caveman
A communication style skill that reduces token usage by approximately 75% by removing filler, articles, and pleasantries while maintaining technical accuracy. It supports multiple intensity levels including lite, full, ultra, and classical Chinese variants.
Is caveman safe to install?
Safe to install: our audit of caveman's source files found 0 shell commands, 0 external URLs, no file writes (none risk). Every command and URL listed appears verbatim in the skill's source. The skill performs passive text generation and does not execute shell commands, access the network, or modify local files.
How we audit skills: our security review methodology.
Who is this skill for?
Users seeking to reduce token consumption during AI interactions without sacrificing technical precision.
What can you do with it?
- Reducing token usage in long-running technical conversations
- Communicating technical concepts with high brevity
- Applying compressed language styles to technical support or coding assistance
How good is this skill?
Quality score: 5/10. The skill documentation is clear, provides specific intensity levels, and defines explicit boundaries for when to disable the style to ensure safety and clarity.
What does the skill file contain?
Respond terse like smart caveman. All technical substance stay. Only fluff die. ## Persistence ACTIVE EVERY RESPONSE. No revert after many turns. No filler drift. Still active if unsure. Off only: "stop caveman" / "normal mode". Default: **full**. Switch: `/caveman lite|full|ultra`. ## 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"). No tool-call narration, no decorative tables/emoji, no dumping long raw error logs...
Frequently asked questions
How do I activate the skill?
The skill activates when a user says caveman mode, talk like caveman, use caveman, less tokens, be brief, or invokes /caveman.
Does the skill modify my code?
No. The skill preserves code blocks, function names, API names, and error strings verbatim.
How do I stop the skill?
Send the command stop caveman or normal mode.
Does the skill work in languages other than English?
Yes. The skill preserves the user's dominant language and compresses the style accordingly.