Repository inventory

blader/humanizer

Skills indexed from this repository, with install-style signals scoped to the repo.
1 skills8K GitHub stars0 weekly installsGitHubOwner profile

Overview

This skill removes signs of AI-generated writing to make text sound natural and human-written. It detects common AI patterns and rewrites problematic passages while preserving meaning and the author's intended voice. Use it when editing or reviewing draft copy that feels mechanical, promotional, or formulaic.

How this skill works

The skill scans text for a curated set of AI tells (e.g., inflated significance, promotional language, -ing clause padding, vague attributions, em dash overuse, rule-of-three lists, AI vocabulary, negative parallelisms, and excessive conjunctive phrases). It flags each pattern, rewrites flagged passages with natural alternatives, and preserves tone and intent. A final anti-AI pass lists remaining tells briefly and then revises the text to add voice, rhythm, and personality where appropriate.

When to use it

  • Editing blog posts, articles, or newsletters that read sterile or promotional
  • Polishing reports, white papers, or proposals to remove vague authority claims and formulaic sections
  • Preparing marketing copy so it sounds authentic rather than AI-generated
  • Reviewing user-facing documentation or help content for unnatural phrasing
  • Before publication when tone, credibility, and human voice matter

Best practices

  • Keep the author's intended tone and vocabulary; avoid replacing voice with a new one
  • Prioritize preserving facts and attributions—replace vague claims with specific sources when available
  • Vary sentence length and rhythm to introduce a human cadence
  • Remove AI tells first, then add modest personality or opinion where suitable
  • Run a final anti-AI check: list remaining tells, then make one cohesive pass to humanize

Example use cases

  • A product blog draft that overuses buzzwords and rule-of-three lists
  • Academic summaries that read like an AI-generated literature review and need clearer attribution
  • Press releases that feel like promotional copy and require a neutral factual tone
  • Internal reports padded with vague "expert" claims and inflated significance
  • Customer-facing FAQs that need friendlier, more conversational phrasing

FAQ

No. The goal is to preserve meaning and facts while adjusting phrasing, tone, and attribution to sound human. Any substantive factual edits are flagged for review.

Can it add humor or strong opinions?

Yes, but only if that fits the intended voice. The skill injects modest personality—short sentences, asides, or first-person comments—when appropriate and requested.

1 skills

More from this maintainer
Other repositories and skills published under the same GitHub owner.
Skills library
Jump back to the full directory or explore grouped topics.
Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational