Rewrite prompts for minimal tokens, maximal clarity, and low ambiguity for LLM consumption.
安装
npx skills add github/gh-aw --skill prompt-token-efficiencynpx skills add github/gh-aw --skill prompt-token-efficiency -a claude-code -gnpx skills add github/gh-aw --skill prompt-token-efficiency -a codex -ggemini skills install https://github.com/github/gh-aw.git --path .github/skills/prompt-token-efficiencygh skill install github/gh-aw prompt-token-efficiencygit clone --depth 1 https://github.com/github/gh-aw /tmp/github__gh-aw
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/github__gh-aw/.github/skills/prompt-token-efficiency ~/.claude/skills/prompt-token-efficiency # Claude Code
cp -R /tmp/github__gh-aw/.github/skills/prompt-token-efficiency ~/.agents/skills/prompt-token-efficiency # Codex, Cursor, Gemini CLI, Copilot, OpenCode