humanizer

Use when writing or editing text intended for other humans — READMEs, emails, Slack messages, commit messages, documentation, PR descriptions. Cleans AI-generated text patterns and applies context-appropriate tone.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "humanizer" with this command: npx skills add hjewkes/agent-skills/hjewkes-agent-skills-humanizer

Humanizer

Clean AI-generated text by normalizing characters, flagging overused phrases, and following context-appropriate writing guidelines.

Workflow

  1. Identify context — determine what you're writing: README, email, Slack message, commit message, or general documentation
  2. Load the guide — read the appropriate reference file (see table below)
  3. Write following the guide — apply tone, structure, and length guidelines as you draft
  4. Run the script — pipe final text through humanize for mechanical cleanup and phrase flagging
  5. Review flags — rewrite any flagged phrases naturally; don't just delete them, replace with plain language

Context Guides

ContextReferenceKey principle
READMEreferences/readme-guide.mdDirect and factual, show the command first
Emailreferences/email-guide.mdState the ask in the first sentence
Slackreferences/slack-guide.mdTerse — 1-2 sentences max
Commitreferences/commit-guide.mdImperative mood, explain why not what
GeneralApply common sense from all guidesPrefer clarity over formality

CLI Reference

CommandDescription
echo "text" | humanizeClean text via stdin
humanize file.mdClean text from file
humanize --report file.mdVerbose output with replacement counts
humanize --helpShow usage

Exit codes: 0 = clean, 1 = error, 2 = phrase flags found (text still cleaned)

What the Script Fixes Automatically

  • Em dashes → space-hyphen-space
  • Smart quotes → straight quotes
  • Unicode ellipsis → three periods
  • Non-breaking/invisible spaces → regular spaces
  • Invisible Unicode watermark characters → removed
  • Bullet characters → ASCII hyphens

What Gets Flagged (Not Auto-Fixed)

The script flags phrases that need human judgment to rewrite:

  • Red-flag words: delve, tapestry, seamless, robust, comprehensive, etc.
  • Hedging filler: "it's important to note", "it's worth noting"
  • Cliche openers/closers: "I hope this finds you well", "feel free to reach out"
  • Overused transitions: furthermore, moreover, additionally

Full pattern list: references/phrases.txt

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

humanizer

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

self-improve

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

skills-management

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

agent-browser

No summary provided by upstream source.

Repository SourceNeeds Review