Widget Coherence logo

Widget Coherence

Organization
serac-labs
widget-coherence

Build Service Portal widgets (sp_widget) with synchronized server/client/HTML — data.* initialization, ng-click + controller method matching, c.server.get action handlers, and Angular directive usage.

Overview

Publisherserac-labs
Repositoryserac
Skill namewidget-coherence
Stars
77
Forks
28
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by serac-labs on GitHub. Read the source before you install it.

Installation

Install the Widget Coherence AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/serac-labs/serac/tree/main/packages/skills/widget-coherence
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/serac-labs/serac.git /tmp/serac
mkdir -p .claude/skills
cp -r /tmp/serac/packages/skills/widget-coherence .claude/skills/widget-coherence
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Widget Coherence in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Widget Coherence on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Widget Coherence is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Widget Coherence for ServiceNow Service Portal

Service Portal widgets MUST have perfect communication between Server Script, Client Controller, and HTML Template. This is not optional - widgets fail when these components don't talk to each other correctly.

The Three-Way Contract

Every widget requires synchronized communication:

1. Server Script Must:

  • Initialize ALL data.* properties that HTML will reference
  • Handle EVERY input.action that client sends via c.server.get()
  • Return data in the format the client expects

2. Client Controller Must:

  • Implement EVERY method called by ng-click in HTML
  • Use c.server.get({action: 'name'}) for server communication
  • Update c.data when server responds

3. HTML Template Must:

  • Only reference data.* properties that server provides
  • Only call methods defined in client controller
  • Use correct Angular directives and bindings

Data Flow Patterns

Server → Client → HTML

javascript
// SERVER SCRIPT
;(function () {
  data.incidents = []
  data.loading = true

  var gr = new GlideRecord("incident")
  gr.addQuery("active", true)
  gr.setLimit(10)
  gr.query()

  while (gr.next()) {
    data.incidents.push({
      sys_id: gr.getUniqueValue(),
      number: gr.getValue("number"),
      short_description: gr.getValue("short_description"),
    })
  }
  data.loading = false
})()
javascript
// CLIENT CONTROLLER
api.controller = function ($scope) {
  var c = this

  c.selectIncident = function (incident) {
    c.selectedIncident = incident
  }
}
html
<!-- HTML TEMPLATE -->
<div ng-if="data.loading">Loading...</div>
<div ng-if="!data.loading">
  <div ng-repeat="incident in data.incidents" ng-click="c.selectIncident(incident)">
    {{incident.number}}: {{incident.short_description}}
  </div>
</div>

Client → Server (Actions)

javascript
// CLIENT CONTROLLER
c.saveIncident = function () {
  c.server
    .get({
      action: "save_incident",
      incident_data: c.formData,
    })
    .then(function (response) {
      if (response.data.success) {
        c.data.message = "Saved successfully"
      }
    })
}
javascript
// SERVER SCRIPT
if (input && input.action === "save_incident") {
  var gr = new GlideRecord("incident")
  gr.initialize()
  gr.setValue("short_description", input.incident_data.short_description)
  data.new_sys_id = gr.insert()
  data.success = !!data.new_sys_id
}

Validation Checklist

Before deploying a widget, verify:

  • Every data.property in server is used in HTML or client
  • Every ng-click="c.method()" has matching c.method in client
  • Every c.server.get({action: 'x'}) has matching if(input.action === 'x') in server
  • No orphaned methods or unused data properties
  • All data.* properties are initialized in server (even if empty)

Common Failures

Action Name Mismatch

javascript
// CLIENT - sends 'saveIncident'
c.server.get({ action: "saveIncident" })

// SERVER - expects 'save_incident' (MISMATCH!)
if (input.action === "save_incident") {
}

Method Name Mismatch

html
<!-- HTML - calls saveData() -->
<button ng-click="c.saveData()">Save</button>
javascript
// CLIENT - defines save() (MISMATCH!)
c.save = function () {}

Undefined Data Properties

html
<!-- HTML - references user.email -->
<span>{{data.user.email}}</span>
javascript
// SERVER - only sets user.name (user.email is undefined!)
data.user = { name: userName }

Angular Directives Reference

DirectivePurpose
ng-ifConditionally render element
ng-show/ng-hideToggle visibility (element stays in DOM)
ng-repeatIterate over array
ng-clickHandle click events
ng-modelTwo-way data binding
ng-classDynamic CSS classes
ng-disabledDisable form elements

Frequently asked questions

What does the Widget Coherence AI skill do?

Build Service Portal widgets (sp_widget) with synchronized server/client/HTML — data.* initialization, ng-click + controller method matching, c.server.get action handlers, and Angular directive usage.

Why use Widget Coherence on TypingMind?

Because you install it once and use it with any model. Widget Coherence is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Widget Coherence in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/serac-labs/serac/tree/main/packages/skills/widget-coherence. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Widget Coherence?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Widget Coherence?

As many as you like. As long as a model supports skills, you can use Widget Coherence with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Widget Coherence AI skill free?

Yes. It is published on GitHub by serac-labs under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