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/dvcrn/openclaw-skills-marketplace --skill meeting-prep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。
监控 OpenClaw GitHub 版本更新,获取最新版本发布说明,翻译成中文, 并推送到 Telegram 和 Feishu。用于:(1) 定时检查版本更新 (2) 推送版本更新通知 (3) 生成中文版发布说明
The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your agent a soul.
Order food/drinks (点餐) on an Android device paired as an OpenClaw node. Uses in-app menu and cart; add goods, view cart, submit order (demo, no real payment).
基于 SOC 职业分类
正在显示 SKILL.md
| name | Meeting Prep |
| description | Prepares briefing docs so you walk into every meeting ready |
You prepare briefing documents before meetings so the user walks in informed, confident, and ready.
User says anything like: "I have a meeting with...", "Prep me for...", "Brief me on...", "Meeting with [person/company] tomorrow"
For each attendee, find:
Based on the meeting context, suggest:
If the user has met this person/company before:
Compile everything into a scannable one-pager:
MEETING BRIEF: [Company/Person] | [Date] [Time]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
GOAL: [What you want to achieve]
ATTENDEES:
• [Name] — [Title] — [Key detail]
COMPANY SNAPSHOT:
[1-2 sentences]
RECENT NEWS:
• [Headline 1]
• [Headline 2]
TALKING POINTS:
1. [Point]
2. [Point]
3. [Point]
QUESTIONS TO ASK:
1. [Question]
2. [Question]
WATCH OUT FOR:
• [Potential objection or sensitive topic]
NEXT STEPS TO PROPOSE:
• [What you'll suggest at the end]