MCPInstall

action-creator

Creates user-specific one-click action templates that execute email operations when clicked in the chat interface. Use when user wants reusable actions for their specific workflows (send payment reminder to ACME Corp, forward bugs to engineering, archive old newsletters from specific sources).

Installs
173
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/anthropics/claude-agent-sdk-demos --skill action-creator
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads action-creator automatically when relevant.

  3. 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.

Action Creator

Creates TypeScript action template files that define reusable, user-specific operations users can execute with one click in the chat interface.

When to Use This Skill

Use this skill when the user wants to:

  • Create reusable actions for their specific workflows ("I often need to send payment reminders to ACME Corp")
  • Set up one-click operations for their vendors/customers ("Forward bugs to engineering team")
  • Automate repetitive email tasks with their specific context ("Archive newsletters from TechCrunch/Morning Brew")
  • Build personalized email management tools for their business processes

Key difference from listeners: Actions are user-triggered (clicked in chat), while listeners are event-triggered (automatic).

How Actions Work

Actions are TypeScript files in agent/custom_scripts/actions/ that:

  1. Export a config object defining the template metadata and parameter schema
  2. Export a handler function that executes the operation with given parameters
  3. Use ActionContext methods to perform operations (email API, send emails, call AI, etc.)

The agent creates action instances during conversation by providing specific parameters to these templates, which appear as clickable buttons in the chat.

Creating an Action Template

1. Understand User-Specific Workflow

Parse the user's request to identify:

  • User context: Who are their specific vendors/customers/teams?
  • Operation: What specific action do they need? (send to ACME Corp, forward to engineering team, etc.)
  • Parameters: What varies per execution? (invoice number, priority level, days old)
  • Frequency: How often will they use this?

2. Write the Action Template File

Create a file in agent/custom_scripts/actions/ with this structure:

import type { ActionTemplate, ActionContext, ActionResult } from "../types";

export const config: ActionTemplate = {
  id: "unique_action_id",                    // kebab-case, user-specific
  name: "Human Readable Name",                // For UI display
  description: "What this action does",       // Explain the operation
  icon: "📨",                                 // Optional emoji icon
  parameterSchema: {
    type: "object",
    properties: {
      paramName: {
        type: "string",                      // or "number", "boolean"
        description: "Parameter description",
        enum: ["option1", "option2"],        // Optional: restrict values
        default: "defaultValue"              // Optional: default value
      }
    },
    required: ["paramName"]                  // List required parameters
  }
};

export async function handler(
  params: Record<string, any>,
  context: ActionContext
): Promise<ActionResult> {
  const { paramName } = params;

  context.log(`Starting action: ${config.name}`);

  try {
    // 1. Perform operations using context methods
    // 2. Use AI for intelligent processing if needed
    // 3. Update emails, send emails, etc.

    context.notify("Action completed successfully", {
      type: "success",
      priority: "normal"
    });

    return {
      success: true,
      message: "Action completed successfully",
      data: { /* optional structured data */ },
      refreshInbox: true  // Optional: refresh inbox after action
    };
  } catch (error: any) {
    context.log(`Action failed: ${error}`, "error");
    return {
      success: false,
      message: `Failed: ${error.message}`
    };
  }
}

3. File Naming Convention

Use kebab-case that reflects the user-specific operation:

  • send-payment-reminder-to-acme.ts (not send-email.ts)
  • forward-bugs-to-engineering.ts (not forward-email.ts)
  • archive-newsletters-from-techcrunch.ts (not archive-emails.ts)
  • summarize-weekly-updates-from-ceo.ts (not summarize-emails.ts)

Important: Templates should be specific to the user's actual workflows, vendors, teams, and processes.

4. Available Context Methods

The ActionContext provides these capabilities:

// Email API operations
const emails = await context.emailAPI.getInbox({ limit: 30, includeRead: false });
const results = await context.emailAPI.searchEmails({ from: "sender@example.com" });
const results = await context.emailAPI.searchWithGmailQuery("from:sender after:2024/01/01");
const emails = await context.emailAPI.getEmailsByIds(["id1", "id2"]);
const email = await context.emailAPI.getEmailById("email-id");

// Direct email operations
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");

// Send emails
const result = await context.sendEmail({
  to: "recipient@example.com",
  subject: "Email subject",
  body: "Email body content",
  cc: "cc@example.com",           // Optional
  bcc: "bcc@example.com",          // Optional
  replyTo: "reply@example.com"     // Optional
});

