Spacing System logo

Spacing System

Organization
KyaniteLabs
spacing-system

Use when layout rhythm, density, or gaps feel arbitrary or inconsistent, or when one product needs different reading pressures without splitting into unrelated spacing systems.

Overview

PublisherKyaniteLabs
Repositorytastecheck
Skill namespacing-system
Stars
10
Forks
7
Bundled files
3
LicenseMIT
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.

  • 3 bundled files

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

  • Open source

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

Installation

Install the Spacing System 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/KyaniteLabs/tastecheck/tree/main/skills/spacing-system
  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/KyaniteLabs/tastecheck.git /tmp/tastecheck
mkdir -p .claude/skills
cp -r /tmp/tastecheck/skills/spacing-system .claude/skills/spacing-system
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Spacing System 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 Spacing System 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 Spacing System 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.

Spacing System (the scale nobody owns)

Every gap uses one --space-* scale; relationships create composition, not arbitrary margins.

The decision order

  1. Start with the 4px-base ladder 4/8/12/16/24/32/48/64/96px and --space-section: clamp(48px, 32px + 4vw, 96px) defaults. An alternate bounded scale needs brief and observed-hierarchy evidence.
  2. Map attachment, control, task, group, region, and chapter to visibly different steps (roughly ≥1.5× between levels), or document a content-pressure exception.
  3. Choose metronomic or intentional syncopated section rhythm from content pressure; explain it.
  4. Use gap and one-direction logical margins; explain any arbitrary-margin exception.

Let content set the rhythm

Map operational tasks to compact predictability and editorial/narrative content to breathing room; retain one system and explain differing roles. Use the role map first:

RelationshipShared tokenCompact operational rhythmLong-form editorial rhythm
attachment--space-1 (4px)icon/state to its labelinline metadata pair
control--space-2/3 (8/12px)label-to-control / inside a controlclaim-to-citation / tight evidence pair
task--space-4 (16px)repeated queue itemadjacent paragraph or evidence group
group--space-5 (24px)task-group breakdiscrete finding
region--space-6/7/8 (32/48/64px)console-region breaknarrative subsection or causal pivot
chapter--space-section (fluid)major workflow viewmajor account transition

The console may be metronomic; an account may widen at finding, subsection, and chapter boundaries. One vocabulary, different relationships—not two scales.

Invariants and defaults

Invariant craft: audit margin/padding/gap; make proximity truthful and whitespace intentional; keep one explainable vocabulary. Ladder, clamp, separation, and rhythm are brief-dependent defaults; rendered overrides record scale, map, and tradeoff.

Migration and honest audit boundary

Classify every literal by relationship. Starter disposition: 13px→12px (--space-3), 17px→16px (--space-4), bare 24px→var(--space-5); override only with observed hierarchy evidence. Keep 19px unresolved; do not silently round it. Sole prose exception: documented following-paragraph 1em spacing.

Use assets/spacing-starter.css as fixture/start. Without a target CSS fixture, mark audit PENDING, name it and the next action; never claim residual off-scale values are gone. The ladder, map, and migration rules remain required.

Evidence

Audit source before describing it; map each value to a role. Handoff one Markdown table with status, reason, remediation, evidence, and provenance, covering scale, off-scale, proximity, rhythm, and handoff. PENDING names missing source/next action; it blocks that check, not placeholder proof.

Rhythm map

Name attachment, control, task, group, region, and chapter; show compact/editorial selection without parallel scales. Replace, justify as observed exception, or leave each arbitrary value PENDING with source and next action.

Authoritative self-check

Include exactly one labeled Authoritative self-check. It confirms ladder/clamp or evidence-backed override, all six relationships, context selection, migration, and honest fixture boundary. Judge reasoning/evidence, not literal starter values.

Deliver

Deliver base, token scale, role map, context rhythm, off-scale audit, and one authoritative self-check. responsive-layout owns breakpoint reflow, not scale/proximity/reading pressure; hand it --space-* and the evidence table. Send control/form relationships to component-states or form-ux, not re-decide their behavior.

References

  • references/decision-records.md — novel-case ADR rules.
  • assets/spacing-starter.css — ladder, layout primitives, migration helpers.

Contract (generated)

Canonical detail: contract.json.

  • Route: An interface needs a spacing scale, content-derived rhythm, or gap consistency (+1 in contract.json); avoid: The request is only responsive reflow or component state behavior (+1 in contract.json)
  • Exclude: Do not impose one uniform cadence across dissimilar content (+1 in contract.json)
  • Stop / handoff: Pause when content hierarchy is absent and spacing would be arbitrary (+1 in contract.json); receives [design-system-interview, improve-existing-website, tasteroll, web-typography] -> sends [responsive-layout, component-states, form-ux]
  • Output: A tokenized spacing scale and stated section-rhythm strategy tied to content hierarchy
  • Evidence: table_with_evidence with status, reason, remediation, evidence, provenance.

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 Spacing System AI skill do?

Use when layout rhythm, density, or gaps feel arbitrary or inconsistent, or when one product needs different reading pressures without splitting into unrelated spacing systems.

Why use Spacing System on TypingMind?

Because you install it once and use it with any model. Spacing System 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 Spacing System in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/KyaniteLabs/tastecheck/tree/main/skills/spacing-system. 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 Spacing System?

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 Spacing System?

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

Is the Spacing System AI skill free?

Yes. It is published on GitHub by KyaniteLabs under the MIT 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 👇