
email-check
Intelligent inbox triage that connects to Gmail or Outlook, scores emails by importance (0-100) using sender recognition, urgency keywords, thread depth, time sensitivity, and business relevance, categorizes into Urgent/Important/Routine/Archive, and generates reply suggestions for top priority items. Use when the user wants to check email, review inbox, triage messages, see what's urgent, or get reply suggestions. Triggers on check email, inbox triage, what's important, email summary, unread emails, priority inbox.
- Installs
- 82
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/agricidaniel/claude-email --skill email-check- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads email-check automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Email Check Sub-Skill
Purpose
This sub-skill handles intelligent inbox triage by connecting to Gmail or Outlook via MCP, analyzing unread emails, scoring them by importance, categorizing them, and generating reply suggestions for high-priority items.
Workflow
1. Detect Available Email Provider
Check which MCP tools are available:
- Gmail:
search_gmail_messages,get_gmail_messages_content_batch,get_gmail_thread_content,list_gmail_labels - Outlook:
list-mail-messages,list-mail-folder-messages,get-mail-message
Prefer Gmail if both are available (better batch operations).
2. Fetch Unread Emails
For Gmail:
search_gmail_messages(query="is:unread", max_results=50)
For Outlook:
list-mail-messages (defaults to recent messages, filter for unread)
3. Batch Fetch Email Content
For Gmail:
get_gmail_messages_content_batch(message_ids=[...]) # Up to 25 at a time
If more than 25 unread, prioritize most recent first.
For Outlook:
get-mail-message for each message (sequential)
Limit to 25 emails maximum to avoid overwhelming analysis.
4. Score Each Email (0-100)
Apply the following scoring algorithm:
Base Score: 50
Sender Recognition (+20 to -20)
- +20: VIP/known contact (domain matches user's company, appears in sent folder frequently)
- +10: Recognized sender (has prior thread history)
- 0: Unknown sender with legitimate domain
- -15: Newsletter/automated sender (bulk email headers, unsubscribe links)
- -20: Notification sender (no-reply@, noreply@, automated@)
Direct Address (+15 to -10)
- +15: Primary recipient (To: field)
- 0: CC'd (CC: field)
- -10: BCC'd or mass email (many recipients)
Thread Depth (+10)
- +10: Reply in active thread (Re: subject, multiple messages in thread)
- 0: New email (no thread history)
Urgency Keywords (+15)
Check subject and first 200 characters for:
- urgent, ASAP, deadline, action required, immediate, time-sensitive, expiring, expires, due
- +15 if any urgency keyword found
Calendar/Meeting (+20)
- +20: Calendar invite, meeting request, event notification
- Detect via attachments (ics file) or subject patterns (Invitation:, Meeting:)
Deadline Detection (+25)
Parse email body for dates/deadlines:
- +25: Deadline within 48 hours
- +10: Deadline within 7 days
- 0: No deadline or deadline > 7 days
Business Relevance (+15 to -10)
If email-profile.md exists in parent directory:
- +15: Mentions user's key topics, clients, projects
- +5: Industry-relevant keywords
- -10: Off-topic or personal (if business inbox)
Final Score Calculation
Sum all adjustments to base score of 50. Clamp to 0-100 range.
