caveman
Respond terse like smart caveman. All technical substance stay. Only fluff die.
Overview
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.
Use Cases
Install Notes
# Review source first
open https://github.com/mxyhi/ok-skills/blob/main/caveman/SKILL.mdCopy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.
Security Notes
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.
Related Skills
internal comms
anthropics/skills
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project update
Find Skills
mxyhi/ok-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Diagnose
mxyhi/ok-skills
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
grill with docs
mxyhi/ok-skills
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
grill me
mxyhi/ok-skills
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Dogfood
mxyhi/ok-skills
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step