How do I install the Gmail Analyze skill?

Run npx skillmds@latest add corentinlumineau/gmail-analyze in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Gmail Analyze safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Gmail Analyze?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Gmail Analyze free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under Apache-2.

Who published Gmail Analyze?

CorentinLumineau (@corentinlumineau) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Gmail Analyze by corentinlumineau — Agent Skill

Name: Gmail Analyze
Author: CorentinLumineau

Gmail Analyze

Analyze Gmail inbox patterns to identify high-volume senders and suggest filter rules. Use when organizing email, creating automation rules, or understanding inbox composition. Works with personal Gmail accounts via gog CLI.

File contents

Gmail Inbox Analyzer

Analyze inbox patterns and suggest intelligent filter rules using Pareto analysis.

Prerequisites Check

First, verify gog CLI is authenticated:

gog auth status

If not authenticated, guide the user to run:

gog auth add their.email@gmail.com

Analysis Workflow

Step 1: Fetch Recent Emails

Fetch emails from the specified time period (default: 30 days):

gog gmail search 'newer_than:${DAYS}d' --json

Parse the JSON output to extract:

from - Sender email
subject - Email subject
date - Received date
labelIds - Applied labels

Step 2: Pattern Analysis

Analyze the fetched emails to identify:

Top Sender Domains (Pareto: focus on top 20%)
- Group emails by sender domain
- Count frequency per domain
- Identify domains with 5+ emails
Sender Categories
- Newsletters: substack, mailchimp, newsletter, digest
- Notifications: github, gitlab, jira, slack, notion
- Shopping: amazon, ebay, order, shipping
- Social: facebook, twitter, linkedin
Volume Distribution
- Total emails analyzed
- Emails per day average
- Peak sending times

Step 3: Generate Suggestions

For each high-volume pattern, suggest:

Domain	Count	Suggested Label	Filter Criteria	Confidence
substack.com	45	Newsletters	from:@substack.com	High
github.com	32	Notifications	from:@github.com	High

Step 4: Present Results

Output a formatted report:

## Inbox Analysis Report

**Period**: Last {days} days
**Total Emails**: {count}
**Unique Senders**: {unique}

### Top 10 Sender Domains

1. example.com - 142 emails (28%)
2. github.com - 89 emails (18%)
...

### Suggested Filters

| Priority | Pattern | Label | Est. Impact |
|----------|---------|-------|-------------|
| 1 | from:@newsletter.com | Newsletters | 45 emails/month |
| 2 | from:@github.com | Notifications | 32 emails/month |

### Recommended Actions

1. Create "Newsletters" label and filter
2. Create "Notifications" label with auto-archive
3. ...

Would you like me to create these filters? Use `/gmail-filter` to proceed.

Arguments

$ARGUMENTS - Number of days to analyze (default: 30)

Example Usage

User: /gmail-analyze 60

Analyzes the last 60 days of email.

Output Format

Always provide:

Summary statistics
Top senders table
Suggested filters with confidence levels
Clear next steps

Error Handling

If gog not installed: Provide installation instructions
If not authenticated: Guide through OAuth setup
If no emails found: Suggest widening the search period

---name: gmail-analyzedescription: Analyze Gmail inbox patterns to identify high-volume senders and suggest filter rules. Use when organizing email, creating automation rules, or understanding inbox composition. Works with personal Gmail accounts via gog CLI.license: Apache-2.0---# Gmail Inbox AnalyzerAnalyze inbox patterns and suggest intelligent filter rules using Pareto analysis.## Prerequisites CheckFirst, verify gog CLI is authenticated:```bashgog auth status```If not authenticated, guide the user to run:```bashgog auth add their.email@gmail.com```## Analysis Workflow### Step 1: Fetch Recent EmailsFetch emails from the specified time period (default: 30 days):```bashgog gmail search 'newer_than:${DAYS}d' --json```Parse the JSON output to extract:- `from` - Sender email- `subject` - Email subject- `date` - Received date- `labelIds` - Applied labels### Step 2: Pattern AnalysisAnalyze the fetched emails to identify:1. **Top Sender Domains** (Pareto: focus on top 20%) - Group emails by sender domain - Count frequency per domain - Identify domains with 5+ emails2. **Sender Categories** - Newsletters: substack, mailchimp, newsletter, digest - Notifications: github, gitlab, jira, slack, notion - Shopping: amazon, ebay, order, shipping - Social: facebook, twitter, linkedin3. **Volume Distribution** - Total emails analyzed - Emails per day average - Peak sending times### Step 3: Generate SuggestionsFor each high-volume pattern, suggest:| Domain | Count | Suggested Label | Filter Criteria | Confidence ||--------|-------|-----------------|-----------------|------------|| substack.com | 45 | Newsletters | from:@substack.com | High || github.com | 32 | Notifications | from:@github.com | High |### Step 4: Present ResultsOutput a formatted report:```## Inbox Analysis Report**Period**: Last {days} days**Total Emails**: {count}**Unique Senders**: {unique}### Top 10 Sender Domains1. example.com - 142 emails (28%)2. github.com - 89 emails (18%)...### Suggested Filters| Priority | Pattern | Label | Est. Impact ||----------|---------|-------|-------------|| 1 | from:@newsletter.com | Newsletters | 45 emails/month || 2 | from:@github.com | Notifications | 32 emails/month |### Recommended Actions1. Create "Newsletters" label and filter2. Create "Notifications" label with auto-archive3. ...Would you like me to create these filters? Use `/gmail-filter` to proceed.```## Arguments- `$ARGUMENTS` - Number of days to analyze (default: 30)## Example Usage```User: /gmail-analyze 60```Analyzes the last 60 days of email.## Output FormatAlways provide:1. Summary statistics2. Top senders table3. Suggested filters with confidence levels4. Clear next steps## Error Handling- If gog not installed: Provide installation instructions- If not authenticated: Guide through OAuth setup- If no emails found: Suggest widening the search period

Frequently asked questions