Humanizer
Polish landing pages, docs, emails, and posts so they read like a human wrote them—not generic LLM filler.
Overview
Humanizer is a journey-wide agent skill that rewrites text to strip AI-writing tells—using 24 Wikipedia-derived patterns—usable whenever a solo builder needs publishable copy.
Install
npx skills add https://github.com/softaworks/agent-toolkit --skill humanizerWhat is this skill?
- 24 AI-writing patterns with before/after examples (Wikipedia WikiProject AI Cleanup)
- Targets significance inflation, vague gravitas, and statistically "average" LLM phrasing
- Invoke via /humanizer or direct "please humanize this text" in Claude Code
- Clone-into-~/.claude/skills install path for persistent skill usage
- Content-pattern table covering tone, structure, and credibility fixes
- 24 patterns detected with before/after examples
- Based on Wikipedia WikiProject AI Cleanup "Signs of AI writing" guide
Adoption & trust: 4k installs on skills.sh; 2k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your marketing, docs, or emails sound polished but hollow—readers spot LLM cadence and inflated significance instantly.
Who is it for?
Founders publishing landing copy, lifecycle emails, docs, or social posts without a dedicated editor.
Skip if: Legal or medical content requiring professional review, or workflows that need factual research rather than tone editing.
When should I use this skill?
Publishing or sharing text that may read as AI-generated; invoke /humanizer with pasted copy or ask to humanize directly.
What do I get? / Deliverables
You get the same ideas expressed in tighter, more natural language aligned to human editorial standards.
- Humanized rewrite of supplied text
- Pattern-aware edits (significance inflation, generic phrasing, etc.)
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Humanize hero and FAQ copy before running waitlist ads.
Soften README and setup guides that the agent drafted too grandiosely.
Tighten launch thread and Product Hunt blurb for a specific voice.
Rewrite onboarding and win-back emails that read like generic AI templates.
Humanize macro replies while keeping technical accuracy.
How it compares
Editorial cleanup skill—not a SEO keyword tool or full ghostwriting pipeline.
Common Questions / FAQ
Who is humanizer for?
Solo and indie builders using Claude Code (or compatible agents) who publish text and want it to pass a human sniff test.
When should I use humanizer?
Before Launch distribution posts, when polishing Grow lifecycle emails, when tightening Build docs or changelogs, and anytime Validate landing copy feels robotic.
Is humanizer safe to install?
It is a local SKILL.md with no required API keys—review the Security Audits panel on this page and avoid sending secrets inside text you paste for editing.
SKILL.md
READMESKILL.md - Humanizer
# Humanizer A Claude Code skill that removes signs of AI-generated writing from text, making it sound more natural and human. ## Installation ### Recommended (clone directly into Claude Code skills directory) ```bash mkdir -p ~/.claude/skills git clone https://github.com/blader/humanizer.git ~/.claude/skills/humanizer ``` ### Manual install/update (only the skill file) If you already have this repo cloned (or you downloaded `SKILL.md`), copy the skill file into Claude Code’s skills directory: ```bash mkdir -p ~/.claude/skills/humanizer cp SKILL.md ~/.claude/skills/humanizer/ ``` ## Usage In Claude Code, invoke the skill: ``` /humanizer [paste your text here] ``` Or ask Claude to humanize text directly: ``` Please humanize this text: [your text] ``` ## Overview Based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing) guide, maintained by WikiProject AI Cleanup. This comprehensive guide comes from observations of thousands of instances of AI-generated text. ### Key Insight from Wikipedia > "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." ## 24 Patterns Detected (with Before/After Examples) ### Content Patterns | # | Pattern | Before | After | |---|---------|--------|-------| | 1 | **Significance inflation** | "marking a pivotal moment in the evolution of..." | "was established in 1989 to collect regional statistics" | | 2 | **Notability name-dropping** | "cited in NYT, BBC, FT, and The Hindu" | "In a 2024 NYT interview, she argued..." | | 3 | **Superficial -ing analyses** | "symbolizing... reflecting... showcasing..." | Remove or expand with actual sources | | 4 | **Promotional language** | "nestled within the breathtaking region" | "is a town in the Gonder region" | | 5 | **Vague attributions** | "Experts believe it plays a crucial role" | "according to a 2019 survey by..." | | 6 | **Formulaic challenges** | "Despite challenges... continues to thrive" | Specific facts about actual challenges | ### Language Patterns | # | Pattern | Before | After | |---|---------|--------|-------| | 7 | **AI vocabulary** | "Additionally... testament... landscape... showcasing" | "also... remain common" | | 8 | **Copula avoidance** | "serves as... features... boasts" | "is... has" | | 9 | **Negative parallelisms** | "It's not just X, it's Y" | State the point directly | | 10 | **Rule of three** | "innovation, inspiration, and insights" | Use natural number of items | | 11 | **Synonym cycling** | "protagonist... main character... central figure... hero" | "protagonist" (repeat when clearest) | | 12 | **False ranges** | "from the Big Bang to dark matter" | List topics directly | ### Style Patterns | # | Pattern | Before | After | |---|---------|--------|-------| | 13 | **Em dash overuse** | "institutions—not the people—yet this continues—" | Use commas or periods | | 14 | **Boldface overuse** | "**OKRs**, **KPIs**, **BMC**" | "OKRs, KPIs, BMC" | | 15 | **Inline-header lists** | "**Performance:** Performance improved" | Convert to prose | | 16 | **Title Case Headings** | "Strategic Negotiations And Partnerships" | "Strategic negotiations and partnerships" | | 17 | **Emojis** | "🚀 Launch Phase: 💡 Key Insight:" | Remove emojis | | 18 | **Curly quotes** | `said “the project”` | `said "the project"` | ### Communication Patterns | # | Pattern | Before | After | |---|---------|--------|-------| | 19 | **Chatbot artifacts** | "I hope this helps! Let me know if..." | Remove entirely | | 20 | **Cutoff disclaimers** | "While details are limited in available sources..." | Find sources or remove | | 21 | **Sycophantic tone** | "Great question! You're absolutely right!" | Respond directly | ### Filler and Hedging | # | Pattern | Before | After | |---|---------|--------|-------| | 22 | **Filler phrases** | "In order to", "Due to the fact that" | "To", "Because" | |