agentleFS
saloprjsaloprj/dialogbrain-claude-plugin/skills/setup-livechat-widget/SKILL.md

setup-livechat-widget

Skill0 starsChanged 57 days agoMITView on GitHub

Put a DialogBrain chat widget on a website — create it, restrict it to the site's domains, hand over the two script tags, and make sure an agent answers. Use when someone asks for a chat widget, live chat, a chat bubble on their site, or "how do I put DialogBrain on my website".

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Do not invent a widget key or a script URL.

    line 38
  2. Very specific:

    Do not leave allowed_domains empty on a real site: the key is public and the domain list is what stops someone else spending this agent.

    line 40

≈ “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

Set up a LiveChat widget

A widget is one installation: its own key, its own look, its own allowed domains. Most businesses need exactly one.

Steps

  1. Ask for two things before creating anything: the site's domain (with and without www — they count as different) and the name to show in the panel header. Everything else has good defaults.
  2. Create it with widgets.create: name, primary_color, position ("bottom-right" unless told otherwise), header_title, display_mode ("chat"), auto_reply_mode ("draft" so a person approves the first replies).
  3. Restrict and polish with widgets.update: widget_id, allowed_domains (the list from step 1), header_subtitle (an honest expectation such as "we reply within minutes"), greeting_text.
  4. Get the snippet with widgets.get_embed_code (widget_id) and show it verbatim. It is two script tags; tell the person to paste them before </body> on every page, or into their tag manager. Platform notes: https://dialogbrain.com/help/livechat-widget (#wordpress, #shopify, #wix).
  5. Make sure someone answers, and check it, do not assume it. agents.list (status "active"), then agents.get on each candidate and look at its triggers: the widget is answered only by an enabled incoming_message trigger whose channel_types include "livechat" or has no channel filter at all. Nine active agents with no such trigger means nobody answers. If that is the case, say so plainly and offer the create-agent skill. A widget with no agent collects conversations nobody answers.

Do not

  • Do not invent a widget key or a script URL. The snippet comes from widgets.get_embed_code only.
  • Do not leave allowed_domains empty on a real site: the key is public and the domain list is what stops someone else spending this agent.

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.