Slack Unanswered logo

Slack Unanswered

Community
minicoohei
slack-unanswered

Slackの未返信メッセージを検出し、返信ドラフトを生成するスキル。 「未返信メッセージ」「返信してないメッセージ」「Slack確認」等のリクエストで発動。

Overview

Publisherminicoohei
Repositoryai-agent-camp
Skill nameslack-unanswered
Stars
346
Forks
13
Bundled files
3
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.

  • 3 bundled files

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

  • Open source

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

Installation

Install the Slack Unanswered 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/minicoohei/ai-agent-camp/tree/main/.claude/skills/slack-unanswered
  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/minicoohei/ai-agent-camp.git /tmp/ai-agent-camp
mkdir -p .claude/skills
cp -r /tmp/ai-agent-camp/.claude/skills/slack-unanswered .claude/skills/slack-unanswered
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Slack Unanswered 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 Unanswered 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 Unanswered 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.

トリガーワード

「未返信メッセージ」「返信してないメッセージ」「Slack確認」「未読メンション」

Slack Unanswered Messages Finder

This skill finds Slack messages that need your attention and helps you reply to them.

Target Directory

All searches are performed in: slack-sync/data/

Your Identifiers

以下を自分の Slack 表示名・ユーザー名に置き換えてください。

Search for these names (case-insensitive):

  • @{YOUR_DISPLAY_NAME}
  • @{YOUR_FULL_NAME}
  • @{YOUR_SLACK_USERNAME}
  • Messages posted by: {YOUR_FULL_NAME}, {YOUR_SLACK_USERNAME}

設定方法: 上記のプレースホルダーを自分の情報に書き換えるか、--users オプションで指定してください。


Workflow

Step 1: Find Unanswered Messages

Search for messages containing your identifiers:

bash
grep -rn -B2 -A10 -E "@{YOUR_DISPLAY_NAME}|@{YOUR_SLACK_USERNAME}|{YOUR_FULL_NAME}" slack-sync/data/

Step 2: Identify Unanswered Messages

A message is unanswered if:

  1. It contains a mention of your name (or you posted it)
  2. It ends with a question (?) or contains a request
  3. There are NO lines starting with > #### immediately after it (before the next ### or ---)

Focus on recent messages (last 7 days). Exclude bot messages (Sentry, Vercel, etc.).

Step 3: Present Findings

For each unanswered message, provide:

  • Channel name
  • Date/Time
  • Sender
  • Content summary
  • Slack link
  • Whether it needs a reply or is a follow-up

Step 4: Generate Reply Draft

For messages that need replies, generate a draft reply in Japanese. Ask the user to review and edit.

Step 5: Send Reply (with confirmation)

IMPORTANT: Always get user confirmation before sending!

The reply flow is:

  1. Show the draft reply to the user
  2. Ask: "この内容で送信してよろしいですか? (修正があれば教えてください)"
  3. Wait for user confirmation or edits
  4. Only after explicit approval, use the reply script

Replying to Messages

Reply Script Location

data/slack-sync/scripts/reply_slack.py

Usage

bash
# Dry run (preview without sending)
python data/slack-sync/scripts/reply_slack.py \
  --url "https://xxx.slack.com/archives/CHANNEL/pTIMESTAMP" \
  --message "返信内容" \
  --dry-run

# Actually send (only after user confirms!)
python data/slack-sync/scripts/reply_slack.py \
  --url "https://xxx.slack.com/archives/CHANNEL/pTIMESTAMP" \
  --message "返信内容"

Environment Variable Required

SLACK_USER_TOKEN=xoxp-...

This token needs the chat:write scope. See setup instructions below.


Reply Flow Example

Claude: 以下の返信案を作成しました:

---
宛先: @{SENDER_NAME}
チャンネル: datadev-ai
Slack: [リンク](https://...)

返信案:
「担当者名のSlackアカウントは @xxx です!」
---

この内容で送信してよろしいですか? (修正があれば教えてください)

User: OKです

Claude: [reply_slack.py を実行して送信]
送信しました!

Setup: Adding chat:write Scope

To enable reply functionality:

  1. Go to Slack API Apps
  2. Select your app (e.g., "Message Archiver")
  3. Navigate to OAuth & Permissions
  4. Under User Token Scopes, add:
    • chat:write - Post messages
  5. Click Reinstall to Workspace
  6. Copy the new xoxp-... token
  7. Update SLACK_USER_TOKEN in your environment/GitHub Secrets

Message Format Reference

Messages in markdown files:

  • Main message: ### HH:MM - Sender Name [[Slack]](url)
  • Reply: Lines starting with > ####

TODO File Management

TODO File Location

slack-sync/TODO.md

TODO Format

markdown
- [ ] **[channel-name]** Sender名 (日付 時刻)
  - 内容: メッセージの要約
  - Slack: URL
  - 返信案: 返信内容のドラフト

Workflow with TODO

  1. 検索時: 未回答メッセージを見つけたらTODO.mdに追加
  2. 返信時: 返信したらチェックボックスを [x] に変更
  3. 完了時: 「完了したメッセージ」セクションに移動

Adding a Task

When you find an unanswered message, add it to slack-sync/TODO.md:

markdown
- [ ] **[datadev-ai]** {SENDER_NAME}さん (1/7 19:10)
  - 内容: 担当者名のSlackアカウント名の確認
  - Slack: https://...
  - 返信案: アカウント名を確認して回答

Completing a Task

After sending a reply:

  1. Change - [ ] to - [x]
  2. Move the item to the "完了したメッセージ" section

Quick Commands

Find mentions in recent files:

bash
grep -rn -B2 -A10 "@{YOUR_DISPLAY_NAME}" slack-sync/data/ | head -200

Find your posts:

bash
grep -rn "### [0-9:]* - {YOUR_DISPLAY_NAME}" slack-sync/data/ | head -100

Find questions to you:

bash
grep -rn -A5 "@{YOUR_DISPLAY_NAME}" slack-sync/data/ | grep -E "\?$|でしょうか|ですか|ますか|ください"

View current TODO:

bash
cat slack-sync/TODO.md

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 Slack Unanswered AI skill do?

Slackの未返信メッセージを検出し、返信ドラフトを生成するスキル。 「未返信メッセージ」「返信してないメッセージ」「Slack確認」等のリクエストで発動。

Why use Slack Unanswered on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/minicoohei/ai-agent-camp/tree/main/.claude/skills/slack-unanswered. 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 Slack Unanswered?

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 Unanswered?

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

Is the Slack Unanswered AI skill free?

It is published on GitHub by minicoohei. Check the repository for licensing terms. 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 👇