菜单
Drafts personalized follow-up emails and messages based on Evergreen CRM contact history, past interactions, and pending actions. Use when you need to write a follow-up email, thank-you note, check-in message, or any outreach to an existing contact.
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。
基于 SOC 职业分类
Parses recent Gmail activity and logs interaction summaries to Evergreen CRM contacts — without storing full email bodies. Use when you want to sync email activity to your CRM, update interaction history, or keep Evergreen current with your communications. Requires Gmail connected in Claude.
Parses unstructured text (email signatures, business cards, LinkedIn profiles, meeting notes) into structured Evergreen CRM contacts. Use when adding new contacts from raw text, importing contacts from emails or messages, or batch-creating contacts from event notes.
Researches and enriches Evergreen CRM contacts with publicly available information — LinkedIn details, company info, recent news, and shared context. Use when a contact has sparse details, before an important meeting, or when batch-updating stale records.
Generates a narrative summary of everything known about a contact in Evergreen CRM — how you met, what you've discussed, mutual connections, and pending threads. Use when you need to quickly refresh your memory before reaching out, replying, or meeting someone.
Batch-processes contacts from a conference, dinner, or networking event into Evergreen CRM — creates records, tags them by event, and drafts personalized follow-up messages. Use after any event where you met multiple new people.
Generates a prioritized follow-up list from Evergreen CRM based on overdue actions, stale contacts, and interaction cadences. Use when planning your week, checking who needs attention, or building a daily outreach list.
| name | drafting-evergreen-follow-ups |
| description | Drafts personalized follow-up emails and messages based on Evergreen CRM contact history, past interactions, and pending actions. Use when you need to write a follow-up email, thank-you note, check-in message, or any outreach to an existing contact. |
Works with Evergreen, a local-first personal CRM for macOS. Get it on the Mac App Store.
get_contact for full profileinteractions.list for conversation historyactions.list for any commitmentsget_contact_network for shared connections contextinteractions.logactions.complete| Type | Tone | Key Elements |
|---|---|---|
| Post-meeting recap | Professional, warm | Key takeaways, action items, next steps |
| Thank-you note | Grateful, specific | What you're thankful for, why it mattered |
| Check-in | Casual, genuine | Reference last conversation, ask about their work |
| Introduction follow-up | Enthusiastic, brief | Reference who introduced you, what excited you |
| Congratulations | Warm, sincere | Specific achievement, genuine reaction |
| Re-engagement | Low-pressure, curious | Shared memory, open-ended question |
Context from Evergreen:
Contact: Sarah Chen (CTO, Meridian Health)
Last interaction: Meeting on Mar 20 — "Discussed API integration possibilities"
Pending action: "Send API documentation" (due Apr 2)
Notes: "Interested in our healthcare data pipeline"
Drafted message:
Subject: API docs + a few thoughts from our chat
Hi Sarah,
Great catching up at the dinner last month. I've been thinking more
about the integration approach we discussed for Meridian's patient
data pipeline.
As promised, here are our API docs: [link]
I flagged the batch processing section specifically — based on what
you described about your throughput needs, that's probably the most
relevant starting point.
Happy to jump on a quick call if any questions come up as your team
reviews. What does your week look like?
Best,
[Name]
Post-send:
1. interactions.log(contact_id, type: "email", summary: "Sent API docs follow-up, offered call to discuss")
2. actions.complete(action_id) // "Send API documentation"
| Principle | Meaning |
|---|---|
| Specific | Reference real details from your history, not generic pleasantries |
| Brief | Respect their time — get to the point in 3-5 sentences |
| Action-oriented | Include a clear next step or question |
| Authentic | Match the user's natural voice and relationship level |
| Contextual | Show you remember what matters to them |
Follow-Up Draft:
- [ ] Contact history reviewed for relevant context
- [ ] Message references specific shared details
- [ ] Clear call-to-action or next step included
- [ ] Tone matches the relationship level
- [ ] Interaction logged after sending
- [ ] Related actions marked complete