SkillFoxx

Type a name, a task or a service

pohuy

ПОХУЙ

An agent voice mode using idiomatic Russian profanity while keeping technical precision, 18+

SkillMedium risk

smixs/pohuyAuthor: smixs

Install

claude plugin marketplace add smixs/pohuy && claude plugin install pohuy@pohuy

Enabled per session with /pohuy.

This is third-party code. Review the repository files before installing.

What it does

The skill switches the agent's tone to an engineer's colloquial speech with Russian profanity. Terms, code, commands and error strings stay unchanged, and code, commits, PRs and docs are written clean. There are three intensity levels, lite, full and ultra, and a ten-step scale that matches emotion to severity. In incidents and security warnings, facts and recovery steps stay literal.

Who it is for. For adult Russian-speaking developers who prefer an informal agent tone in chat.

Good fit when

  • You want an informal tone in personal agent work: debugging, reviews, logs
  • You want short emotional status updates instead of polite phrasing

Not a fit when

  • Shared sessions, screen recordings or client demos
  • You need public texts: articles, posts, documentation
  • You need token savings: the author admits it does not save tokens

Example request

/pohuy lite

Limitations

18+ content. The skill changes only communication style and does not improve solution quality. Installing the output style changes global Claude Code settings and adds a per-turn hook.

How to disable. Turn off in a session with /pohuy normal or the phrase normal mode. For the output style, choose /config, Output style, Default. For Codex, run install-codex.sh with --uninstall.

Security check

  • curl | bash install changes global agent settings and registers hooks
  • The skill compares SKILL.md with GitHub over the network once per session

README in short

Inspired by the caveman skill, the project describes an agent voice mode using Russian profanity. The README includes before and after examples, joke benchmarks, a level table and a project state scale. It installs as a Claude Code plugin, via npx skills, with a script for Codex CLI and as a Pi extension. It ships an idiom dictionary, reference scenes and usage rules.

FAQ

Will profanity leak into code and commits?

No, the skill rules keep code, commits, PRs and docs clean.

How do I make the mode permanent?

Install the output style with install.sh, which sets the Pohuy style in ~/.claude/settings.json and registers a hook.

Editors’ pick

A self-improving agent from Nous Research with a TUI, messaging gateway, cron jobs and skills it writes itself

CLIHigh risk245.5K
Editors’ pick

Anthropic's coding agent for the terminal, IDE and GitHub: understands your codebase, runs tasks and handles git

CLIHigh risk145K
Editors’ pick

OpenAI's coding agent that runs locally in your terminal, with IDE and desktop versions

CLIHigh risk124.1K
Editors’ pick

Google's open-source terminal agent on Gemini models: code work, shell, web search and MCP

CLIHigh risk107K