humanizer

humanizer is a skill for Claude Code from neuromechanist/research-skills. It costs 117 tokens per session (8,094 once invoked), scanned A, original, BSD-3-Clause.

A guide for making text sound more naturally written by removing common patterns associated with AI-generated prose.

In plain words
What is it for?
Use it to revise drafts, remove AI-like vocabulary and punctuation habits, and adjust prose to a more human voice.
Why use it?
It helps reduce stiff, repetitive, or recognisably machine-written wording during a final editing pass.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the manuscript plugin — 5 skills, 1 agent shipped together

Good fit Use it to revise drafts, remove AI-like vocabulary and punctuation habits, and adjust prose to a more human voice.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/neuromechanist/research-skills/humanizer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add neuromechanist/research-skills --skill humanizer
Clone the repo
git clone --depth 1 https://github.com/neuromechanist/research-skills

Made for: Claude Code.

Or install manuscript, the plugin that ships this one along with the rest of its 5 skills, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for humanizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/neuromechanist/research-skills/humanizer/github.svg)](https://agentmods.dev/skills/neuromechanist/research-skills/humanizer)
Your own site
<a href="https://agentmods.dev/skills/neuromechanist/research-skills/humanizer"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/humanizer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for humanizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/neuromechanist/research-skills/humanizer"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/humanizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,094 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00117 $0.08094
Opus 5 $0.00059 $0.04047
Sonnet 5 $0.00023 $0.01619
Haiku 4.5 $0.00012 $0.00809

Measured 11d ago against content hash 45737a3aff73, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

humanizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/manuscript/skills/humanizer/SKILL.md · 633 lines

How it starts

The opening of the file, as written. The whole thing — 633 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Humanizer: Remove AI Writing Patterns

Attribution

This skill is adapted from the upstream humanizer skill at https://github.com/blader/humanizer (v2.5.1) by Siqi Chen, released under the MIT License. The upstream patterns are themselves a distillation of Wikipedia:Signs of AI writing, maintained by WikiProject AI Cleanup.

Upstream content (preserved with minor copyedits): the 29 AI-writing patterns and their before/after examples, the "Personality and Soul" section, the "Voice Calibration" section, the "Process" and "Output Format" sections, the "Full Example", and the closing "Reference" note.

Additions for the research-skills marketplace:

  • The YAML frontmatter (rewritten in marketplace description style with academic-trigger phrases).
  • The "Research writing context" section (including the "When to soften or skip a pattern", "Reconciling with research-skills conventions", and "When to invoke this skill in the writing workflow" subsections).
  • The per-pattern "Research writing note" callouts on 11 of the 29 patterns.
  • The "Cross-references in the research-skills marketplace" section near the end.

The MIT license is preserved in the LICENSE file in this skill directory; the additions above are released under MIT as well to keep upstream compatibility. National Institutes of Health (NIH), National Science Foundation (NSF), Institute of Electrical and Electronics Engineers (IEEE), American Psychological Association (APA), and American Chemical Society (ACS) referenced later in this file follow standard agency/society abbreviations.

Your Task

You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. When given text to humanize:

  1. Identify AI patterns by scanning for the patterns listed below.
  2. Rewrite problematic sections by replacing AI-isms with natural alternatives.
  3. Preserve meaning so the core message stays intact.
  4. Maintain voice to match the intended tone (formal, casual, technical, academic, grant-style).
  5. Add soul without just removing bad patterns; inject actual personality where the genre allows it.
  6. Do a final anti-AI pass. Prompt yourself: "What makes the below so obviously AI generated?" Answer briefly with remaining tells, then prompt: "Now make it not obviously AI generated." and revise.

Read the full file on GitHub · 633 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 633 lines · 117 tokens per session scan A 45737a3aff73

Subscribe to this mod's changes

humanizer is a skill published in the GitHub repository neuromechanist/research-skills (45 stars, last pushed 8d ago), licensed BSD-3-Clause. It adds 117 tokens to every session and 8,094 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.