pohuy skill
ПОХУЙ
An agent voice mode using idiomatic Russian profanity while keeping technical precision, 18+
- 1,433 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- curl | bash install changes global agent settings and registers hooks
- The skill compares SKILL.md with GitHub over the network once per session
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/pohuyDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- curl | bash install changes global agent settings and registers hooks
- The skill compares SKILL.md with GitHub over the network once per session
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 liteLimitations
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.
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.
Discussion
No questions or reviews yet.
Related
SkillsA skill for coding agents that pushes them to finish the job: keep trying after failures, switch approaches and prove the result
A multi-agent harness that verifies results by artifacts: stop hooks, an independent judge and an event log for Claude Code, Codex, Cursor and more
A skill that cuts an agent's prose output, plus a local proxy that compresses what the agent reads
A skill plus hooks that keep a coding agent on task and cut speculative defenses, unread checksums and scope creep
28 skills that remove instead of add: rewrite a document clean, check the read of a request, compress text and challenge a decision
A CLI that lets agents in different terminals message, watch and spawn each other
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.