5. Categorize Emails
Based on final score:
| Score Range | Category | Action |
|---|---|---|
| 85-100 | Urgent | Immediate attention, generate reply suggestions |
| 65-84 | Important | Review soon, may need action |
| 40-64 | Routine | Normal priority, review when available |
| 20-39 | Low Priority | Skim or defer |
| 0-19 | Archive | Likely noise or automated |
6. Generate Reply Suggestions
For emails scored 85+ (Urgent category):
- Read full thread context using
get_gmail_thread_contentor equivalent - Check for email-profile.md in parent directory for user's:
- Brand voice (professional, casual, direct, warm)
- Common sign-off
- Industry/role context
- Draft two reply options:
- Brief: 1-2 sentences, direct answer
- Detailed: 1 paragraph with context
Do NOT draft replies if:
- Email requires research beyond available context
- Email needs user decision (approve/decline, choose option)
- Email is FYI/informational only
- Email is calendar invite (suggest accept/decline/tentative instead)
In these cases, output: "This email requires your personal attention: [reason]"
7. Output Format
## Inbox Summary
**X unread emails** | Y Urgent | Z Important | W Routine | V Low Priority
### Urgent (Action Required)
| # | From | Subject | Score | Suggested Action |
|---|------|---------|-------|------------------|
| 1 | sender@domain.com | Subject line | 95 | [Reply/Review/Respond] |
| 2 | ... | ... | 88 | ... |
---
### Important
| # | From | Subject | Score | Category |
|---|------|---------|-------|----------|
| 3 | ... | ... | 78 | Meeting follow-up |
| 4 | ... | ... | 70 | Client inquiry |
---
### Routine & Low Priority
- **Routine (40-64)**: X emails - [grouped summary by sender/topic]
- **Low Priority (20-39)**: Y emails - newsletters, notifications
- **Archive (<20)**: Z emails - automated/noise
---
### Suggested Replies
#### 1. Re: [Subject] (to: sender@domain.com)
**Context:** [Why this email scored high, key points]
**Brief Option:**
> [1-2 sentence reply]
>
> [Sign-off]
**Detailed Option:**
> [Paragraph with more context/explanation]
>
> [Sign-off]
#### 2. Re: [Next urgent email]
[Repeat format]
---
### Emails Requiring Personal Attention
- **#X - [Subject]**: Needs decision on [topic]
- **#Y - [Subject]**: Requires research before responding
Scoring Signal Reference
| Signal | Score Impact | Detection |
|---|---|---|
| Direct To: address | +15 | Check To: field |
| VIP/known sender | +20 | Domain match, sent folder history |
| Active thread | +10 | Thread ID, Re: in subject |
| Urgency keywords | +15 | Subject/body scan |
| Calendar invite | +20 | .ics attachment, invite headers |
| Deadline <48h | +25 | Date parsing in body |
| Deadline <7d | +10 | Date parsing in body |
| Business relevance | +15 | Match email-profile.md topics |
| CC'd (not primary) | -10 | CC: field |
| Newsletter | -20 | Unsubscribe link, bulk headers |
| Notification | -15 | no-reply@ sender |
| Unknown sender | -10 | No thread history |
Reply Suggestion Guidelines
Tone Adaptation
If email-profile.md exists, adapt replies to match:
- Professional: Formal, structured, clear
- Casual: Friendly, conversational
- Direct: Brief, action-oriented
- Warm: Personable, relationship-focused
Default to professional-friendly if no profile exists.
Reply Structure
Brief Option:
- Answer the core question/request
- 1-2 sentences maximum
- Clear next step if needed
Detailed Option:
- Address all points raised
- Provide context or explanation
- 1 paragraph (3-5 sentences)
- Suggest next steps or timeline
When NOT to Draft
- Email asks for approval/decision → Suggest: "Review and approve/decline X"
- Email requires data you don't have → "This email requires your personal attention: needs [data/info]"
- Email is complex multi-part → "This email requires your personal attention: multiple decisions needed"
- Email is FYI only → Suggested Action: "Review (no response needed)"
Error Handling
No MCP Connection
If neither Gmail nor Outlook MCP is available:
Error: No email provider connected. Please ensure Gmail MCP or Outlook MCP is configured.
Empty Inbox
## Inbox Summary
**0 unread emails** - Your inbox is clear!
MCP Rate Limits
If batch fetch fails, fall back to individual message retrieval (slower but reliable).
Thread Context Unavailable
If get_gmail_thread_content fails, draft replies based on single message only (note: "Limited context - single message view").
Integration Points
email-profile.md (optional)
If exists in parent directory (../email-profile.md), use for:
- Brand voice detection
- Business relevance scoring
- Reply tone/style matching
- Common topics/clients list
Gmail-Specific Features
- Use labels to refine categorization (e.g., skip "Promotions" labeled emails)
- Check sent folder for sender recognition
Outlook-Specific Features
- Use folder structure for context (Inbox vs Focused)
- Leverage categories if available
Performance Optimization
- Batch fetch 25 emails at a time (Gmail)
- Limit analysis to 50 most recent unread
- Cache sender recognition data during session
- Prioritize most recent emails if >50 unread
Output Constraints
- Keep total output under 2000 lines
- Group routine/low priority emails by topic/sender
- Only show full details for Urgent and Important categories
- Collapse archived emails into summary count
Quality Gates
Before outputting digest:
- Verify all urgency scores are justified with signal breakdown
- Ensure reply suggestions are actionable (not generic)
- Check that "personal attention" notes explain why
- Confirm categories align with score ranges
- Validate that batch operations completed successfully
Success Criteria
A successful email check session should:
- Identify all truly urgent emails (no false negatives)
- Minimize false positives in Urgent category (precision > 80%)
- Provide actionable reply drafts for top 3-5 emails
- Complete analysis in <30 seconds for 25 emails
- Output clear next actions for each category
FAQ
What does the email-check skill do?
