Be Human — AI skill for Claude Code
A Claude Code / agent skill that strips the tells of AI writing from any prose.
How to install Be Human
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Moh4696/be-human and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Be Human does
A Claude Code / agent skill that strips the tells of AI writing from any prose. Based on Wikipedia's Signs of AI writing.
Alternatives in AI
- Humanizer — A Claude Code skill that removes signs of AI-generated writing from text, making it sound more natural and hum 11.3k ★
- Academic Humanizer — Strip AI-writing tells from papers and grant proposals (NSF/NIH), while keeping scholarly voice and tying clai 1.1k ★
- DontFeedTheAI — Transparent anonymization proxy for AI-assisted pentesting 654 ★
README
be-human
A Claude Code / agent skill that strips the tells of AI writing from any prose.
It's a checklist you run against every draft before it ships: articles, threads, posts, emails, captions, summaries, anything meant to be read. It catches inflated significance, promotional tone, rule-of-three padding, formulaic transitions, editorializing, hollow attribution, structural rigidity, and formatting tics.
Based on Wikipedia's [Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:WikiProject_AI_Cleanup/AI_catchphrases) field guide (WikiProject AI Cleanup).
What's in the box
A single [`SKILL.md`](SKILL.md). That's the whole skill. When it's installed, your agent loads it automatically on writing tasks (via the `description` in the frontmatter) and applies the checklist.
Install
Skills live in a `skills/` directory that your agent reads on startup. Pick the scope you want.
For your whole machine (Claude Code)
Clone straight into your personal skills directory:
git clone https://github.com/Moh4696/be-human.git ~/.claude/skills/be-human
The file then sits at `~/.claude/skills/be-human/SKILL.md` and is available in every project.
For one project only
From the root of the project you want it in:
git clone https://github.com/Moh4696/be-human.git .claude/skills/be-human
Now it's scoped to that repo (and travels with it if you commit `.claude/skills/`).
Manual
If you'd rather not clone, create the folder and drop the file in:
mkdir -p ~/.claude/skills/be-human
curl -o ~/.claude/skills/be-human/SKILL.md \
https://raw.githubusercontent.com/Moh4696/be-human/main/SKILL.md
Other agents (Cursor, Windsurf, etc.)
The skill is plain Markdown, so it works anywhere that reads skill or rule files. Put `SKILL.md` wherever that tool expects its skills, or paste its contents into your rules/instructions file.
Verify it loaded
In Claude Code, run `/skills` (or start a new session and ask what skill
Related Skills
Slopbuster
Strips the AI tells out of prose, code, and academic writing. 152 patterns from real AI-vs-human analysis, two
AI Tells Validator
Detect and rewrite AI-sounding text. Grounded in the live Wikipedia 'Signs of AI writing' catalog.
Ultimate Humanizer
Claude Code skill that keeps AI writing tells out of your text, built on Wikipedia's Signs of AI writing guide
Humanizer: Remove AI Writing Patterns
You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more nat
Human Eyes
A Claude Code skill for auditing and rewriting prose that carries common AI-writing tells.
Strip AI Tells
Use when prose a human reads as writing sounds machine-written and needs an edit that fixes it rather than a r
Related Agents
AI Signal Reviewer
Reviews human-facing prose for AI writing signals and formatting traps. Use proactively before finalizing any
Guide Writer
(/auto, /meeting) Maintain research//guide.md as the human oversight entrypoint, reading durable node surfaces
Corp Doc Builder
A /corp DOCUMENT BUILDER on Opus at xhigh effort: writes the text a human signs and sends (document and docume