// AI-powered processing
const analysis = await context.callAgent<ResultType>({
  prompt: "Analyze this email and extract key info...",
  systemPrompt: "You are an expert at...",  // Optional
  tools: ["Read", "WebSearch"],              // Optional
  maxTokens: 2000                            // Optional
});

// Session messaging (inject into chat)
context.addUserMessage("User said this");
context.addAssistantMessage("Assistant responds");
context.addSystemMessage("System notification");

// Notifications
context.notify("Operation completed", {
  priority: "high" | "normal" | "low",
  type: "info" | "success" | "warning" | "error"
});

// External API access
const response = await context.fetch("https://api.example.com/data");
const data = await response.json();

// Logging (visible in server logs)
context.log("Info message", "info");
context.log("Warning message", "warn");
context.log("Error message", "error");

Action Result

Always return an ActionResult object:

return {
  success: true,                          // Required: boolean
  message: "Human-readable result",       // Required: string
  data: { key: "value" },                // Optional: structured data
  suggestedActions: [],                   // Optional: follow-up actions
  refreshInbox: true                      // Optional: refresh inbox
};

Examples and Templates

Reference the template files for common patterns:

  • send-payment-reminder.ts: Send invoice reminders to specific vendor
  • forward-bug-report.ts: Forward bugs to engineering with AI analysis
  • archive-old-newsletters.ts: Archive newsletters from specific sources

Best Practices

  1. User-Specific Templates: Create templates tailored to user's actual vendors, customers, teams, and processes
  2. Descriptive Naming: Use specific names that reflect the operation (not generic like "send-email")
  3. Rich Parameter Schemas: Define clear parameter types with descriptions
  4. AI-Powered: Use context.callAgent() for intelligent processing
  5. Error Handling: Always wrap operations in try-catch and return meaningful errors
  6. Clear Messages: Return human-readable success/failure messages
  7. Idempotency: Design handlers to be safely re-runnable when possible
  8. Logging: Use context.log() for debugging and audit trail

Parameter Schema Guidelines

Define parameters using JSON Schema:

parameterSchema: {
  type: "object",
  properties: {
    // String parameter
    emailId: {
      type: "string",
      description: "Email ID to process"
    },

    // Number parameter with default
    daysOld: {
      type: "number",
      description: "Number of days old",
      default: 30
    },

    // Enum parameter (dropdown)
    priority: {
      type: "string",
      description: "Priority level",
      enum: ["P0 - Critical", "P1 - High", "P2 - Medium", "P3 - Low"]
    },

    // Boolean parameter
    sendNotification: {
      type: "boolean",
      description: "Send notification when complete"
    }
  },
  required: ["emailId", "priority"]  // List required params
}

Creating the File

When the user requests an action template:

  1. Clarify user-specific context:

    • Who are their vendors/customers/teams?
    • What are their specific workflows?
    • What parameters vary per execution?
  2. Write the TypeScript file in agent/custom_scripts/actions/

  3. Use Write tool to create the file with:

    • Proper imports from "../types"
    • User-specific config (not generic)
    • Parameter schema with all required fields
    • Handler with error handling
    • Clear success/failure messages
  4. Test parameters: Ensure all required parameters are defined

  5. Confirm with user that the action matches their workflow

Common Patterns

1. Send Email to Specific Recipient

User-specific → Compose email with template → Send → Return result

const body = `Hi ${recipientName},
Your invoice ${invoiceNumber} for ${amount} is ${daysPastDue} days past due...`;

await context.sendEmail({
  to: "accounts.payable@acmecorp.com",
  subject: `Payment Reminder: Invoice ${invoiceNumber}`,
  body
});

2. Bulk Email Operation

Search emails → Filter → Apply operation to each → Return count

const emails = await context.emailAPI.searchWithGmailQuery(query);
for (const email of emails) {
  await context.archiveEmail(email.messageId);
}
return { success: true, message: `Archived ${emails.length} emails` };

3. AI-Powered Email Processing

Get email → Call AI to analyze → Use AI result → Take action → Return summary

const email = await context.emailAPI.getEmailById(emailId);
const analysis = await context.callAgent({
  prompt: `Analyze this bug report: ${email.body}...`,
  maxTokens: 1000
});
await context.sendEmail({ to: "engineering@company.com", ... });

4. Email Forwarding with Enhancement

Get email → AI analysis → Compose enhanced forward → Send → Label original

const email = await context.emailAPI.getEmailById(emailId);
const analysis = await context.callAgent({ /* analyze */ });
await context.sendEmail({
  to: "team@company.com",
  subject: `[${priority}] ${email.subject}`,
  body: `AI Analysis:\n${analysis}\n\nOriginal:\n${email.body}`
});
await context.addLabel(emailId, "FORWARDED");