Intelligent inbox triage that connects to Gmail or Outlook, scores emails by importance (0-100) using sender recognition, urgency keywords, thread depth, time sensitivity, and business relevance, categorizes into Urgent/Important/Routine/Archive, and generates reply suggestions for top priority items. Use when the user wants to check email, review inbox, triage messages, see what's urgent, or get reply suggestions. Triggers on check email, inbox triage, what's important, email summary, unread emails, priority inbox.
How do I install email-check?
Run npx skills add https://github.com/agricidaniel/claude-email --skill email-check in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/email-check/ (personal) or .claude/skills/email-check/ (project).
Which AI agents can use email-check?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is email-check safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains email-check?
It is published by agricidaniel in agricidaniel/claude-email. It has 82 recorded installs.
More from agricidaniel/claude-email
email-audit
agricidaniel/claude-email
Audits email domain deliverability setup (SPF, DKIM, DMARC, MX records, blacklists, TLS) and generates health score (0-100) with prioritized fix list. Checks bulk sender compliance against Google/Yahoo/Microsoft 2024-2026 requirements. Provides DNS records to add/update. Use when user asks to audit, check, or analyze email deliverability, domain health, or inbox placement.
email-sequence
agricidaniel/claude-email
Designs complete email automation sequences with timing, subject lines, copy, and conditional logic. Supports welcome series, nurture campaigns, re-engagement, abandoned cart, post-purchase, review requests, and custom sequences. Adapts sequence type, cadence, frameworks, and conditional branching to business context. Use when user wants to create an automated email series triggered by subscriber actions or time intervals.
email-write
agricidaniel/claude-email
Compose high-converting emails using proven copy frameworks (PAS, AIDA, BAB, FAB, 4Ps). Generates subject line variants with scores, responsive HTML templates with dark mode support, plain-text fallback, and preheader recommendations. Optimized for cold outreach, newsletters, product launches, promotions, and transactional emails. Adapts to user context from email-profile.md.
email-review
agricidaniel/claude-email
Pre-send email quality review and scoring across 5 dimensions (subject line, copy quality, technical/HTML, deliverability, compliance). Analyzes subject lines, body copy, HTML structure, spam triggers, and CAN-SPAM compliance. Scores 0-100 with detailed recommendations for improvement. Use when user wants to review an email before sending, check email quality, or validate marketing email best practices.
agricidaniel/claude-email
Comprehensive email management and marketing for any business type. Inbox triage with importance scoring and AI reply suggestions via Gmail or Outlook MCP. Email composition using proven copy frameworks (PAS, AIDA, BAB, FAB). Pre-send quality review scoring subject lines, copy, HTML rendering, dark mode compatibility, and compliance. Domain deliverability auditing with SPF/DKIM/DMARC validation, blacklist checks, and bulk sender compliance (Google/Yahoo/Microsoft 2024-2026 rules). Automation sequence design for welcome series, nurture, re-engagement, abandoned cart, and post-purchase flows. Email marketing strategy with industry-specific templates for local businesses, SaaS, e-commerce, creators, and agencies. Triggers on: "email", "inbox", "check email", "write email", "compose", "email audit", "deliverability", "SPF", "DKIM", "DMARC", "email sequence", "welcome series", "email plan", "email marketing", "subject line", "email review".
email-plan
agricidaniel/claude-email
Generate comprehensive email marketing strategy with 90-day implementation roadmap. Analyzes business type (local-business, saas, ecommerce, creator, agency) to deliver industry-specific segmentation plans, automation sequences, content calendars, KPI targets, platform recommendations, and week-by-week rollout schedule. Use when building email program from scratch or restructuring existing strategy.
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。