菜单
Use when dispatching subagents with non-trivial prompts, writing system prompts or skill descriptions, or when any prompt feels vague — scores 7 quality dimensions, auto-selects from 11 techniques, and rewrites with before/after scores.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Vvkmnn/claude-orator-mcp --skill claude-orator命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | claude-orator |
| description | Use when dispatching subagents with non-trivial prompts, writing system prompts or skill descriptions, or when any prompt feels vague — scores 7 quality dimensions, auto-selects from 11 techniques, and rewrites with before/after scores. |
Make prompts measurably better before sending them.
Dispatching subagents → Run the prompt through orator_optimize first. Better prompt = less back-and-forth, more accurate results.
Writing system prompts → SKILL.md files, agent instructions, tool descriptions. Small improvements compound over many invocations.
Prompt feels vague or under-specified → Score it. Orator identifies weak dimensions and applies targeted techniques.
orator_optimize(prompt: "...", intent?: "code|analysis|creative|extraction|system", techniques?: ["xml-tags", "few-shot"])
Output: Before score → techniques applied → optimized prompt → after score.
Already good? One-line confirmation: 🪶 ━━ already well-structured (8.4)
Skip for trivial prompts, simple questions, or prompts already scoring above 7.0. The overhead isn't worth it for single-step instructions.
| Mistake | Fix |
|---|---|
| Optimizing everything | Focus on high-leverage: subagent prompts, system prompts |
| Ignoring the score delta | Close before/after scores mean the prompt was already good |
Not using techniques override | When you know which techniques apply, force them |