Skip to content
Research
Skill

/listener-creator

Creates event-driven email listeners that monitor for specific conditions (like urgent emails from boss, newsletters to archive, package tracking) and execute custom actions. Use when user wants to be notified about emails, automatically handle certain emails, or set up email

BOOST
From plugin
claude-agent-sdk-demos
2.8k6 skills1 agent5 commands
Install
$ npx -y skills add anthropics/claude-agent-sdk-demos --skill listener-creator --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/listener-creator

Context preview

The summary Claude sees to decide when to auto-load this skill.

Creates event-driven email listeners that monitor for specific conditions (like urgent emails from boss, newsletters to archive, package tracking) and execute custom actions. Use when user wants to be notified about emails, automatically handle certain emails, or set up email

SKILL.md

listener-creator.SKILL.md
name: listener-creator
description: Creates event-driven email listeners that monitor for specific conditions (like urgent emails from boss, newsletters to archive, package tracking) and execute custom actions. Use when user wants to be notified about emails, automatically handle certain emails, or set up email automation workflows.
allowed-tools: Write, Edit, Read, Glob

Listener Creator

Creates TypeScript listener files that monitor email events and execute custom logic when conditions are met.

When to Use This Skill

Use this skill when the user wants to:

  • Get notifications about specific emails ("notify me when boss sends urgent emails")
  • Automatically handle certain emails ("auto-archive newsletters")
  • Monitor for patterns ("watch for package tracking emails")
  • Set up scheduled actions ("daily email summary at 9am")
  • Create custom email workflows

How Listeners Work

Listeners are TypeScript files in `agent/custom_scripts/listeners/` that: 1. Export a `config` object defining the event type and metadata 2. Export a `handler` function that filters and processes events 3. Use `ListenerContext` methods to perform actions (notify, archive, star, etc.)

The system automatically loads enabled listeners and executes them when matching events occur.

Creating a Listener

1. Understand the User's Intent

Parse the user's request to identify:

  • **Event type**: What triggers this listener? (email_received, email_sent, email_starred, email_archived, email_labeled, scheduled_time)
  • **Filter conditions**: What specific emails/events to match? (sender, subject keywords, time-based)
  • **Actions**: What should happen? (notify, archive, star, mark as read, add label)
  • **Priority**: How urgent is this? (high/normal/low)

2. Choose an Event Type

// Available event types:
- "email_received"  // Most common - new email arrives
- "email_sent"      // User sends an email
- "email_starred"   // Email is starred
- "email_archived"  // Email is archived
- "email_labeled"   // Label added to email
- "scheduled_time"  // Time-based (cron) - requires scheduler setup

3. Write the Listener File

Create a file in `agent/custom_scripts/listeners/` with this structure:

import type { ListenerConfig, Email, ListenerContext } from "../types";

export const config: ListenerConfig = {
  id: "unique_listener_id",           // kebab-case, descriptive
  name: "Human Readable Name",         // For UI display
  description: "What this does",       // Optional but helpful
  enabled: true,                       // Start enabled
  event: "email_received"              // Event type
};

export async function handler(email: Email, context: ListenerContext): Promise<void> {
  // 1. Basic filter (identity/sender only)
  if (!email.from.includes("example@email.com")) return;

  // 2. Use AI for intelligent classification (PREFERRED over keyword matching)
  const analysis = await context.callAgent<{ isUrgent: boolean; reason: string }>({
    prompt: `Is this email urgent?\nSubject: ${email.subject}\nBody: ${email.body.substring(0, 500)}`,
    schema: {
      type: "object",
      properties: {
        isUrgent: { type: "boolean" },
        reason: { type: "string" }
      },
      required: ["isUrgent", "reason"]
    },
    model: "haiku"
  });

  if (!analysis.isUrgent) return;

  // 3. Perform actions via context methods
  await context.notify(`Urgent email: ${email.subject}\n${analysis.reason}`, {
    priority: "high"
  });

  await context.starEmail(email.messageId);
}

4. File Naming Convention

Use kebab-case matching the listener's purpose:

  • `boss-urgent-watcher.ts`
  • `auto-archive-newsletters.ts`
  • `package-tracking.ts`
  • `daily-summary.ts`

5. Available Context Methods

The `ListenerContext` provides these methods:

// Notifications
await context.notify(message, { priority: "high" | "normal" | "low" });

// Email actions
await context.archiveEmail(emailId);
await context.starEmail(emailId);
await context.unstarEmail(emailId);
await context.markAsRead(emailId);
await context.markAsUnread(emailId);
await context.addLabel(emailId, "label-name");
await context.removeLabel(emailId, "label-name");

// AI-powered analysis
const result = await context.callAgent<ResultType>({
  prompt: "Your prompt with email content",
  schema: {
    type: "object",
    properties: { field: { type: "string" } },
    required: ["field"]
  },
  model: "haiku" // or "sonnet" or "opus"
});

Recommended Approach: AI-Powered Classification

**Default to using `context.callAgent()` for intelligent decision-making** instead of hard-coded keyword lists. This provides better accuracy and adaptability.

// PREFERRED: AI-based urgency detection
const analysis = await context.callAgent<{ isUrgent: boolean; reason: string }>({
  prompt: `Analyze if this email is urgent:
Subject: ${email.subject}
Body: ${email.body.substring(0, 500)}

Is this email urgent or time-sensitive? Consider context, not just keywords.`,

  schema: {
    type: "object",
    properties: {
      isUrgent: { type: "boolean" },
      reason: { type: "string" }
    },
    required: ["isUrgent", "reason"]
  },
  model: "haiku" // Fast and cost-effective
});

if (analysis.isUrgent) {
  await context.notify(`Urgent: ${email.subject}\n${analysis.reason}`);
}

// AVOID: Hard-coded keyword lists (brittle and prone to false positives)
// const isUrgent = subject.includes("urgent") || subject.includes("asap");

Examples and Templates

Reference the template files for common patterns:

  • **[ai-classifier.ts](templates/ai-classifier.ts)**: ⭐ AI-powered email classification (RECOMMENDED)
  • **[urgent-watcher.ts](templates/urgent-watcher.ts)**: AI-based urgent email detection
  • **[auto-archive.ts](templates/auto-archive.ts)**: Automatically archives newsletters
  • **[package-tracker.ts](templates/package-tracker.ts)**: Package tracking with status extraction

Best Practices

1. **

Read more
Ships withclaude-agent-sdk-demos

⚠️ IMPORTANT: These are demo applications by Anthropic. They are intended for local development only and should NOT be deployed to production or used at scale.

Get the whole plugin

Other skills on claude-agent-sdk-demos.