agentleFS
crysixcrysix/skills/discord-news/SKILL.md

discord-news

Skill1 starsChanged 28 days agoMITView on GitHub

Posts news, articles and announcements to a configured Discord channel via browser automation. Use this only when the user explicitly asks to post something on Discord, e.g. "post this to DC", "make a discord news post", "share this on Discord", "post this in the channel", "Discord message", "DC post" (or German equivalents such as "poste das im DC", "mach discord news", "teile das auf Discord"). A link shared without such a request does not trigger this skill. Once asked, start right away; do not ask whether the skill should be used.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Wait until Discord has fully loaded.

    line 36
  2. Very specific:

    Use the browser's find tool (find in Claude in Chrome) with a natural-language description such as:

    line 40
  3. Distinctive:

    Write the message in the configured post language and type it line by line in this format:

    line 52
  4. Distinctive:

    Always put the URL at the end as plain text (not a Markdown link)

    line 87
  5. Distinctive:

    Wait for an explicit yes: Never send automatically.

    line 96
  6. Distinctive:

    Only after an explicit "yes" / "send" / "go":

    line 100
  7. Distinctive:

    Wait briefly until the message appears

    line 102

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Discord News Skill

Posts formatted news messages to the configured Discord channel via browser automation.

Configuration


Workflow

Step 1: Extract the article

Fetch the content of the shared link with your web fetch tool, or navigate to the URL in the browser. Extract:

  • the article's title
  • the main message (2–3 sentences)
  • the key points (3–6 bullet points)
  • the original URL (for the link at the end)

Step 2: Navigate to the Discord channel

Navigate to the channel URL:

https://discord.com/channels/YOUR_SERVER_ID/YOUR_CHANNEL_ID

Wait until Discord has fully loaded. If a login is required, tell the user and wait.

Step 3: Find the input field

Use the browser's find tool (find in Claude in Chrome) with a natural-language description such as:

  • "message input field in the Discord channel"
  • "text box for writing a message"

Click the field to focus it.

Step 4: Type the message

⚠️ CRITICAL: line breaks in Discord Discord sends the message on Enter. Line breaks must use Shift+Enter. Never put \n into a string. Type each line separately and end it with Shift+Enter.

Write the message in the configured post language and type it line by line in this format:

[Emoji] **Bold title** [optional emoji]
[Shift+Enter]
[Shift+Enter]
One or two sentences summarizing the article.
[Shift+Enter]
[Shift+Enter]
• Key point 1
[Shift+Enter]
• Key point 2
[Shift+Enter]
• Key point 3
[Shift+Enter]
[more bullet points if needed]
[Shift+Enter]
[Shift+Enter]
🔗 https://original-url.com/article

Emoji choice (pick one that fits the topic):

  • 🔴 Breaking news / important alert
  • 🤖 AI / tech
  • 💼 Business / economy
  • 🔒 Security / privacy
  • 🚀 Startups / launches
  • 🌍 Politics / society
  • 💡 Innovation / science

Formatting rules:

  • Title in **bold** (two asterisks)
  • Bullet points with the • character
  • At most 6 bullet points; keep them concise
  • Summary: 1–2 sentences, no jargon
  • Always put the URL at the end as plain text (not a Markdown link)
  • The whole message must stay under Discord's limit of 2,000 characters

Step 5: Screenshot and confirmation

Take a screenshot that shows the finished message in the input field. Show it to the user and ask:

"The message is ready. Should I send it now?"

Wait for an explicit yes. Never send automatically.

Step 6: Send and confirm

Only after an explicit "yes" / "send" / "go":

  1. Press Enter to send the message
  2. Wait briefly until the message appears
  3. Take a final screenshot as confirmation
  4. Tell the user: "✅ Posted!"

Format example

🤖 **OpenAI and Microsoft — A New Phase** 🤝

The partnership has been fundamentally restructured. Here are the key changes.

• Microsoft remains the primary cloud partner
• OpenAI can now use other cloud providers as well
• New license structure runs until 2032, but is no longer exclusive
• Both sides retain access to jointly developed models

🔗 https://openai.com/index/next-phase

Error cases

ProblemSolution
Not logged into DiscordTell the user and wait until they have logged in
Input field not foundTake a screenshot and ask the user for help
Article cannot be fetchedAsk the user whether they want to paste the content manually
Message over 2,000 charactersShorten the bullet points, use at most 4 instead of 6

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.