More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Explain Message: Decode a Confusing Slack Message

    1

    Work messages arrive in someone else's shorthand, and replying without understanding them goes badly. Your agent reads the whole thread, says in plain words what it asks of you, and drafts a reply.

    Free

    Security scanned
    Explain Message: Decode a Confusing Slack Message

    Explain Message: Decode a Confusing Slack Message

    Example session with this skill installed

    https://yourteam.slack.com/archives/C0123/p1700000000 help me understand this, what is she asking me?

    • Read your context and instructions
    • Compiled the explain message

    The agent reads the thread and the 10 messages before it, and opens the linked dashboard. It answers: she is asking you to approve moving 40 leads to a different sales rep by Thursday. In plain words, those leads have had no contact in 30 days and she wants to reassign them so someone follows up. Example: one named lead from the list, last contacted in September. Your call: approve, with one exception it names. Then a draft reply opening with her name, your approval, and the exception.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    About this skill

    A salesperson's pipeline terms, an engineer's code names, or a block pasted from a colleague's AI agent can be hard to read when you were not in the context it came from. The usual move is to guess, or to ask a question that shows you did not follow.

    This skill reads the full Slack thread, not only the linked message, and the 10 messages before it if the thread starts mid-topic. It opens up to 3 links, files, PRs, or docs that the meaning depends on, and reads the README or notes of any project the message names that you work on. The answer has five fixed parts: what they are asking you to do, or "nothing, FYI only"; what the message says in 2 to 4 plain sentences with no code identifiers, acronyms, or internal names you did not use; one concrete example; the decision or reply it needs, with a recommendation; and a reply ready to paste that opens with the person's name and the action, then the deadline.

    The proof

    There is no measurement for this skill, and the listing claims none. Its check is a final gate the agent runs before sending: could you act on the answer without asking "what does that mean"? Any sentence that holds a term you did not use gets rewritten. The draft reply uses only facts and dates you gave, so it does not invent a deadline or a commitment.

    What you get

    One SKILL.md with the reading procedure, the five-part answer shape, and the plain-language gate.

    How to use

    1. Add the skill folder to your agent's skills directory (for Claude Code, ~/.claude/skills/explain-message/).
    2. Paste a Slack link or the message text and say "help me understand this" or "how should I respond?"
    3. Read the first line for what is asked of you, then edit the draft reply and send it yourself.

    Source and license

    Free to use and MIT licensed. The full source, install steps, and issue tracker are on GitHub at https://github.com/robertmnyborg/everyday-agent-skills.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Productivity.

    Without a Slack tool it works only from the text you paste and misses the rest of the thread. It reads at most 3 linked items, and cannot open private docs it has no access to. It drafts but never sends. The plain-language gate depends on the agent knowing which terms you use.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 8 days ago

    • Free with an Agensi account

    Nothing to install. It runs in your AI agent.

    Optional
    A Slack connector
    orMCP tool for reading threads

    Permissions

    Allowed Hosts

    your Slack workspace, through your connector

    File Scopes

    README
    or
    notes
    of
    a
    named
    project
    (read)

    Read-only. It never posts to Slack.

    Listed8 days ago

    What's inside

    Frequently Asked Questions

    Agents will explain a message, but usually from the one message you pasted and in the same jargon. This skill reads the thread and linked items first, and rewrites any sentence that uses a term you did not use.

    No. With a Slack tool it reads the full thread. Without one, paste the message and it works from that and says so.

    Yes. It is one SKILL.md with no scripts, so any agent that reads SKILL.md can use it.

    No. It drafts the reply for you to edit and send.

    On GitHub at https://github.com/robertmnyborg/everyday-agent-skills, under the MIT license. Every file in this package is there, plus the README and install steps.

    New in Productivity

    Free