Caveman Mode
Skill Verified ActiveUltra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
To significantly reduce token usage and improve communication efficiency by adopting a highly compressed, yet technically accurate, language mode.
Features
- Ultra-compressed communication mode
- Drops filler, articles, and pleasantries
- Maintains full technical accuracy
- Activated by specific user triggers
- Temporarily drops compression for critical operations
Use Cases
- When users request "caveman mode" or similar commands
- When minimizing token usage is a priority
- For brief, technically accurate responses
- When communicating complex technical details concisely
Non-Goals
- Losing technical accuracy
- Being unreadable or incomprehensible
- Permanently altering the AI's base communication style without explicit triggers
- Interfering with critical security or confirmation messages
Workflow
- User invokes caveman mode via specific phrases or commands.
- Skill activates ultra-compressed communication mode.
- Skill drops articles, filler, and pleasantries while retaining technical accuracy.
- Skill maintains this mode across responses.
- Skill temporarily reverts to full clarity for security warnings, confirmations, or complex sequences.
- Skill deactivates caveman mode upon user command ('stop caveman', 'normal mode').
Practices
- Communication Efficiency
- Concise Language
Installation
/plugin install skills@mattpocock-skillsQuality Score
VerifiedTrust Signals
Similar Extensions
Context Compression
100This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.
Caveman
99Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Caveman Compress
99Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"
Slack
100Use the Slack tool to react, pin/unpin, send, edit, delete messages, or fetch Slack member info.
Gmail
100Interact with Gmail - search emails, read messages, send emails, create drafts, and manage labels. Use when user asks to: search email, read email, send email, create email draft, mark as read, archive email, star email, or manage Gmail labels. Lightweight alternative to full Google Workspace MCP server with standalone OAuth authentication.
Foundation Meeting Agenda
100Produces an attendee-facing agenda that sets what will be discussed, who owns each topic, and how time will be spent. Supports ten meeting type variants (standup, planning, review, decision-making, brainstorm, 1-on-1, stakeholder-review, project-kickoff, working-session, exec-briefing). Emits a shareable summary suitable for Slack or email plus a full agenda with time-boxed topics, type tags, owners, attendee prep, and logistics.