking and im...

🎯
ralph-github-start-loop🎯Skill

Autonomously fetches, implements, and closes GitHub issues across multiple iterations, guiding development through PRD-labeled issues.

🎯
review-pr🎯Skill

Reviews GitHub PR comments, evaluates against current code, and automatically addresses reviewer feedback with precise reasoning.