Reduce token usage by removing filler words while preserving technical accuracy.
npx skills add https://github.com/danievanzyl/code-skills --skill caveman-danievanzyl
Please help me install this Agent Skill. Skill: caveman Source: https://github.com/danievanzyl/code-skills/tree/main/skills/caveman Command: npx skills add https://github.com/danievanzyl/code-skills --skill caveman-danievanzyl
Ultra-compressed communication mode that cuts token usage by removing filler, articles, and pleasantries while preserving full technical accuracy.
Activate caveman mode and respond tersely with direct, technical statements.
High-intent search queries and answers about installing and using this skill.
Token minimization in AI prompting drops filler, articles, and pleasantries while preserving technical accuracy. This rule-based interaction mode strips unnecessary words to compress responses and save token costs.
Caveman mode is an ultra-compressed communication style that removes filler and unnecessary words to reduce token usage in technical chats. It keeps technical accuracy intact when brief responses are needed.
Activate terse mode by invoking caveman mode or asking for brevity. It implements persistent rule-based drop rules with optional exception handling, allowing you to resume normal mode when explicitly asked.
Dropping articles and filler words does not affect technical accuracy. The mode removes pleasantries while keeping the technical details intact, ensuring precise, direct statements for coding sessions.
Use token minimization when you need brevity or want to reduce token usage in coding sessions. It is ideal for terse, precise communication, dropping filler while keeping technical accuracy intact.
kevinnftReduce token usage by removing filler words from AI responses.
gbenckeCompress AI responses by removing filler while preserving technical accuracy.
RDCrystalLabCompress AI responses into terse modes while preserving technical accuracy.
ryancnelsonDelegate New Relic NRQL queries and monitoring tasks to a sub-agent.
