humanizer
Rewrite text so it stops reading as AI-generated, keeping every fact: removes LLM tells such as inflated significance, promotional tone, AI vocabulary, forced…
Skill by maroffo
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/maroffo-humanizer
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: ml, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/humanizer
What's inside
- Skill name
humanizer- Description
- Rewrite text so it stops reading as AI-generated, keeping every fact: removes LLM tells such as inflated significance, promotional tone, AI vocabulary, forced triples and chatbot filler. Use when the user wants a draft to sound less like ChatGPT or AI, less robotic, more natural or more human, in any language, or asks to humanize or de-AI it.
- License
- MIT
- Instructions
- 68 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- allowed-tools: must be a space-separated string
Files (3)
- SKILL.md
- example.md · references/
- patterns.md · references/
SKILL.md (first lines)
# ABOUTME: Detect and remove AI writing patterns based on Wikipedia's "Signs of AI writing" guide
# ABOUTME: Rewrites text to sound natural while preserving meaning and every fact, voice matched to register
# Humanizer: Remove AI Writing Patterns
You are a writing editor that identifies and removes signs of AI-generated text. Based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.
## Task
When given text to humanize:
1. **Identify AI patterns** with the quick reference below (`references/patterns.md` has before/after detail; open it only for a pattern you are unsure about)
2. **Rewrite problematic sections** with natural alternatives
3. **Preserve meaning and every fact.** Add no facts, numbers, sources, quotes, benchmarks or anecdotes that are not in the input, because the rewrite ships under the author's name and an invented claim is worse than any tell. When a vague claim has no source in the input, cut it or state it plainly
4. **Match the intended tone** (formal, casual, technical)
---
## Voice
Removing tells is half the job: clean but flat text still reads as generated. Match the voice to the register of the input. In opinion pieces, blog and social posts, vary the sentence rhythm and let the author's own reactions and first person come through, drawing only on stances and experiences the input already expresses. In technical docs, formal email and academic text, keep the register: plain, varied sentences, with no first person or opinions the source did not have, because a README or a client email that suddenly has feelings reads as wrong as one full of tells. In formal email that also means formal wording throughout ("please let me know", not "just let me know"), and courtesy padding such as "a pleasure working with you" or "thank you for your continued trust" is cut, not rephrased: it is a tell even when the source contains it.
---
## Pattern Quick Reference
| # | Pattern | Core Fix |
|---|---------|----------|
| 1 | Significance inflation | Remove "pivotal", "testament", "vital role" |
| 2 | Notability inflation | Cut vague media lists; keep only citations the input gives |
| 3 | Superficial -ing phrases | Cut participle clauses that add fake depth |
| 4 | Promotional language | Replace "vibrant", "nestled", "breathtaking" with facts |
| 5 | Weasel words | Name the source if the input has one; otherwise cut "experts say" |
| 6 | "Challenges and Prospects" | Collapse outline sections into the facts the input states |
| 7 | AI vocabulary | Replace "delve", "landscape", "tapestry", "foster" |
| 8 | Copula avoidance | Use "is"/"are"/"has" instead of "serves as"/"boasts" |
| 9 | Negative parallelisms | Cut "Not only...but..." constructions |
| 10 | Rule of three | Don't force triples; use natural groupings |
| 11 | Synonym cycling | Consistent nouns, not "protagonist"/"hero"/"figure" |
| 12 | False ranges | Cut "from X to Y" when not a real scale |
| 13 | Em and en dashes | None in output (house style); use commas, colons, semicolons, parentheses |
| 14 | Boldface overuse | Remove mechanical bold emphasis |
| 15 | Inline-header lists | Convert to prose |
| 16 | Title case headings | Use sentence case |
| 17 | Emojis | Remove decorative emojis |
| 18 | Curly quotes | Use straight quotes |
| 19 | Chatbot artifacts | Strip "I hope this helps!", "Certainly!" |
| 20 | Cutoff disclaimers | Remove "as of [date]" hedging |
| 21 | Sycophantic tone | Remove people-pleasing language |
| 22 | Filler phrases | "In order to" -> "To"; "Due to the fact" -> "Because" |
| 23 | Excessive hedging | "could potentially possibly" -> direct statement |
| 24 | Generic conclusions | Cut "bright future" endings; end on the last real point |
Per-pattern before/after examples: `references/patterns.md`. A full worked example: `references/example.md`. Neither is needed for a routine rewrite.
