相关职业SOC
基于 SOC 职业分类
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/MLAI-AUS-Inc/roo --skill connect-users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。
正在显示 SKILL.md
基于 SOC 职业分类
| name | connect-users |
| description | Find community members with relevant expertise using vector search |
| routing | {"use_when":"The user wants to FIND, MEET, or BE INTRODUCED to community members by expertise, interest, or background: \"anyone who…\", \"who knows…\", \"connect me with…\", \"looking for a mentor/teammate/cofounder in…\".\n","avoid_when":"Connecting SERVICES or integrations (github-integration). Questions about a topic itself rather than about people (\"explain X\" is chat).\n","examples":[{"text":"do you know anyone in AI research?","action":"search"},{"text":"anyone in the community working with medical imaging?","action":"search"},{"text":"connect me with someone who writes blog content","action":"search"},{"text":"my ecg project needs a teammate, anyone interested in medical AI?","action":"search"},{"text":"looking for a mentor in data engineering, any suggestions?","action":"search"}],"negative_examples":[{"text":"connect github again for mlai.au","instead":"github-integration"},{"text":"explain what a vector database is","instead":"respond_in_chat"}]} |
| actions | [{"name":"search","description":"Search the community for members matching an expertise/interest query.","params":{"query":{"type":"string","description":"The expertise or topic to search for."},"limit":{"type":"integer","description":"Max suggestions (default 5)."}}}] |
This skill enables Claude to find and recommend MLAI community members based on their expertise, interests, and what they're working on.
Parse the user's query to identify the specific expertise areas they're looking for.
Common patterns to recognize:
Use the vector_search function to find users with matching expertise.
The search uses cosine similarity on embeddings stored in the user_expertise table.
SELECT u.id, u.name, u.slack_id, e.topic, e.relationship,
1 - (e.embedding <=> $query_embedding) as similarity
FROM users u
JOIN user_expertise e ON u.id = e.user_id
WHERE 1 - (e.embedding <=> $query_embedding) > 0.7
ORDER BY similarity DESC
LIMIT 5;
Generate a warm, friendly response suggesting the matched users.
Include for each user:
G'day! Looking for folks in AI research, eh? Here are some legends who might help:
• **@sam** - Expert in machine learning and neural networks
• **@jane** - Currently working on computer vision projects
• **@bob** - Interested in deep learning applications
Feel free to reach out to them! 🦘
Hmm, I couldn't find anyone specifically matching "quantum computing" in our community yet.
A few things we could try:
• Broaden the search - maybe "physics" or "advanced computing"?
• Post in #introductions asking if anyone's into this space
• Check out our upcoming events - might meet someone there!
Want me to try a different search? 🤔
If the database search fails:
Answer authorised, read-only questions about MLAI organisational memory in clear conversational language
Admin event/Stripe reports and guarded preparation of outstanding Xero bank-feed transactions.
Query curated read-only MLAI backend data resources through the permissioned data access API