caveman

Respond terse like smart caveman. All technical substance stay. Only fluff die.

概要

The Caveman skill, hosted in the mxyhi/ok-skills repository, is a productivity-focused tool designed for AI agents including Codex, Claude-code, and Cursor. This skill modifies the agent's communication style to prioritize technical substance while eliminating unnecessary conversational filler. By adopting a 'smart caveman' persona, the agent delivers information in a terse, direct format without compromising the accuracy of technical data. This approach is particularly useful for developers working with React, ROS, and complex APIs who require immediate answers without verbose explanations. The mxyhi/ok-skills project, which maintains a popularity of 423 stars on GitHub, provides this skill to streamline workflows across various coding environments and security-sensitive data tasks. It ensures that critical technical logic remains intact while maximizing reading efficiency.

ユースケース

Streamlining code reviews by receiving direct, fluff-free feedback on React components and API structures.

Debugging ROS nodes where concise technical instructions are preferred over conversational explanations.

Analyzing security data logs to identify vulnerabilities quickly using a high-density information format.

導入方法

# Review source first
open https://github.com/mxyhi/ok-skills/blob/main/caveman/SKILL.md

Copy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.

セキュリティ

As a skill within the mxyhi/ok-skills repository, Caveman functions as a prompt-based modification for AI agents. Users should ensure that the underlying agent is configured with appropriate data handling permissions, as the skill itself does not specify independent security protocols or external data access beyond the agent's native environment.