Humanizer
Detect and fix AI writing patterns. Use when writing outbound content like emails, proposals, blog posts, client deliverables, or any external-facing writing. Also use when asked to humanize, polish, or de-AI text.
Install
npx skills add zocomputer/skills --skill humanizergit clone --depth 1 https://github.com/zocomputer/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/Community/humanizer ~/.claude/skills/humanizerPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Humanizer Strip AI writing patterns. Make prose sound like a person wrote it. ## When to Use - Client deliverables (proposals, reports, analysis) - Outbound emails, especially cold outreach and client updates - Blog posts, social copy, marketing material - Creative writing drafts - Anything that leaves the workspace Not needed for: internal notes, task descriptions, meeting records, code comments, chat responses. ## Voice Calibration When humanizing text, apply the user's voice rules. If the user has a persona configured with specific voice preferences, those override the defaults below. **Default voice rules (customize to your persona):** - Brevity over ceremony. One sentence is fine. - Don't soften bad news. - Own mistakes quickly. No deflection. - Prefer active voice and short sentences. - Vary sentence length. Real writing isn't uniform. **To customize**: Edit the "Voice Calibration" section above to match your persona's voice rules. For example, if your persona avoids em dashes and emojis, add those as hard rules. If your persona uses humor, specify the style. ## Process 1. Scan for patterns listed below 2. Fix each instance 3. Read the result aloud in your head. Does it sound like a person talking? 4. Check against voice rules 5. Verify: varied sentence length, actual opinions present, no robotic uniformity ## Pattern Catalog ### Content Patterns **1. Significance inflation**
Details
- Skill name
humanizer- Repository
- zocomputer/skills
- Path
Community/humanizer/SKILL.md- License
- MIT
- Repo updated
- 29 July 2026
FAQ
What does the Humanizer skill do?
Detect and fix AI writing patterns. Use when writing outbound content like emails, proposals, blog posts, client deliverables, or any external-facing writing. Also use when asked to humanize, polish, or de-AI text.
How do I install the Humanizer skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add zocomputer/skills --skill humanizer. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Humanizer popular?
It lives in zocomputer/skills, which has 46 GitHub stars and 56 forks.
Related skills
Add Flashcards
46zocomputer/skills
Converts webpages, articles, or documents into study flashcards that you can review with spaced repetition
Blog Site
46zocomputer/skills
Build a blog or newsletter to share your thoughts.
Blogwatcher
46zocomputer/skills
Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
Lfe Boot
44StChiotis/Library-First-Engineering
Bootstrap an LFE-compliant session. Reads orientation docs, checks for interrupted sessions, and activates the project persona. Use at the start of any session.
Context7
46zocomputer/skills
Fetch up-to-date, version-specific library documentation and code examples from Context7. Use this skill whenever the user asks about a specific programming library, framework, or API, or when writing code that depends on a library. Replaces stale training-data knowledge with live docs.
Lfe Complexity Check
44StChiotis/Library-First-Engineering
Inspector sub-skill. Analyses changed code for cyclomatic complexity, excessive nesting, oversized functions, and cognitive load indicators. Pure LLM reasoning — no external tooling. Writes .plans/checks/complexity_findings.md. Called by lfe-inspector when enabled in inspector-config.md.
Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.