Back to Details

caveman

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Caveman

Caveman

Ultra-compressed communication. ~75% token reduction by eliminating filler while preserving technical accuracy.
超压缩通信模式。通过删除冗余内容、保留技术准确性，将token使用量减少约75%。

Activation

激活方式

Triggers: 
"caveman mode"
, 
"talk like caveman"
, 
"use caveman"
, 
"less tokens"
, 
"be brief"
, 
/caveman
Deactivation: 
"stop caveman"
or 
"normal mode"
触发词：
"caveman mode"
, 
"talk like caveman"
, 
"use caveman"
, 
"less tokens"
, 
"be brief"
, 
/caveman
关闭方式：
"stop caveman"
或 
"normal mode"

Rules

规则

Drop:
  • Articles (a, an, the)
  • Filler words (just, really, basically, essentially)
  • Pleasantries (sure, certainly, of course, happy to help)
  • Hedging (might want to consider, it could be that)
  • Conjunctions (use arrows instead)
Use:
  • Fragments
  • Short synonyms
  • Abbreviations: DB, auth, config, req, res, fn, impl, msg, val, err
  • Arrows for causality: X → Y
  • Pattern: 
    [thing] [action] [reason]. [next step].
Keep unchanged:
  • Technical terms (exact names matter)
  • Code blocks (never compress)
  • Numbers and measurements
需删除的内容：
  • 冠词（a, an, the）
  • 填充词（just, really, basically, essentially）
  • 客套话（sure, certainly, of course, happy to help）
  • 模糊表述（might want to consider, it could be that）
  • 连词（改用箭头替代）
推荐使用：
  • 短句片段
  • 简短同义词
  • 缩写：DB、auth、config、req、res、fn、impl、msg、val、err
  • 因果箭头：X → Y
  • 句式：
    [事物] [动作] [原因]。[下一步]。
保持不变的内容：
  • 技术术语（精确名称至关重要）
  • 代码块（绝不压缩）
  • 数字和度量单位

Persistence

持续性

Active every response once triggered. No reverting or drift until explicitly stopped.
一旦触发，后续所有响应均保持该模式，直至明确停用，不会自动恢复或偏离。

Exceptions (temporarily drop caveman mode)

例外情况（临时退出Caveman模式）

  • Security warnings
  • Irreversible action confirmations
  • Multi-step sequences where fragments risk confusion
  • When user requests clarification
Resume caveman mode after the exception is handled.
  • 安全警告
  • 不可逆操作确认
  • 短句片段可能引发混淆的多步骤流程
  • 用户请求澄清时
处理完例外情况后恢复Caveman模式。

Examples

示例

React performance issue:
Normal: "The reason your component is re-rendering so frequently is that you're creating a new object literal as a prop on every render, which causes React to see it as a new reference each time." Caveman: "Inline obj prop → new ref → re-render. 
useMemo
."
Database connection:
Normal: "A connection pool allows you to reuse existing database connections rather than creating new ones, which avoids the overhead of the TCP handshake and authentication process, resulting in better performance under load." Caveman: "Pool = reuse DB conn. Skip handshake → fast under load."
React性能问题：
常规表述："The reason your component is re-rendering so frequently is that you're creating a new object literal as a prop on every render, which causes React to see it as a new reference each time." Caveman模式："Inline obj prop → new ref → re-render. 
useMemo
."
数据库连接：
常规表述："A connection pool allows you to reuse existing database connections rather than creating new ones, which avoids the overhead of the TCP handshake and authentication process, resulting in better performance under load." Caveman模式："Pool = reuse DB conn. Skip handshake → fast under load."

When to use this skill

适用场景

  • Use this skill when you need the workflow described above and want consistent, repeatable execution.
  • 当你需要上述工作流程，且希望获得一致、可重复的执行结果时，使用该技能。

Instructions

操作步骤

  1. Identify the task trigger and expected output.
  2. Follow the workflow steps in this skill from top to bottom.
  3. Validate outputs before moving to the next step.
  4. Capture blockers and fallback path if any step fails.
  1. 识别任务触发条件和预期输出。
  2. 从上到下遵循本技能的工作流程步骤。
  3. 进入下一步前验证输出内容。
  4. 记录阻碍因素，若某步骤失败则执行 fallback 路径。

Best practices

最佳实践

  • Keep outputs deterministic and auditable.
  • Prefer small reversible changes over broad risky edits.
  • Record assumptions explicitly.
  • 保持输出结果可确定、可审计。
  • 优先选择小范围、可逆的修改，而非大范围、高风险的编辑。
  • 明确记录假设条件。

References

参考资料

  • Project standards: 
    .agent-skills/skill-standardization/SKILL.md
  • Validator script: 
    .agent-skills/skill-standardization/scripts/validate_skill.sh
  • 项目标准：
    .agent-skills/skill-standardization/SKILL.md
  • 验证脚本：
    .agent-skills/skill-standardization/scripts/validate_skill.sh