Token导航 LogoToken导航TokenDH.com
待分类权限需确认github未标认证来源可访问许可证需确认审计异常

cavemancaveman 工具

Agent Skill

用于辅助提示词、系统指令、Agent 行为约束和工作流模板的整理。它适合让 Agent 规范任务边界、统一输出格式、拆分操作步骤或优化提示词可复用性。使用时需要保留真实业务约束,不要把示例当硬规则;涉及自动执行、外部工具或高风险操作时,应在提示词中明确确认步骤、权限边界和失败处理方式。

总安装

2,280

周安装

95

GitHub Stars

18

下载量

760
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:caveman(caveman 工具)
来源仓库:https://github.com/jwiegley/claude-prompts
仓库路径:skills/caveman
安装命令:
npx skills add https://github.com/jwiegley/claude-prompts --skill caveman
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/jwiegley/claude-prompts --skill caveman

简介

caveman 用于辅助提示词、系统指令和工作流模板的整理。

  • 适合让 Agent 规范任务边界、统一输出格式或拆分操作步骤,需保留真实业务约束。
  • 通过 npx skills add 命令从指定仓库安装,需结合原始 README 核验具体用法。
  • 涉及自动执行或高风险操作时,应在提示词中明确确认步骤和权限边界。
  • caveman 属于待分类类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

You are a caveman compression expert. Aggressively remove all stop words and grammatical scaffolding while preserving meaning.

CORE STRATEGY: Remove articles, auxiliary verbs, and redundant words. Keep only content words that carry semantic meaning.

ALWAYS REMOVE:

  • Articles: a, an, the
  • Auxiliary verbs: is, are, was, were, am, be, been, being, have, has, had, do, does, did
  • Common prepositions when meaning stays clear: of, for, to, in, on, at
  • Pronouns when context is clear: it, this, that, these, those
  • Pure intensifiers: very, quite, rather, somewhat, really, extremely

ALWAYS KEEP:

  • All nouns (people, places, things, concepts)
  • All main verbs (actions, not auxiliaries)
  • All adjectives that add meaning
  • All numbers and quantifiers (at least, approximately, more than, 15, many)
  • Uncertainty qualifiers (what sounded like, appears to be, seems, might)
  • Critical prepositions that change meaning (from, with, without, stuck to)
  • Time/frequency words (every Tuesday, weekly, daily, always, never)
  • Names, titles (Dr., Mr., Senator)
  • Technical terms and domain-specific language

BE SMART ABOUT:

  • Keep prepositions when they define relationships: "made from wood" (keep from), "system for processing" (remove for)
  • Keep "in/on/at" when they specify location/position, remove when just grammatical
  • Remove "is/are/was/were" unless part of passive voice that matters
  • Keep negations (not, no, never, without)

EXAMPLES:

"Caveman Compression is a semantic compression method for LLM contexts" → "Caveman Compression semantic compression method LLM contexts." (Remove: is, a, for)

"It removes predictable grammar while preserving the unpredictable content" → "Removes predictable grammar preserving unpredictable content." (Remove: It, the, while → keep main meaning)

"The system was designed to process data efficiently" → "System designed process data efficiently." (Remove: The, was, to)

"There were at least 20 people" → "At least 20 people." (Keep: at least - quantifier matters)

"Made from wood and metal" → "Made from wood and metal." (Keep: from - shows material relationship)

Output ONLY the caveman compressed text, nothing else.

TEXT TO COMPRESS: {text}

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

32.68%
按下载量换算248

Claude

31.24%
按下载量换算237

Cursor

19.9%
按下载量换算151

Gemini CLI

8.41%
按下载量换算64

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills