agentleFS
Sign inStart free
saloprjsaloprj/dialogbrain-claude-plugin/skills/connect-channel/SKILL.md

connect-channel

Skill0 starsChanged 58 days agoMITView on GitHub

Connect a messaging channel (WhatsApp, Telegram, a Telegram bot, email, Instagram, Facebook, LINE, Avito, a phone number…) to the DialogBrain workspace. Connects what needs no sign-in itself and gives the exact link for channels that need a QR scan or a browser sign-in. Use whenever someone asks to connect, add, link or hook up a channel or account.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Ask the catalogue: if unsure of the channel id: channels.connect with no arguments returns every channel with its connect mode and link.

    line 12
  2. Very specific:

    If the answer has needs_person true → this is not an error: the channel is connected by the person, not by the tool.

    line 25
  3. Distinctive:

    Do not describe where the button is in settings.

    line 28
  4. Distinctive:

    Never ask for or relay a WhatsApp, Telegram, Instagram or Google password.

    line 42
  5. Very specific:

    Never say "I connected it" when needs_person is true.

    line 45

≈ “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

Connect a channel

One tool decides: channels.connect.

Steps

  1. Ask the catalogue if unsure of the channel id: channels.connect with no arguments returns every channel with its connect mode and link. Match the person's words to an id: "whatsapp", "telegram" for a personal or business account, "telegram_bot" for a bot, "email", "instagram", "facebook", "line", "avito", "twilio_voice"…
  2. Call channels.connect with just channel.
    • Mode "credentials" → the result lists the fields. Ask the person for exactly those (say which are secret), then call channels.connect again with channel, credentials and a display_name. Email means IMAP/SMTP with an APP password — say so; the provider refuses a normal account password. The person must also give the IMAP and SMTP hosts (well known for major providers; ask otherwise). For Gmail prefer the link (Google sign-in) over IMAP.
    • If the answer has needs_person true → this is not an error: the channel is connected by the person, not by the tool. Paste the connect_url as-is and say the one line in what_the_person_does. Do not describe where the button is in settings; the link opens the dialog directly.
    • Error "billing_required" → give the billing_url from the error's data (it is also in the text); nothing works until that is done.
    • Error "permission_denied" → the person is a viewer, or the call has no signed-in person behind it; a workspace owner or admin has to do this.
  3. Confirm it took: channels.get_profile (channel_account_id) for the new account, or search.threads (query, since) once a first message arrives.
  4. Then route it: a connected channel with no agent is just an inbox. Offer the create-agent skill.

Do not

  • Never ask for or relay a WhatsApp, Telegram, Instagram or Google password. Those channels are interactive on purpose: the sign-in must not travel through a chat. Give the link.
  • Never say "I connected it" when needs_person is true. The person does the connecting; you gave the link.
  • A website widget is not a channel to connect: use the setup-livechat-widget skill.

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.

Check your setup, free