Auto Reply logo

Auto Reply

CommunityPopular
alsk1992
auto-reply

Automatic response rules, patterns, and scheduled messages

Overview

Publisheralsk1992
RepositoryCloddsBot
Skill nameauto-reply
Stars
2.8K
Forks
336
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by alsk1992 on GitHub. Read the source before you install it.

Installation

Install the Auto Reply AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/alsk1992/CloddsBot.git /tmp/CloddsBot
mkdir -p .claude/skills
cp -r /tmp/CloddsBot/src/skills/bundled/auto-reply .claude/skills/auto-reply
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Auto Reply in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Auto Reply on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Auto Reply is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Auto-Reply - Complete API Reference

Create rules for automatic responses based on patterns, keywords, and conditions.


Chat Commands

List Rules

/autoreply list                             List all rules
/autoreply active                           Show active rules only
/autoreply stats                            Rule statistics

Create Rules

/autoreply add <pattern> <response>         Simple keyword match
/autoreply add-regex <regex> <response>     Regex pattern
/autoreply add-keywords <kw1,kw2> <resp>    Keyword rule

Manage Rules

/autoreply enable <id>                      Enable rule
/autoreply disable <id>                     Disable rule
/autoreply remove <id>                      Remove rule
/autoreply edit <id> <new-response>         Update response
/autoreply get <id>                         Rule details

Testing

/autoreply test <message>                   Test which rules match
/autoreply simulate <message>               Preview response

Advanced

/autoreply cooldown <id> <seconds>          Set cooldown
/autoreply schedule <id> <start-end>        Active hours (e.g. 9-17)
/autoreply priority <id> <number>           Set priority (higher first)
/autoreply channel <id> <channel>           Restrict to channel
/autoreply clear-cooldowns                  Clear all cooldowns
/autoreply reload                           Reload rules from disk

TypeScript API Reference

Create Auto-Reply Manager

typescript
import { createAutoReplyManager } from 'clodds/auto-reply';

const autoReply = createAutoReplyManager({
  // Storage
  storage: 'sqlite',
  dbPath: './auto-reply.db',

  // Defaults
  defaultCooldownMs: 0,
  defaultPriority: 0,

  // Limits
  maxRulesPerUser: 100,
  maxResponseLength: 2000,
});

Add Simple Rule

typescript
// Keyword match
await autoReply.addRule({
  name: 'greeting',
  pattern: {
    type: 'keyword',
    value: 'hello',
    caseSensitive: false,
  },
  response: 'Hi there! How can I help?',
});

Add Regex Rule

typescript
// Regex pattern
await autoReply.addRule({
  name: 'price-query',
  pattern: {
    type: 'regex',
    value: /price\s+(btc|eth|sol)/i,
  },
  response: async (match, ctx) => {
    const symbol = match[1].toUpperCase();
    const price = await getPrice(symbol);
    return `${symbol} price: $${price}`;
  },
});

Add Conditional Rule

typescript
// With conditions
await autoReply.addRule({
  name: 'trading-hours',
  pattern: {
    type: 'keyword',
    value: 'trade',
  },
  conditions: [
    // Only during market hours
    {
      type: 'time',
      start: '09:30',
      end: '16:00',
      timezone: 'America/New_York',
    },
    // Only on weekdays
    {
      type: 'day',
      days: ['mon', 'tue', 'wed', 'thu', 'fri'],
    },
    // Only for certain users
    {
      type: 'user',
      userIds: ['user-123', 'user-456'],
    },
  ],
  response: 'Markets are open! What would you like to trade?',
  elseResponse: 'Markets are closed. Try again during trading hours.',
});

Add Cooldown

typescript
// Prevent spam
await autoReply.addRule({
  name: 'faq',
  pattern: {
    type: 'keyword',
    value: 'faq',
  },
  response: 'Check our FAQ at https://...',
  cooldown: {
    perUser: 60000,    // 60s per user
    perChannel: 10000, // 10s per channel
    global: 5000,      // 5s global
  },
});

Dynamic Responses

typescript
// Response with variables
await autoReply.addRule({
  name: 'welcome',
  pattern: {
    type: 'exact',
    value: '!welcome',
  },
  response: 'Welcome {{user.name}}! You joined {{user.joinDate}}.',
  variables: {
    'user.name': (ctx) => ctx.user.displayName,
    'user.joinDate': (ctx) => ctx.user.createdAt.toDateString(),
  },
});

// Response with API call
await autoReply.addRule({
  name: 'portfolio',
  pattern: {
    type: 'keyword',
    value: 'portfolio',
  },
  response: async (match, ctx) => {
    const portfolio = await getPortfolio(ctx.user.id);
    return `Your portfolio: $${portfolio.totalValue.toFixed(2)}`;
  },
});

List Rules

typescript
const rules = await autoReply.listRules();

for (const rule of rules) {
  console.log(`${rule.id}: ${rule.name}`);
  console.log(`  Pattern: ${rule.pattern.value}`);
  console.log(`  Enabled: ${rule.enabled}`);
  console.log(`  Triggers: ${rule.triggerCount}`);
}

Test Rule

typescript
// Test which rules would match
const matches = await autoReply.test('hello world', {
  userId: 'user-123',
  channelId: 'telegram-456',
});

for (const match of matches) {
  console.log(`Rule: ${match.rule.name}`);
  console.log(`Response: ${match.response}`);
}

Enable/Disable

typescript
await autoReply.enable('rule-id');
await autoReply.disable('rule-id');

Delete Rule

typescript
await autoReply.deleteRule('rule-id');

Pattern Types

TypeExampleDescription
keywordhelloContains keyword
exact!helpExact match only
regex/price\s+\w+/iRegular expression
startsWith!Starts with prefix
endsWith?Ends with suffix

Condition Types

TypeDescription
timeActive during time window
dayActive on specific days
userOnly for specific users
channelOnly in specific channels
roleOnly for users with role
customCustom function

Response Variables

VariableDescription
{{user.name}}User display name
{{user.id}}User ID
{{channel.name}}Channel name
{{match[0]}}Full regex match
{{match[1]}}First capture group
{{date}}Current date
{{time}}Current time

Best Practices

  1. Use priorities — Important rules first
  2. Set cooldowns — Prevent spam
  3. Test patterns — Verify before enabling
  4. Use conditions — Context-aware responses
  5. Monitor triggers — Check rule effectiveness

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Auto Reply AI skill do?

Automatic response rules, patterns, and scheduled messages

Why use Auto Reply on TypingMind?

Because you install it once and use it with any model. Auto Reply is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Auto Reply in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alsk1992/CloddsBot/tree/main/src/skills/bundled/auto-reply. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Auto Reply?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Auto Reply?

As many as you like. As long as a model supports skills, you can use Auto Reply with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Auto Reply AI skill free?

Yes. It is published on GitHub by alsk1992 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