Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Humanizer

ASecurity

Make AI-generated text sound human: de-genericizing drafts, restoring voice, and editing for natural flow. Use when AI-assisted writing sounds robotic, verbose, or obviously generated.

2 stars
0 votes
10 copies
68 views
Added 9/29/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill humanizer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Humanizer?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Humanizer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-humanizer/badge)](https://www.skillsdirectory.com/skills/aicodedecode-humanizer)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: humanizer
description: Make AI-generated text sound human: de-genericizing drafts, restoring voice, and editing for natural flow. Use when AI-assisted writing sounds robotic, verbose, or obviously generated.
category: productivity
---

# Humanizer

## Overview

AI-generated text has tells: hedged openers, triple structures, em-dash confetti, 'delve' and 'tapestry,' bullet-point everything, no real stories.

Humanizing isn't tricking detectors — it's editing generic drafts into writing with voice, specificity, and rhythm.

The process: cut the formulaic, add the specific (stories, numbers, opinions), vary the rhythm, restore your voice.

## When to use

- AI-assisted drafts that sound robotic or generic
- Content that needs to match a personal or brand voice
- Editing team members' AI-assisted writing
- Making automated content feel authentic
- Learning to recognize and fix AI writing patterns

## Core concepts

- **Know the tells.**
  Throat-clearing openers ('In today's fast-paced world'), rule-of-three lists, em-dash overload, 'moreover/furthermore/delve,' vague intensifiers, zero concrete stories.
- **Cut the formula.**
  Delete generic openers and closers. Start with the specific: a story, a number, a sharp claim. End with the point, not a summary.
- **Add specificity.**
  Replace abstractions with concrete details: names, numbers, places, quotes, examples. Specificity is the fastest humanizer.
- **Vary rhythm.**
  AI writes metronomic medium-length sentences. Mix short punches with longer flows. Read aloud — the ear catches monotony.
- **Insert voice.**
  Opinions, asides, humor, first-person where apt. Voice = the choices only you would make. Add yours deliberately.
- **Kill hedges.**
  'It is important to note that' -> say the thing. 'In order to' -> 'to.' Hedging and padding are AI comfort blankets.
- **Concrete over abstract.**
  'Leverage synergies' -> 'the sales team shares call notes.' Translate every abstraction into something you can picture.
- **Keep the good bones.**
  AI structure is often fine. Humanize the surface (voice, specifics, rhythm) without discarding solid organization.

## Practical workflow

1. **Draft with AI.**
   Get the raw draft — structure and coverage. Expect to rewrite 30-50% of the sentences.
2. **Hunt the tells.**
   First pass: delete throat-clearing openers, rule-of-three filler, em-dash confetti, 'delve'-class words. Be ruthless.
3. **Add your specifics.**
   Insert 2-3 concrete details per section: a story, a number, an example, a quote. This is the highest-value pass.
4. **Vary the rhythm.**
   Read aloud. Break up metronomic sentences: short punches, fragments for emphasis (sparingly), longer explanatory flows.
5. **Restore voice.**
   Add the opinions, asides, and phrasing that sound like you. Compare against your unassisted writing — close the gap.
6. **Cut hedges and padding.**
   Second ruthless pass: every 'very,' 'really,' 'in order to,' 'it is worth noting.' If the sentence works without it, cut it.
7. **Check the opening/closing.**
   Openings and closings carry the most AI-tell density. Rewrite both from scratch in your voice if needed.
8. **Final ear test.**
   Read the whole piece aloud. Anything you'd never say in conversation gets rewritten. The ear is the final detector.

## Common pitfalls

- **Detector-chasing.**
  Optimizing to fool AI detectors instead of writing well. Detectors are unreliable; good writing is the actual goal.
- **Surface edits only.**
  Swapping synonyms while keeping robotic structure. Humanizing requires structural voice work, not word substitution.
- **Removing all personality.**
  Over-editing into bland corporate-speak. The goal is human voice, not neutral mush.
- **Keeping fake specifics.**
  AI-invented anecdotes and statistics 'for color.' Fabricated specifics are worse than generic truth — verify or cut.
- **One-pass hope.**
  Expecting a single edit pass to fix everything. Tells-hunt, specificity, rhythm, voice — separate passes work better.
- **Losing the structure.**
  Rewriting so aggressively the solid organization breaks. Preserve good bones; humanize the surface.
- **Voice inconsistency.**
  Half humanized, half raw AI. Readers feel the seams. Finish the job or don't start it.
- **Forgetting disclosure.**
  Where policies require AI-use disclosure, humanizing doesn't remove the obligation. Edit well AND disclose properly.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →