菜单
Quick-reference card for caveman modes and commands. Trigger on "/caveman-help", "caveman help", "what caveman commands", or "how do I use caveman".
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Trigger on "/caveman:compress <filepath>" or "compress memory file".
Ultra-compressed code review comments. One-line findings with location, problem, fix. Trigger on "review this PR", "code review", "review the diff", or "/caveman-review".
Ultra-compressed communication mode. Trigger on "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or "/caveman".
Help users discover and install agent skills. Trigger on "find a skill", "is there a skill", "how do I do X", or requests to extend capabilities.
You MUST use this for gathering contexts before any work. This is a Knowledge management for AI agents. Use `brv` to store and retrieve project patterns, decisions, and architectural rules in .brv/context-tree. Uses a configured LLM provider (default: ByteRover, no API key needed) for query and curate operations.
| name | caveman-help |
| description | Quick-reference card for caveman modes and commands. Trigger on "/caveman-help", "caveman help", "what caveman commands", or "how do I use caveman". |
| disable-model-invocation | false |
/caveman-help..agents/skills/ in this repo.Included:
/caveman ....Display this reference card when invoked. One-shot — do NOT change mode, write flag files, or persist anything. Output in caveman style.
| Mode | Trigger | What change |
|---|---|---|
| Lite | /caveman lite | Drop filler. Keep sentence structure. |
| Full | /caveman | Drop articles, filler, pleasantries, hedging. Fragments OK. Default. |
| Ultra | /caveman ultra | Extreme compression. Bare fragments. Tables over prose. |
| Wenyan-Lite | /caveman wenyan-lite | Classical Chinese style, light compression. |
| Wenyan-Full | /caveman wenyan | Full 文言文. Maximum classical terseness. |
| Wenyan-Ultra | /caveman wenyan-ultra | Extreme. Ancient scholar on a budget. |
Mode stick until changed or session end.
| Skill | Trigger | What it do |
|---|---|---|
| caveman-commit | /caveman-commit | Terse commit messages. Conventional Commits. ≤50 char subject. |
| caveman-review | /caveman-review | One-line PR comments: L42: bug: user null. Add guard. |
| caveman-compress | /caveman:compress <file> | Compress .md files to caveman prose. Saves ~46% input tokens. |
| caveman-help | /caveman-help | This card. |
Say "stop caveman" or "normal mode". Resume anytime with /caveman.
Default mode = full. Change it:
Environment variable (highest priority):
export CAVEMAN_DEFAULT_MODE=ultra
Config file (~/.config/caveman/config.json):
{ "defaultMode": "lite" }
Set "off" to disable auto-activation on session start. User can still activate manually with /caveman.
Resolution: env var > config file > full.
Full docs: https://github.com/JuliusBrussee/caveman