Slack logo

Slack

OrganizationPopular
laude-institute
slack

Talk with people on Slack — recognize slack-* senders and reach them via chat reply

Overview

Publisherlaude-institute
Repositoryheadlong
Skill nameslack
Stars
1.2K
Forks
127
Bundled files
Instructions only
LicenseApache-2.0
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.

  • Self-contained

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

  • Open source

    Published by laude-institute on GitHub. Read the source before you install it.

Installation

Install the Slack 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/laude-institute/headlong/tree/main/skills/slack
  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/laude-institute/headlong.git /tmp/headlong
mkdir -p .claude/skills
cp -r /tmp/headlong/skills/slack .claude/skills/slack
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Slack 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 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 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

Instructions

A Slack bridge forwards messages between your mind log and the org's Slack workspace. You do not need to call the Slack API — the bridge handles delivery in both directions.

Recognizing Slack messages

Messages from Slack arrive as normal message steps whose from looks like:

  • slack-U07AB12CD-D09XYZ123 — a direct message
  • slack-U07AB12CD-C09XYZ123-1722400000.123456 — a channel thread

The parts are Slack IDs: user, channel, and (for channels) the thread timestamp. The message content starts with a readable header like (Slack: Dana Kim in #eng) telling you who is talking and where.

Some senders are other Headlong personas, not people. Their header says so: (Slack: harris, a Headlong persona like you, not a person in #eng). Reply to them the same way. Each bridge stops forwarding after a few peer messages in a row in one thread until a person speaks there, so an unanswered message to a peer is that guard, not a snub. Say what you have to say in one message rather than a chain of short ones, and let a person carry the thread when it goes quiet.

Replying

Reply exactly as you would to any other sender — the bridge delivers it to the right Slack conversation (in-thread for channels, top-level for DMs):

bash
chat reply slack-U07AB12CD-C09XYZ123-1722400000.123456 "On it — deploy is green."

Always use the sender's full slack-… name verbatim as the reply target. Do not shorten it or substitute the person's display name.

Reacting

Add an emoji reaction to the Slack message you are answering. Use the Slack short name (thumbsup, eyes, +1), not unicode:

bash
chat react slack-U07AB12CD-C09XYZ123-1722400000.123456 thumbsup
chat react --reply-to <inbound-step-id> slack-U07AB12CD-C09XYZ123-1722400000.123456 eyes

--reply-to copies that inbound step's source_url so the reaction lands on the specific message, not just the thread root. Needs the Slack app's reactions:write scope (reinstall after it lands).

Following up proactively

To continue a Slack conversation later (e.g. after finishing a task someone asked about), chat reply to the same slack-… name from the earlier message. The bridge posts it into that conversation.

Posting to a channel or DMing someone without an earlier message

Two short forms exist for when you are starting the conversation:

  • slack-C09XYZ123 — post top-level in that channel
  • slack-U07AB12CD — DM that person (the bridge opens the DM)
bash
chat send --to slack-C09XYZ123 "Daily papers for today: ..."
chat send --to slack-U07AB12CD "Built the thing you asked about."

Slack ids are uppercase; users start with U, channels with C. chat rejects any other slack-… shape with a non-zero exit, and the bridge writes a delivery step back to your trajectory for every send, status: delivered with the permalink or status: failed with the reason. A failed delivery shows in your recent stream; check it before assuming a message landed.

Formatting

Write normal markdown; the bridge converts it for Slack (bold, links, headings, code blocks). Long messages are split automatically. Prefer concise messages — it is chat, not a report.

Frequently asked questions

What does the Slack AI skill do?

Talk with people on Slack — recognize slack-* senders and reach them via chat reply

Why use Slack on TypingMind?

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

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

Which AI models can use Slack?

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?

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

Is the Slack AI skill free?

Yes. It is published on GitHub by laude-institute under the Apache-2.0 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 👇