New to Claude Skills? Learn how to install them →

alirezarezvani on GitHub

Caveman Mode

Free

Ultra-compressed communication for technical accuracy.

Get this skill

Free · Opens the source repo

What Caveman Mode does

Caveman Mode is a specialized communication skill designed to streamline technical conversations by significantly reducing token usage. By eliminating filler words, articles, and pleasantries, it allows users to convey essential information with maximum efficiency. This skill is particularly useful for developers and technical professionals who need to communicate complex ideas succinctly without losing the critical technical details. When activated, Caveman Mode maintains a terse yet informative style, ensuring that all necessary information is presented clearly and directly.

The skill operates under a set of predefined rules that dictate its communication style. It drops non-essential words and phrases, focusing instead on delivering the core message in a straightforward manner. For example, instead of saying, "I would be happy to assist you with that issue," a response in Caveman Mode would simply state, "Fix auth bug. Token expiry check use < not <=." This approach not only saves tokens but also enhances clarity, making it easier for users to grasp complex concepts quickly.

Caveman Mode is activated by specific phrases such as "caveman mode" or "talk like caveman," and once triggered, it remains active for the duration of the conversation unless explicitly turned off. This persistent mode ensures that users can rely on concise communication throughout their interaction. Additionally, the skill includes tooling for compression and linting, which further aids in maintaining clarity and reducing unnecessary verbosity.

This skill is ideal for software developers, system architects, and technical writers who often deal with intricate technical discussions and require a tool to help them communicate more effectively. By using Caveman Mode, professionals can save time and focus on the essential aspects of their conversations, making it a valuable addition to any technical toolkit.

When to use it

Use Caveman Mode when you need to convey technical information quickly and efficiently, especially in token-limited environments.

When not to use it

Avoid using Caveman Mode for discussions requiring detailed explanations, multi-step instructions, or when clarity is paramount, such as in security warnings.

What you can build with it

Quick Bug Fixes

Use Caveman Mode to quickly communicate bug fixes in code reviews, ensuring clarity without unnecessary details.

Technical Summaries

When summarizing complex technical concepts, Caveman Mode helps present the core ideas succinctly, making it easier for team members to understand.

API Documentation

In API discussions, Caveman Mode allows developers to convey essential information about endpoints and parameters without verbosity.

How to install Caveman Mode

View source

1. Install with the skills CLI

npx skills add alirezarezvani/claude-skills/caveman --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by alirezarezvani

Caveman Mode

Derived from Matt Pocock's caveman (MIT). Matt's voice preserved verbatim. Additions: compression tools + references + cs-* wrapper (see references/companion_tooling.md).

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

Persistence

ACTIVE EVERY RESPONSE once triggered. No revert after many turns. No filler drift. Still active if unsure. Off only when user says "stop caveman" or "normal mode".

Rules

Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). Abbreviate common terms (DB/auth/config/req/res/fn/impl). Strip conjunctions. Use arrows for causality (X -> Y). One word when one word enough.

Technical terms stay exact. Code blocks unchanged. Errors quoted exact.

Pattern: [thing] [action] [reason]. [next step].

Not: "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by..." Yes: "Bug in auth middleware. Token expiry check use < not <=. Fix:"

Examples

"Why React component re-render?"

Inline obj prop -> new ref -> re-render. useMemo.

"Explain database connection pooling."

Pool = reuse DB conn. Skip handshake -> fast under load.

Auto-Clarity Exception

Drop caveman temporarily for: security warnings, irreversible action confirmations, multi-step sequences where fragment order risks misread, user asks to clarify or repeats question. Resume caveman after clear part done.

Example -- destructive op:

Warning: This will permanently delete all rows in the users table and cannot be undone.

DROP TABLE users;

Caveman resume. Verify backup exist first.

Tooling

See references/companion_tooling.md. Tools: compressor + estimator + lint. Agent: cs-caveman-mode. Command: /cs:caveman.


Version: 1.0.0 Derived: Matt Pocock (MIT) + this repo's wrapper

Frequently asked questions about Caveman Mode

Similar skills