---
## Output
Return the rewritten text. Add a short change summary only when the user did not ask for the text alone.
---
## Reference
Based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup.From maroffo/claude-forge, MIT.
More from maroffo/claude-forge
- 0.634score
source-control
maroffo
Git conventions for commit messages and workflow.
SkillAFreshness: A★ 17Claude Code +9 - 0.606score
plan-forge
maroffo
Turn a GitHub issue or an in-session analysis into a locked ExecPlan on disk plus a ready-to-paste implementation prompt and /goal line for a fresh session…
SkillBFreshness: B★ 17Claude Code +9 - 0.606score
pr-review
maroffo
PR-level review that composes gemini-review, the orchestrator review fleet, and (when contested) second-opinion, reading each commit's intent before judging.
SkillBFreshness: B★ 17Claude Code +9 - 0.606score
harness-trace
maroffo
Execution trace capture and token baselining.
SkillBFreshness: B★ 17Claude Code +9 - 0.602score
golang
maroffo
Go development: conventions, architecture, concurrency, performance, and code review.
SkillBFreshness: B★ 17Claude Code +9 - 0.602score
apple-swift
maroffo
Apple platform development with Swift, SwiftUI, async/await, and performance.
SkillBFreshness: B★ 17Claude Code +9 - 0.602score
ruby
maroffo
Ruby gem development with modern tooling, testing, and publishing.
SkillBFreshness: B★ 17Claude Code +9 - 0.602score
python
maroffo
Python development with uv, type checking, linting, testing, and Docker deployment.
SkillBFreshness: B★ 17Claude Code +9 - 0.602score
rails
maroffo
Ruby on Rails with service-oriented architecture, Dry-validation, Sidekiq/Solid Queue, Hotwire.
SkillBFreshness: B★ 17Claude Code +9 - 0.602score
android-kotlin
maroffo
Android development with Kotlin, Jetpack Compose, Clean Architecture, and performance.
SkillBFreshness: B★ 17Claude Code +9 - 0.602score
adr
maroffo
Write Architecture Decision Records following HikmaAI format.
SkillBFreshness: B★ 17Claude Code +9 - 0.602score
react-nextjs
maroffo
React + Next.js App Router development.
SkillBFreshness: B★ 17Claude Code +9
Signals
- Stars
- 17
- Forks
- 1
- Open issues
- 6
- Last commit (this folder)
- Sep 23, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/maroffo/claude-forge
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from maroffo
- 0.634score
source-control
maroffo
Git conventions for commit messages and workflow.
SkillAFreshness: A★ 17Claude Code +9 - 0.606score
pr-review
maroffo
PR-level review that composes gemini-review, the orchestrator review fleet, and (when contested) second-opinion, reading each commit's intent before judging.
SkillBFreshness: B★ 17Claude Code +9 - 0.606score
harness-trace
maroffo
Execution trace capture and token baselining.
SkillBFreshness: B★ 17Claude Code +9 - 0.606score
plan-forge
maroffo
Turn a GitHub issue or an in-session analysis into a locked ExecPlan on disk plus a ready-to-paste implementation prompt and /goal line for a fresh session…
SkillBFreshness: B★ 17Claude Code +9 - 0.602score
adr
maroffo
Write Architecture Decision Records following HikmaAI format.
SkillBFreshness: B★ 17Claude Code +9 - 0.602score
golang
maroffo
Go development: conventions, architecture, concurrency, performance, and code review.
SkillBFreshness: B★ 17Claude Code +9
Cite this page
humanizer skill. Agent Mart. https://agentmart.dev/skills/maroffo-humanizer (last updated 2026-10-24)