Agent Academy is a free, source-linked library of skills, prompts, MCP servers and bot templates, organised into courses by profession, for people who hand real work to AI agents: 1,467 live resources, each with its original link, license and safety tags.
Skill
slack-messaging
Original text · EnglishGuidance for composing well-formatted, effective Slack messages using mrkdwn syntax
Republished in full under its license, with attribution. The source is authoritative.
name: slack-messaging
description: Guidance for composing well-formatted, effective Slack messages using mrkdwn syntax
Slack Messaging Best Practices
This skill provides guidance for composing well-formatted, effective Slack messages.
When to Use
Apply this skill whenever composing, drafting, or helping the user write a Slack message — including when using slack_send_message, slack_send_message_draft, or slack_create_canvas.
Slack Formatting (mrkdwn)
Slack uses its own markup syntax called mrkdwn, which differs from standard Markdown. Always use mrkdwn when composing Slack messages:
Format
Syntax
Notes
Bold
*text*
Single asterisks, NOT double
Italic
_text_
Underscores
Strikethrough
~text~
Tildes
Code (inline)
`code`
Backticks
Code block
``code``
Triple backticks
Quote
> text
Angle bracket
Link
`<url\
display text>`
Pipe-separated in angle brackets
User mention
<@U123456>
User ID in angle brackets
Channel mention
<#C123456>
Channel ID in angle brackets
Bulleted list
- item or • item
Dash or bullet character
Numbered list
1. item
Number followed by period
Common Mistakes to Avoid
Do NOT use bold (double asterisks) — Slack uses *bold* (single asterisks)
Do NOT use ## headers — Slack does not support Markdown headers. Use *bold text* on its own line instead.
Do NOT use [text](url) for links — Slack uses <url|text> format
Do NOT use --- for horizontal rules — Slack does not render these
Message Structure Guidelines
Lead with the point. Put the most important information in the first line. Many people read Slack on mobile or in notifications where only the first line shows.
Keep it short. Aim for 1-3 short paragraphs. If the message is long, consider using a Canvas instead.
Use line breaks generously. Walls of text are hard to read. Separate distinct thoughts with blank lines.
Use bullet points for lists. Anything with 3+ items should be a list, not a run-on sentence.
Bold key information. Use *bold* for names, dates, deadlines, and action items so they stand out when scanning.
Thread vs. Channel Etiquette
Reply in threads when responding to a specific message to keep the main channel clean.
Use reply_broadcast (also post to channel) only when the reply contains information everyone needs to see.
Post in the channel (not a thread) when starting a new topic, making an announcement, or asking a question to the whole group.
Don't start a new thread to continue an existing conversation — find and reply to the original message.
Tone and Audience
Match the tone to the channel — #general is usually more formal than #random.
Use emoji reactions instead of reply messages for simple acknowledgments (though note: the MCP tools can't add reactions, so suggest the user do this manually if appropriate).
When writing announcements, use a clear structure: context, key info, call to action.
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`,…
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar…
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Use after generating code, after accepting AI suggestions, or when reviewing AI-written modules. Also use when code works but feels brittle, when error handling seems thin, when orphaned resources or missing cleanup are suspected, or when the agent claims done but hidden debt may exist. Catches the specific failure patterns AI agents produce that humans would not.