菜单
Audits Evergreen CRM for stale or incomplete contact data — outdated titles, missing fields, potential duplicates, and contacts that may have changed jobs. Use for periodic database hygiene, before a big outreach push, or when data quality feels off.
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.
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.
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.
| name | evergreen-stale-data-audit |
| description | Audits Evergreen CRM for stale or incomplete contact data — outdated titles, missing fields, potential duplicates, and contacts that may have changed jobs. Use for periodic database hygiene, before a big outreach push, or when data quality feels off. |
Works with Evergreen, a local-first personal CRM for macOS. Get it on the Mac App Store.
search_contacts to get the full databaseget_contact| Check | What to Look For | Priority |
|---|---|---|
| Missing email | Contact has no email address | High |
| Missing organization | No company/org listed | Medium |
| Stale title | Title unchanged for 12+ months on active contact | Medium |
| No interactions | Contact exists but zero interactions logged | Low |
| No tags | Contact has no tags for filtering | Low |
| Empty notes | No context about the relationship | Medium |
| No location | Missing city/region | Low |
| Orphaned contacts | No relationships, no interactions, no tags | High |
## Data Audit Report — April 2026
### Summary
- **Total contacts:** 187
- **Complete records:** 112 (60%)
- **Needs attention:** 75 (40%)
### Critical Issues (12)
1. **Sarah Chen** — Email missing (have everything else)
2. **Marcus Webb** — Title still says "Stealth Mode" (company launched 6 months ago)
3. **[5 contacts]** — No interactions ever logged (orphaned?)
4. **[5 contacts]** — Duplicate suspected (same org + similar name)
### Missing Fields Summary
| Field | Missing Count | % of Contacts |
|-------|--------------|---------------|
| Email | 23 | 12% |
| Organization | 18 | 10% |
| Title | 31 | 17% |
| Location | 45 | 24% |
| Tags | 38 | 20% |
### Likely Job Changes
Contacts where title was set 12+ months ago and they're at a startup
(high likelihood of role change):
1. **Jamie Rodriguez** — "Senior Engineer at Acme Labs" (set 14 months ago)
2. **Priya Sharma** — "ML Engineer at NewCo" (set 13 months ago)
### Suggested Actions
1. Enrich the 12 critical contacts (use contact-enrichment skill)
2. Review 5 suspected duplicates for merging
3. Archive or delete 5 orphaned contacts with no activity
4. Batch-update missing tags for 38 untagged contacts
Data Audit:
- [ ] All contacts scanned for completeness
- [ ] Critical issues (missing email, duplicates) flagged first
- [ ] Missing fields summarized by type
- [ ] Potentially stale titles identified
- [ ] Orphaned contacts flagged for review
- [ ] Cleanup actions prioritized by impact