Chunking Form Grouping logo

Chunking Form Grouping

Community
Deibler
chunking-form-grouping

Use this skill when designing or fixing long forms that ask the user for many fields — sign-up flows, profile setup, settings panels, checkout, intake forms, applications. Trigger when forms exceed ~6 fields, when users complain forms are "too long," when seeing high mid-form drop-off, or when picking how to break a form into sections. Sub-aspect of `chunking`; read that first.

Overview

PublisherDeibler
Repositoryuniversal-design-principles
Skill namechunking-form-grouping
Stars
9
Forks
3
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Deibler on GitHub. Read the source before you install it.

Installation

Install the Chunking Form Grouping 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/Deibler/universal-design-principles/tree/main/plugins/cognition-and-learnability-principles/skills/chunking-form-grouping
  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/Deibler/universal-design-principles.git /tmp/universal-design-principles
mkdir -p .claude/skills
cp -r /tmp/universal-design-principles/plugins/cognition-and-learnability-principles/skills/chunking-form-grouping .claude/skills/chunking-form-grouping
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Chunking Form Grouping 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 Chunking Form Grouping 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 Chunking Form Grouping 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.

Chunking applied to forms

A form with 25 fields in one continuous scroll is a wall. The same 25 fields organized into 4–5 named sections of 5–6 fields each is a list of small tasks. The total content is identical; the perceived complexity drops dramatically.

When to chunk a form

  • The form has more than ~7 fields.
  • Drop-off analytics show users abandoning mid-form.
  • Users describe the form as "long," "complicated," or "I don't know where I am."
  • The fields fall into natural categories (account info, profile info, preferences).

If the form is short (3–5 fields) or all fields belong to a single concept, chunking adds noise without benefit.

Section structure

Three patterns for chunked forms:

Single-page with named sections

All sections visible on one page; user scrolls through and fills in.

html
<form class="long-form">
  <section>
    <h2>Account</h2>
    <p class="hint">How you'll sign in.</p>
    <!-- 4-5 fields -->
  </section>

  <section>
    <h2>Profile</h2>
    <p class="hint">How others see you.</p>
    <!-- 4-5 fields -->
  </section>

  <section>
    <h2>Workspace</h2>
    <p class="hint">Set up your team space.</p>
    <!-- 4-5 fields -->
  </section>

  <button>Create account</button>
</form>

Pros: user sees total scope; can fill in any order; one save action.

Cons: the scroll can still feel long; mid-form abandonment possible.

Accordion sections (one open at a time)

Sections collapse to headers; user opens one at a time.

Pros: less visual mass; user focuses on current chunk.

Cons: total scope is hidden; users may not realize how many sections remain.

Multi-step wizard

Each section is its own page; "Continue" advances; "Back" returns.

Pros: focused attention on one chunk; easier mobile experience.

Cons: more clicks; loss of context between steps; back-button management complexity.

The right pattern depends on form length, mobile context, and whether the user benefits from seeing total scope (probably yes for sign-up; maybe not for long government forms).

Naming sections

Section names should:

  • Match the user's mental model — "Profile" not "User Information Subsystem."
  • Suggest what's inside without requiring the user to open it.
  • Be parallel in grammar — all noun phrases, or all verb phrases, not mixed.

Bad section names:

  • "Section 1 of 5" — generic; provides no structure.
  • "Required Information" — vague; everything is information.
  • "Etc." — gives up.

Good section names:

  • "Account credentials"
  • "Notification preferences"
  • "Billing address"

Section progress signals

For long single-page forms, a sticky table-of-contents or progress indicator helps:

html
<aside class="form-toc">
  <ol>
    <li><a href="#account" class="done">Account</a></li>
    <li><a href="#profile" class="active">Profile</a></li>
    <li><a href="#workspace">Workspace</a></li>
  </ol>
</aside>

For multi-step wizards, a stepper:

html
<nav class="stepper" aria-label="Progress">
  <ol>
    <li class="done">1. Account</li>
    <li class="active">2. Profile</li>
    <li>3. Workspace</li>
  </ol>
</nav>

Both let the user see where they are and how much remains.

Field count per section

Aim for 4–7 fields per section. More than that and the section itself becomes a wall; less and the section overhead exceeds its benefit.

If you find yourself with 12 fields in one logical section, ask:

  • Are all 12 actually required? (Often not; cut.)
  • Can the section split into two? (E.g., "Personal" and "Contact.")
  • Can some fields move to "later" via progressive disclosure?

Single-page vs. multi-step decision

A useful matrix:

LengthMobile-primaryRecommended
≤ 5 fieldsEitherSingle page, no sections
6–15 fieldsDesktopSingle page with named sections
6–15 fieldsMobileMulti-step or accordion
16–30 fieldsEitherMulti-step wizard
30+ fieldsEitherMulti-step + reconsider scope

The question after 30+: do you really need all this data up front? Most products can defer 60% of fields until the user has experienced value.

Anti-patterns

  • Sections without names. Visual breaks (a horizontal rule) without headings provide visual chunking but no semantic chunking. The user doesn't know what's in each.
  • Inconsistent section size. Five fields, two fields, fourteen fields. The user can't predict what's coming.
  • Required + optional mixed within sections. A user finishing what looked like a required field discovers more required fields hidden among optional ones. Worse: discovers there are required fields in a section they thought was optional.
  • Auto-advance on field change. A field that automatically moves focus or advances steps when value changes surprises the user.
  • Save state per section unclear. Multi-step wizards that don't save state per step can lose user data on navigation.

Heuristics

  1. The "name each section in 2–3 words" test. If you can't, the chunking isn't meaningful.
  2. The completion-rate audit. If sign-up completion drops below ~70% (varies by industry), the form is too long; cut, defer, or chunk better.
  3. The mobile walkthrough. Walk the form on a 375px screen. Single-page sections that feel manageable on desktop often feel oppressive on mobile.

Related sub-skills

  • chunking (parent).
  • chunking-numeric-and-otp — chunking within field values.
  • progressive-disclosure — defer optional fields rather than showing them all.
  • proximity-form-fields (perception) — visual proximity within and between sections.
  • hicks-law — fewer fields = faster decisions.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Chunking Form Grouping AI skill do?

Use this skill when designing or fixing long forms that ask the user for many fields — sign-up flows, profile setup, settings panels, checkout, intake forms, applications. Trigger when forms exceed ~6 fields, when users complain forms are "too long," when seeing high mid-form drop-off, or when picking how to break a form into sections. Sub-aspect of `chunking`; read that first.

Why use Chunking Form Grouping on TypingMind?

Because you install it once and use it with any model. Chunking Form Grouping 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 Chunking Form Grouping in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Deibler/universal-design-principles/tree/main/plugins/cognition-and-learnability-principles/skills/chunking-form-grouping. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Chunking Form Grouping?

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 Chunking Form Grouping?

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

Is the Chunking Form Grouping AI skill free?

It is published on GitHub by Deibler. Check the repository for licensing terms. 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 👇