- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add rohitg00/pro-workflow --skill token-efficiency -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add rohitg00/pro-workflow --skill token-efficiency -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add rohitg00/pro-workflow --skill token-efficiency -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add rohitg00/pro-workflow --skill token-efficiency -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/rohitg00/pro-workflow/tree/HEAD/skills/token-efficiency來自發布者
Reduce output token waste and prevent iteration cycles that consume context.
Use when:
These patterns waste 30-60% of output tokens:
Set explicit budgets by task complexity:
At the wrap-up threshold: commit progress, assess remaining work, decide whether to continue or start fresh.
For simple-to-medium tasks:
Switch profiles based on what you're doing:
Hard rules:
Use ASCII characters only in all output:
-- not — (em dash)" not " " (smart quotes)' not ' ' (curly apostrophes)This ensures clean copy-paste for code and compatibility with downstream systems.
Track these metrics to measure token savings:
Token efficiency patterns adapted from drona23/claude-token-efficient (MIT).
Reduce token waste by 40-60% through anti-sycophancy rules, tool-call budgets, one-pass coding, task profiles, and read-before-write enforcement. Inspired by drona23/claude-token-efficient.
---name: token-efficiencydescription: Reduce token waste by 40-60% through anti-sycophancy rules, tool-call budgets, one-pass coding, task profiles…---# skills/token-efficiency/SKILL.md常見問題
從發布者下載 skills/token-efficiency/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/rohitg00/pro-workflow。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。