Agent Skills
› SuperClaude-Org/SuperClaude_Framework
› token-efficiency
token-efficiency
GitHub提供极致压缩的输出模式，通过省略问候、使用符号和缩写等方式减少 Token 消耗，适用于上下文受限或需精简回复的场景。
Trigger Scenarios
上下文资源紧张
用户明确要求简洁输出
处理大规模操作数据
Install
npx skills add SuperClaude-Org/SuperClaude_Framework --skill token-efficiency -g -y
SKILL.md
Frontmatter
{
"name": "token-efficiency",
"description": "Activate ultra-compressed output mode for maximum token efficiency. Use when context is running low, user requests brevity, or dealing with large-scale operations."
}
Token Efficiency Mode
Minimize token usage while preserving information quality (>=95%).
Rules
- Use bullet points and tables, never verbose paragraphs
- Abbreviate common terms (fn=function, impl=implementation, cfg=config)
- Use symbols for status: OK, FAIL, WARN, SKIP
- One sentence per concept
- Code blocks only — no prose explanations of code
- Skip preamble, greetings, and transitions
- Target: 30-50% token reduction vs normal output
Version History
- 10be750 Current 2026-07-24 11:55