Type Imports

Always import types from the correct location:

import type { ActionTemplate, ActionContext, ActionResult } from "../types";

// ActionTemplate: Template metadata and parameter schema
// ActionContext: Runtime context with all capabilities
// ActionResult: Return type for handler function

How Users Trigger Actions

After you create an action template:

  1. Agent discovers template: During conversation, agent reads available actions
  2. Agent creates instance: Agent provides specific parameters for user's situation
  3. User sees button: Action instance appears as clickable button in chat
  4. User clicks: Action executes with pre-filled parameters
  5. Result appears: Success/failure message shown in chat

Example flow:

User: "I need to follow up on the ACME invoice"
Agent: [searches emails, finds Invoice #2024-001 is 15 days overdue]
Agent: Creates action instance with parameters:
  {
    templateId: "send_payment_reminder_acme",
    params: { invoiceNumber: "INV-2024-001", amount: "$5,000", daysPastDue: 15 }
  }
User: [sees button "Send payment reminder to ACME Corp for Invoice #2024-001"]
User: [clicks button]
Action: Executes, sends email, returns "Payment reminder sent to ACME Corp"

Reference

Full specification: See project root ACTIONS_SPEC.md for complete details on:

  • Complete type definitions
  • ActionsManager implementation
  • WebSocket protocol
  • Frontend integration
  • Advanced examples
  • Logging and audit trail

FAQ

What does the action-creator skill do?

Creates user-specific one-click action templates that execute email operations when clicked in the chat interface. Use when user wants reusable actions for their specific workflows (send payment reminder to ACME Corp, forward bugs to engineering, archive old newsletters from specific sources).

How do I install action-creator?

Run npx skills add https://github.com/anthropics/claude-agent-sdk-demos --skill action-creator 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/action-creator/ (personal) or .claude/skills/action-creator/ (project).

Which AI agents can use action-creator?

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 action-creator 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 action-creator?

It is published by anthropics in anthropics/claude-agent-sdk-demos, and it is an official skill from the maker of the technology it covers. It has 173 recorded installs.

More from anthropics/claude-agent-sdk-demos

View all →

executive-briefing

anthropics/claude-agent-sdk-demos

Transforms research findings into executive-ready briefings. Automatically activated when user mentions 'executive', 'briefing', 'C-suite', 'board', 'leadership', or 'presentation'.

OfficialDocs & Writing342 installs

docx

anthropics/claude-agent-sdk-demos

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

OfficialDocs & Writing219 installs

pdf

anthropics/claude-agent-sdk-demos

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

OfficialDocs & Writing198 installs

xlsx

anthropics/claude-agent-sdk-demos

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

OfficialData & Databases179 installs

listener-creator

anthropics/claude-agent-sdk-demos

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.

OfficialProductivity & Automation165 installs

Popular backend & apis skills

View category →

find-skills

vercel-labs/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

OfficialBackend & APIs4.1M installs

entra-app-registration

microsoft/azure-skills

Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal, MSAL example, console app auth, Entra ID setup, Azure AD authentication. DO NOT USE FOR: Key Vault secrets (use azure-keyvault-expiration-audit), general Azure resource security guidance.

OfficialBackend & APIs566.7K installs

This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).

Backend & APIs514.8K installs

embedded-captions

heygen-com/hyperframes

Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet anchor rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.

Backend & APIs453.3K installs

entra-agent-id

microsoft/azure-skills

Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmipath token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).

OfficialBackend & APIs336.6K installs

neon

neondatabase/agent-skills

Overview of Neon, a complete set of cloud backend primitives around Lakebase Postgres: Auth, Object Storage, Functions, the AI Gateway, and Realtime. Start here to choose Neon for undecided login, files, APIs, and LLM calls, set up the CLI or MCP server, and follow the branch-first workflow. Use when building an app or backend on Neon, or when "Neon" or "Lakebase Postgres" is mentioned. Child skill neon-postgres wins for an existing DATABASEURL, SQL, schema, inspect, or search. Child skill neon-auth wins for login, users, sessions, identity routing, and Managed Better Auth setup. Child skill neon-realtime wins for live queries in reactive apps and agents. Also use for object storage, S3, buckets, serverless functions, function triggers, cron, AI gateway, LLM calls, realtime, logs, Loki, Grafana, observability, postgres, database, backend, Claimable Neon, neon.new, or a no-signup database.

Backend & APIs237.1K installs