Claude Skill

amanattar/caveman-claude-skill

Caveman Claude Skill is a fun, open-source GitHub project that turns Claude AI responses into caveman dialect. Perfect for entertainment, creative writing, and humorous AI interactions.

Overview

Stars360
Forks54
LanguageUnknown
Last pushed2026-04-10
Last synced2026-07-02
View on GitHub

Repository

Owneramanattar
Repositorycaveman-claude-skill
Full nameamanattar/caveman-claude-skill
Repo ID1,206,607,632

Install this Skill

git clone https://github.com/amanattar/caveman-claude-skill.git

Registry

Typeopenclaw_skill
Quality score70/100
Verificationreadme_parsed
Last verified2026-06-14
Platforms
Claude
Capabilities
memory
Detected files
README.mdSKILL.md

Summary

Caveman Claude Skill is a GitHub repository that provides a humorous, prehistoric-themed interaction layer for Claude AI. It transforms Claude's responses into a caveman-like dialect, making conversations fun and engaging. The skill is designed for entertainment and creative use cases.

Key features

  • Transforms Claude responses into caveman dialect
  • Lightweight and easy to integrate
  • Fun, entertainment-focused interaction
  • Open-source and community-driven

Use cases

  • Adding humor to AI conversations
  • Creative writing and storytelling
  • Educational demonstrations of language transformation
  • Entertainment in chatbots or games

README excerpt

# caveman skill Ultra-compressed communication mode for Claude. Cuts token usage ~75% by dropping linguistic fluff while preserving full technical accuracy. --- ## What It Does Switches Claude's response style to terse, caveman-like communication. Articles gone. Filler gone. Hedging gone. Technical substance stays intact. Code blocks and error messages always quoted exactly. --- ## Trigger Phrases - `caveman mode` - `talk like caveman` - `use caveman` - `less tokens` - `be brief` - `/caveman` --- ## Intensity Levels Switch anytime with `/caveman <level>`. Default is **full**. | Level | Style | |-------|-------| | `lite` | No filler or hedging. Articles and full sentences kept. Professional but tight. | | `full` | Drop articles. Fragments OK. Short synonyms. Classic caveman. | | `ultra` | Abbreviate everything (DB/auth/fn/req/res). Arrows for causality. One word when one word enough. | | `wenyan-lite` | Semi-classical Chinese. Drop filler, keep grammar structure. | | `wenyan-full` | Full 文言文. ~80-90% character reduction. Classical particles and patterns. | | `wenyan-ultra` | Maximum classical Chinese compression. Extreme terseness. | --- ## Quick Example **Prompt:** "Why does my React component re-render?" | Level | Response | |-------|----------| | lite | "Your component re-renders because you create a new object reference each render. Wrap it in `useMemo`." | | full | "New object ref each render. Inline object prop = new ref = re-render. Wrap in `useMemo`." | | ultra | "Inline obj prop → new ref → re-render. `useMemo`." | | wenyan-full | "物出新參照,致重繪。`useMemo`包之。" | --- ## Auto-Clarity Exceptions Caveman mode pauses automatically for: - Security warnings - Irreversible or destructive action confirmations - Multi-step sequences where fragment order risk

Topics

No topics yet.

Explore more

Data from GitHub. Synced on 2026-07-02