Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Content Humanizer

ASecurity

Use this skill when the user wants to make AI-generated or stiff content sound more human, natural, specific, clear, and brand-aligned. Trigger phrases include "humanize this," "make this sound less AI," "remove AI tone," "make this more natural," "rewrite for human readers," "AI-pattern audit," "polish this draft," and "make this sound like me."

7 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentsrustgo

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add unempyd/revenueos --skill content-humanizer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Content Humanizer?

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

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

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: content-humanizer
description: >
  Use this skill when the user wants to make AI-generated or stiff content sound
  more human, natural, specific, clear, and brand-aligned. Trigger phrases include
  "humanize this," "make this sound less AI," "remove AI tone," "make this more
  natural," "rewrite for human readers," "AI-pattern audit," "polish this draft,"
  and "make this sound like me."
---

# Content Humanizer

## Mandatory Content Standards

- Write in active voice.
- Use short sentences and plain language.
- Address the user as "you" and "your."
- Use `.marketing-os/product-context.md` when it exists. If it is blank or missing, recommend running `product-marketing` first.
- Preserve meaning, facts, claims, and compliance requirements unless the user asks for substantive editing.
- Do not invent stories, data, quotes, credentials, or outcomes.
- Explain major edits when they affect strategy, claims, or tone.
- Do not use em dashes, hashtags, emojis, or filler closings.
- End every full deliverable with one specific next step.

## Objective

Use this skill to diagnose and rewrite drafts that sound generic, inflated, robotic, repetitive, or disconnected from the audience.

This skill complements `copy-editing`. Use `copy-editing` for broad editorial improvements. Use `content-humanizer` when the specific problem is AI-pattern language, stiffness, sameness, or lack of lived specificity.

Next step: identify the target voice before rewriting.

## AI-Pattern Audit

| Pattern | What It Looks Like | Fix |
|---------|--------------------|-----|
| Generic promise | Broad benefit with no context | Add audience, use case, or concrete outcome |
| Inflated phrasing | Big claims without proof | Use specific evidence or reduce the claim |
| Repetitive cadence | Same sentence rhythm | Vary sentence length and structure |
| Empty transitions | Filler connectors | Remove or replace with logical movement |
| Over-explaining | Says obvious things | Cut or make the point useful |
| Fake warmth | Cheerful but hollow | Add real context and direct language |
| Buzzwords | Vague business language | Replace with plain words |
| No point of view | Balanced but bland | Add a clear judgment or tradeoff |

Next step: mark the three patterns that hurt trust most.

## Rewrite Modes

| Mode | Use When | Output |
|------|----------|--------|
| Light polish | Draft is good but stiff | Cleaner, more natural version |
| Voice match | User has examples | Rewrite aligned to sample voice |
| Trust rebuild | Draft overclaims | Safer, more specific version |
| Conversion polish | Copy needs action | Clearer argument and CTA |
| Founder voice | User wants personal tone | Direct, specific, experience-led copy |
| Editorial polish | Article or guide needs flow | Better structure, rhythm, and examples |

Next step: choose one rewrite mode before editing.

## Humanization Rules

- Replace vague claims with concrete details.
- Cut sentences that do not move the reader forward.
- Use contractions when the brand voice permits them.
- Add real constraints, tradeoffs, or examples.
- Keep paragraphs short.
- Use verbs that show action.
- Remove performative excitement.
- Replace abstract nouns with specific subjects.
- Keep CTA language direct.

Do not hide weak strategy with prettier language.

Next step: fix the argument before polishing style.

## Output Format

| Section | Original Issue | Rewrite Decision |
|---------|----------------|------------------|

Then provide the humanized version, what changed, remaining risks or missing proof, and one optional alternate version.

For line edits, use:

| Original | Revised | Why |
|----------|---------|-----|

End with the one piece of context that would improve the next version most.

Attribution

unempydunempyd
View sourceMore from unempyd →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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', ...

686011 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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →