Tool.Add Notification Channel.E85166861d03e25f logo

Tool.Add Notification Channel.E85166861d03e25f

Organization
AI45Lab
tool.add_notification_channel.e85166861d03e25f

Adding a new notification channel (e.g. Teams, Discord, PagerDuty) — creating a delivery service, adding the channel type to the schema enum, registering OAuth/token routes, storing credentials encrypted at rest, wiring delivery into notification.ts, and adding per-monitor channel UI. Use when asked to 'add a notification channel', 'integrate Discord notifications', 'add Teams alerts', or 'support PagerDuty'.

Overview

PublisherAI45Lab
RepositoryOpenART
Skill nametool.add_notification_channel.e85166861d03e25f
Stars
251
Forks
28
Bundled files
1
LicenseAGPL-3.0
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 AI45Lab on GitHub. Read the source before you install it.

Installation

Install the Tool.Add Notification Channel.E85166861d03e25f 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.
    https://github.com/AI45Lab/OpenART/tree/main/openart-tools/tool.add_notification_channel.e85166861d03e25f
  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/AI45Lab/OpenART.git /tmp/OpenART
mkdir -p .claude/skills
cp -r /tmp/OpenART/openart-tools/tool.add_notification_channel.e85166861d03e25f .claude/skills/tool.add_notification_channel.e85166861d03e25f
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tool.Add Notification Channel.E85166861d03e25f 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 Tool.Add Notification Channel.E85166861d03e25f 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 Tool.Add Notification Channel.E85166861d03e25f 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.

Use this skill when the OpenART registry selects tool.add_notification_channel.e85166861d03e25f for the current task.

Overview

Notification channels in FetchTheChange follow a strict pattern: a delivery service file, an encrypted credential store, a channel type in the Zod enum, a case in the delivery switch in server/services/notification.ts, and per-monitor UI. The existing Slack and webhook implementations are the reference. This skill encodes the security constraints (encrypted tokens, no plaintext logging) and architectural rules (dedicated service file, tier gating, CSRF exemption for OAuth callbacks).

Workflow

  1. Read server/services/notification.ts — understand deliverToChannels() switch and ChannelDeliveryResult.
  2. Read server/services/slackDelivery.ts — reference for delivery service interface.
  3. Read server/services/webhookDelivery.ts — reference for delivery service interface.
  4. Read server/utils/encryption.ts — understand encryptToken() and decryptToken().
  5. Read shared/schema.ts — note notificationChannels table and slackConnections table patterns.
  6. Read shared/routes.ts — note channelTypeSchema Zod enum and channel-related route definitions.
  7. Add the new channel type string to channelTypeSchema in shared/routes.ts (e.g. z.enum(["email", "webhook", "slack", "discord"])).
  8. If the channel requires stored credentials (OAuth tokens, bot tokens, API keys), add a new table to shared/schema.ts following the slackConnections pattern with an encrypted token column.
  9. Create a delivery service at server/services/{channel}Delivery.ts following slackDelivery.ts:
    • Export a deliver() function accepting (monitor, change, channelConfig, token).
    • Return { success: boolean; error?: string }.
  10. Wire the new channel into the switch (ch.channel) block in deliverToChannels() and deliverDigestToChannels() in server/services/notification.ts:
    • Decrypt stored token with decryptToken().
    • Call the new delivery service.
    • Log delivery results via storage.addDeliveryLog().
  11. If OAuth is required, register install and callback routes in server/routes.ts:
    • Store tokens using encryptToken() — never plaintext.
    • Add the OAuth callback path to EXEMPT_PATHS or EXEMPT_PREFIXES in server/middleware/csrf.ts.
  12. Add a tier gate: new channels must enforce the same Pro/Power check pattern used by Slack and webhook routes — read from TIER_LIMITS in shared/models/auth.ts.
  13. Add storage methods to IStorage and DatabaseStorage in server/storage.ts for credential CRUD.
  14. Add per-monitor channel selection UI in the monitor notification settings, using shadcn/ui primitives.
  15. Run npm run check && npm run test.

Hard constraints

  • NEVER store a bot token, OAuth token, or API key in plaintext — always encrypt with encryptToken() from server/utils/encryption.ts
  • NEVER log a decrypted token — even at debug level; log only safe prefixes or redacted placeholders
  • NEVER return a stored credential in a GET response — return a redacted placeholder only (e.g. "••••connected")
  • NEVER add a new channel type string without adding it to channelTypeSchema in shared/routes.ts — validation will reject the value
  • NEVER wire delivery logic inline in a route handler — create a dedicated service file following slackDelivery.ts / webhookDelivery.ts
  • NEVER add an OAuth callback route without a CSRF exemption in server/middleware/csrf.ts — the callback carries no Origin header
  • NEVER skip the tier gate — new channels must enforce the same Pro/Power check pattern used by existing Slack and webhook routes, reading from TIER_LIMITS
  • NEVER skip the verification gate — run npm run check && npm run test before committing

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 Tool.Add Notification Channel.E85166861d03e25f AI skill do?

Adding a new notification channel (e.g. Teams, Discord, PagerDuty) — creating a delivery service, adding the channel type to the schema enum, registering OAuth/token routes, storing credentials encrypted at rest, wiring delivery into notification.ts, and adding per-monitor channel UI. Use when asked to 'add a notification channel', 'integrate Discord notifications', 'add Teams alerts', or 'support PagerDuty'.

Why use Tool.Add Notification Channel.E85166861d03e25f on TypingMind?

Because you install it once and use it with any model. Tool.Add Notification Channel.E85166861d03e25f 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 Tool.Add Notification Channel.E85166861d03e25f in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AI45Lab/OpenART/tree/main/openart-tools/tool.add_notification_channel.e85166861d03e25f. 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 Tool.Add Notification Channel.E85166861d03e25f?

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 Tool.Add Notification Channel.E85166861d03e25f?

As many as you like. As long as a model supports skills, you can use Tool.Add Notification Channel.E85166861d03e25f with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Tool.Add Notification Channel.E85166861d03e25f AI skill free?

Yes. It is published on GitHub by AI45Lab under the AGPL-3.0 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 👇