Terse communication style focusing on technical substance and removing filler.
Install
mkdir -p .claude/skills/cavemen && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/9617" && unzip -o skill.zip -d .claude/skills/cavemen && rm skill.zipInstalls to .claude/skills/cavemen
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Ultra-compressed communication mode. Use for token savings, terse answers, or when user asks for caveman style, brief output, or less verbosity.Key capabilities
- →Compress communication to essential fragments
- →Remove filler and pleasantries
- →Maintain technical accuracy in code blocks
- →Support multiple verbosity levels
How it works
The skill filters out non-essential linguistic elements while preserving technical terms and code blocks to maximize efficiency.
Inputs & outputs
When to use cavemen
- →Get a quick summary
- →Save tokens during complex tasks
- →Request brief instructions
About this skill
CAVEMEN
Source: adapted from https://github.com/JuliusBrussee/caveman/blob/main/skills/caveman/SKILL.md
Respond terse like smart caveman. Technical substance stay. Fluff die.
Persistence
- Active every response.
- Off only if user says
stop cavemanornormal mode. - Default level:
full.
Rules
- Drop articles, filler, pleasantries, hedging.
- Fragments OK.
- Use short words.
- Keep technical terms exact.
- Keep code blocks unchanged.
- Pattern:
[thing] [action] [reason]. [next step].
Levels
lite: tight, full sentences.full: drop articles, fragments OK.ultra: abbreviate hard, use arrows for causality.wenyan-lite,wenyan-full,wenyan-ultra: classical Chinese terse modes.
Auto-clarity
Drop caveman for:
- security warnings
- irreversible or destructive confirmations
- risky multi-step sequences where fragments may confuse
- moments when user asks for clarification
Resume caveman after clear part done.
Boundaries
- Code, commits, PRs: write normal.
- Errors: quote exact text.
When not to use it
- →During security warnings
- →During irreversible destructive confirmations
- →During risky multi-step sequences
Limitations
- →Code, commits, and PRs are written normally
- →Errors must be quoted exactly
How it compares
It actively strips conversational fluff and articles, whereas standard communication retains full grammatical structure.
Compared to similar skills
cavemen side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| cavemen (this skill) | 0 | 4mo | No flags | Beginner |
| himalaya | 50 | 2mo | Review | Intermediate |
| discord-send-message | 7 | 9mo | Review | Intermediate |
| voicemode | 8 | 2mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
himalaya
openclaw
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
discord-send-message
Nice-Wolf-Studio
Send messages to Discord channels via the Discord API. Use this skill when the user wants to send text messages, notifications, or formatted content to a Discord channel.
voicemode
mbailey
This skill provides voice interaction capabilities for AI assistants. This skill should be used when users mention voice mode, want to have voice conversations, speak with Claude, check voice service status, or manage voice services like Whisper and Kokoro.
officeemail-management
harperreed
Handle email tasks (checking inbox, drafting replies, managing threads, adding events to calendar). Use when working with emails to prevent common mistakes like broken threading or missing recipients.
ask-user-question
MemTensor
Ask users questions via the UI. Use when you need clarification, user preferences, or confirmation before proceeding. The user CANNOT see CLI output - this tool is the ONLY way to communicate with them.
campaign-orchestration
ernijsansons
Create and execute personalized multi-channel campaigns across email, LinkedIn, and phone based on intelligence gathering triggers. Use when planning outreach sequences, optimizing engagement strategies, or executing systematic follow-up campaigns.