Orchestrates a multi-agent loop involving planning, development, review, and publishing sub-agents to implement and publish features test-first and with high standards compliance.
日本語の概要は準備中です。原文の説明を表示しています。
Interact with Slack workspaces safely via dedicated Python helper scripts. Allows reading unread messages, channels, threads, searching messages, sending messages, and reacting with emojis without direct CLI execution.
日本語の概要は準備中です。原文の説明を表示しています。
実行スコア 未検証
インストール方法を見るインストールする前に、エージェントに与えられる指示の中身を確認できます。
This skill enables the agent to safely interact with Slack workspaces using a curated suite of Python scripts.
[!IMPORTANT] Strict Tool Policy: No Direct Raw CLI Fallback Do NOT invoke the raw
slackcliexecutable directly. You must ONLY use the approved Python scripts located in:./scripts/This ensures safe operations, eliminates accidental destructive actions (e.g. channel deletion or token exposure), and provides normalized output.
All scripts reside in ./scripts/. Run them using python3 <script-path> [options].
get_unread.py - Check Unread MessagesQuickly scan for channels, DMs, or threads with unread messages or mentions.
# Human-readable summary table
python3 ./scripts/get_unread.py
# Machine-readable JSON output
python3 ./scripts/get_unread.py --json
list_channels.py - Discover Channels and DMsList public/private channels and conversations you have access to.
# List all channels
python3 ./scripts/list_channels.py
# Filter channels by name
python3 ./scripts/list_channels.py --filter "general"
# Filter by type and limit results
python3 ./scripts/list_channels.py --types public,private --limit 20
read_channel.py - Read Recent Channel or DM MessagesFetch recent messages from any channel, private group, or direct message conversation. Automatically formats timestamps and resolves user IDs to human-readable names and handles.
# Read recent messages from a channel by name
python3 ./scripts/read_channel.py questions --limit 10
# Read by channel ID or #channel
python3 ./scripts/read_channel.py "#questions" --limit 20
# Read only top-level channel messages (exclude threaded replies)
python3 ./scripts/read_channel.py questions --exclude-replies
# Programmatic JSON extraction
python3 ./scripts/read_channel.py questions --limit 10 --json
read_thread.py - Read Message Thread RepliesInspect an entire conversation thread, displaying the parent message and all subsequent replies chronologically.
# By channel and thread parent timestamp
python3 ./scripts/read_thread.py questions 1791446699.326619
# By Slack permalink URL
python3 ./scripts/read_thread.py --permalink "https://workspace.slack.com/archives/C0123/p1791446699326619"
search_messages.py - Search Workspace HistorySearch across messages you have access to using keywords or Slack query operators (after:YYYY-MM-DD, has:link, etc.).
# Search query across conversations
python3 ./scripts/search_messages.py "Thinkpad"
# Search in a specific channel
python3 ./scripts/search_messages.py "deploy" --in general
# Search from a specific user
python3 ./scripts/search_messages.py --from alice --limit 10
send_message.py - Post Messages & Thread RepliesSend a message to a channel, DM, or thread.
[!TIP] Always use
--dry-runto preview and validate the message target before posting to a shared or public channel.
# Preview / Dry run (does not send anything)
python3 ./scripts/send_message.py \
--recipient "#questions" \
--message "Hello team" \
--dry-run
# Post to a channel or user
python3 ./scripts/send_message.py \
--recipient "#general" \
--message "Deployment completed."
# Post reply in an existing thread
python3 ./scripts/send_message.py \
--recipient "#questions" \
--thread-ts 1791446699.326619 \
--message "I found the charger!"
react_message.py - Add or Remove Emoji ReactionsReact to any Slack message using emoji names (without colons).
# Add a reaction
python3 ./scripts/react_message.py \
--channel questions \
--timestamp 1791446699.326619 \
--emoji thumbsup
# Remove a reaction
python3 ./scripts/react_message.py \
--channel questions \
--timestamp 1791446699.326619 \
--emoji thumbsup \
--remove
get_user_info.py - Look Up User ProfilesRetrieve user profile details, email, timezone, and account status.
python3 ./scripts/get_user_info.py @username
python3 ./scripts/get_user_info.py user@example.com
edit_message.py - Edit Existing MessagesReplace the text of an existing message you posted.
python3 ./scripts/edit_message.py \
--channel questions \
--timestamp 1791446699.326619 \
--message "Updated message text"
mark_read.py - Mark Channels as ReadMark a specific channel or all unread channels as read.
# Mark all unread channels as read
python3 ./scripts/mark_read.py --all
# Mark a specific channel as read up to latest message
python3 ./scripts/mark_read.py questions
# Mark up to a specific timestamp
python3 ./scripts/mark_read.py questions --ts 1791446699.326619
--dry-run first or ask the user to confirm the text and target channel.questions, #questions, @username, or email addresses) as well as Slack IDs (C049..., U09A...).--json to any script.まだレビューはありません。使ってみた感想をお寄せください。
ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。
まだコメントはありません。最初のコメントを書いてみませんか。
Orchestrates a multi-agent loop involving planning, development, review, and publishing sub-agents to implement and publish features test-first and with high standards compliance.
日本語の概要は準備中です。原文の説明を表示しています。
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
日本語の概要は準備中です。原文の説明を表示しています。
Generates comprehensive AI context, AGENTS.md, and structured documentation in a context/ directory for any brownfield codebase using Tree-sitter AST extraction, dependency analysis, predefined python scripts, and orchestrated subagents.
日本語の概要は準備中です。原文の説明を表示しています。
Manual browser testing and automation using Chrome DevTools MCP server. Handles port management, app launch, browser automation, login, and end-to-end testing.
日本語の概要は準備中です。原文の説明を表示しています。
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
日本語の概要は準備中です。原文の説明を表示しています。
Progressively investigate PRs, commits, releases, and project evolution. Start with a lightweight assessment, dynamically deepen analysis based on complexity and risk, use subagents for independent investigations, and maintain evidence-backed project knowledge.
日本語の概要は準備中です。原文の説明を表示しています。