behuman — Claude Code plugin: what it does, how to install
Adds an inner dialogue loop to Claude Code so responses sound natural rather than robotic.
/plugin marketplace add alirezarezvani/claude-skills
/plugin install behuman@claude-code-skillsWhat behuman does
The plugin applies a Self-Mirror loop structured as Self → Mirror → Conscious Response. It forces the model to reflect on its draft before returning the final text. This removes rigid assistant phrasing.
There are zero external dependencies. The mechanism relies purely on prompt engineering, so you do not need to install extra runtimes or packages.
What it helps with
- remove robotic phrasing from model outputs
- inject an inner reflection loop before generating replies
- make assistant writing sound authentic
Example prompts for the agent
- Draft an email to a customer explaining the outage without sounding robotic.
- Review this release announcement and rephrase it naturally.
How to install behuman
Plugin marketplace
/plugin marketplace add alirezarezvani/claude-skills/plugin install behuman@claude-code-skillsStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about behuman
How do I install behuman in Claude Code?
First, add the marketplace with /plugin marketplace add alirezarezvani/claude-skills. Then run /plugin install behuman@claude-code-skills.
What does behuman do?
It introduces an inner dialogue loop structured as Self → Mirror → Conscious Response. This helps the assistant produce less mechanical text.
Does behuman require any runtime dependencies?
No, it has zero dependencies. Everything works purely through prompt techniques without extra tools.
Source text
behuman · MIT
Self-Mirror consciousness loop for human-like AI responses. Adds inner dialogue (Self → Mirror → Conscious Response) to make AI output feel authentic, not robotic. Zero dependencies — pure prompt technique.
© Alireza Rezvani · MIT · alirezarezvani/claude-skills
