Slack Announce logo

Slack Announce

Organization
WellApp-ai
slack-announce

Generate formatted Slack messages for team communication

Overview

PublisherWellApp-ai
RepositoryWell
Skill nameslack-announce
Stars
342
Forks
48
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by WellApp-ai on GitHub. Read the source before you install it.

Installation

Install the Slack Announce 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/WellApp-ai/Well.git /tmp/Well
mkdir -p .claude/skills
cp -r /tmp/Well/cursor-rules/skills/slack-announce .claude/skills/slack-announce
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Slack Announce 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 Slack Announce 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 Slack Announce 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.

Slack Announce Skill

Generate copy-ready Slack messages for various team announcements.

When to Use

  • Push PR mode: announce new PR
  • Hotfix mode: urgent fix notification
  • Deploy notifications
  • Incident communication

Phases

Phase 1: Determine Message Type

Identify the type of announcement:

TypeContextPriority
prNew PR createdNormal
hotfixUrgent production fixHigh
deployDeployment to environmentNormal
incidentProduction issueCritical

Phase 2: Gather Context

Collect required information based on type:

For PR:

  • Feature name (from branch or PR title)
  • PR URL
  • Notion task URL
  • Reviewer name and handle
  • Domain name

For Hotfix:

  • Issue description
  • Affected systems
  • PR URL (if applicable)
  • Urgency level

For Deploy:

  • Version/tag
  • Environment (test/production)
  • Key changes summary

Phase 3: Select Emoji

By message type:

TypePrimary EmojiSecondary Emojis
pr (feat)🚀📋 🔗 👀
pr (fix)🔧📋 🔗 👀
pr (chore)🧹📋 🔗 👀
pr (docs)📚📋 🔗 👀
pr (refactor)♻️📋 🔗 👀
hotfix⚠️🔥 🚨
deploy🎉 📦
incident🚨⚠️ 🔴

Phase 4: Generate Fun Closing

Select a closing that matches the PR context. Be human, be fun, be relevant.

By PR Type

Features (feat):

- "Feature flag? Where we're going, we don't need feature flags 🚗"
- "Users asked, we delivered 📦"
- "Fresh code, hot off the keyboard! ⌨️🔥"
- "Time to make some bytes dance! 💃"
- "Let's gooooo! 🎸"

Fixes (fix):

- "Bug squashed. No insects were harmed 🐛✨"
- "It's not a bug, it was an undocumented feature 📝"
- "Another bug bites the dust 🎵"
- "Sleep well tonight, this one's fixed 😴"

Refactors (refactor):

- "Same same, but different, but still same 🔄"
- "If it ain't broke... refactor it anyway ♻️"
- "Deleting code is my love language 💕"
- "Less is more. Literally, we deleted stuff 🗑️"

Chores (chore):

- "The unglamorous work that makes the magic happen ✨"
- "Housekeeping complete, the codebase says thank you 🏠"
- "Ctrl+S, Ctrl+Ship! 🚢"
- "Another day, another deploy (hopefully) 🤞"

Docs (docs):

- "Future us will thank present us 📚"
- "Documentation: because tribal knowledge doesn't scale 🧠"
- "README? More like READ-ME-PLEASE 🙏"
By Domain (Contextual)

Cursor Rules / AI Workflow:

- "Teaching the AI new tricks! 🎓🤖"
- "The machines are learning... from us, for once 🧠"
- "The rules now have rules about rules 🤯"
- "25 skills walk into a codebase... 🚶‍♂️"
- "Now with 100% more patine (it's French, we're fancy) 🥐"

Tables / Data:

- "Rows and columns, living in harmony 📊"
- "Data goes in, insights come out 🔮"

Auth / Security:

- "Keeping the bad guys out since [current_year] 🔐"
- "Trust no one. Except this PR. Trust this PR 🤝"

Payments / Billing:

- "Making money moves 💰"
- "Cha-ching! 💵"
Generic (Fallback)
- "Shipping it before my coffee gets cold ☕"
- "May the code review gods be merciful 🙏"
- "Works on my machine™ 💻"
- "One small commit for dev, one giant leap for the product 🌙"
Hotfixes (Serious but Human)
- "On it! 🔥"
- "Fix incoming, hold tight! 🏃‍♂️"
- "Crisis averted. Coffee break earned ☕"
- "The bat-signal was answered 🦇"
Selection Logic
  1. First, try domain-specific closing if domain is detected
  2. Then, try type-specific closing based on commit type
  3. Fall back to generic if no match
  4. Rotate - don't repeat the same closing twice in a row

Phase 5: Format Message

PR Template:

[emoji] **[Feature Name]**

[Two-liner: what this does + why it matters]

📋 Notion: [notion-link]
🔗 PR: [github-pr-link]
👀 Reviewer: @[handle] (auto-assigned from [domain])

[Fun closing]

Hotfix Template:

⚠️ **HOTFIX: [Issue Title]**

🔴 **Impact:** [affected systems/users]
🔧 **Fix:** [brief description]

🔗 PR: [github-pr-link]
👀 Reviewer: @[handle]

[Closing]

Deploy Template:

✅ **Deployed to [Environment]**

📦 Version: [tag/version]
📝 Changes:
- [bullet 1]
- [bullet 2]

🎉 Ship it!

Output

Present the formatted message in a copyable code block:

## Slack Message (copy-ready)

[Formatted message here - ready to paste into Slack]

Slack MCP Integration (Optional)

If Slack MCP is configured, messages can be sent automatically.

Phase 6: Send via Slack MCP

Prerequisites:

  • Slack MCP server installed and configured
  • Bot token with chat:write scope
  • Channel ID for announcements

Send message:

Slack MCP:
  tool: send_message
  arguments:
    channel: "[CHANNEL_ID]"
    text: "[formatted message from Phase 5]"

Fallback: If Slack MCP not available, output copy-ready message for manual posting.

Setup Instructions

See setup skill Phase 9 for Slack MCP installation.


Integration

This skill is invoked by:

  • push-pr.mdc - Phase 3.1 (Announce)
  • pr-threshold - When threshold crossed (optional notification)
  • hotfix/SKILL.md - Urgent notification
  • Deploy scripts (future)

Frequently asked questions

What does the Slack Announce AI skill do?

Generate formatted Slack messages for team communication

Why use Slack Announce on TypingMind?

Because you install it once and use it with any model. Slack Announce 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 Slack Announce in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/WellApp-ai/Well/tree/main/cursor-rules/skills/slack-announce. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Slack Announce?

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 Slack Announce?

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

Is the Slack Announce AI skill free?

Yes. It is published on GitHub by WellApp-ai 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 👇