Design Continuity Guard logo

Design Continuity Guard

Community
demiurg92
design-continuity-guard

Preserve an existing website or app design system when adding, moving, or restyling sections, cards, headings, backgrounds, CTAs, forms, and other UI blocks. Use before frontend changes that affect colors, gradients, section backgrounds, typography colors, spacing rhythm, visual hierarchy, component grammar, or the order of page sections; use when Codex must infer brand rules from CSS/DESIGN.md/AGENTS.md and neighboring sections instead of inventing new styles.

Overview

Publisherdemiurg92
Repositorydesign-continuity-guard
Skill namedesign-continuity-guard
Stars
12
Forks
0
Bundled files
5
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.

  • 5 bundled files

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

  • Open source

    Published by demiurg92 on GitHub. Read the source before you install it.

Installation

Install the Design Continuity Guard 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/demiurg92/design-continuity-guard/tree/main/design-continuity-guard
  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/demiurg92/design-continuity-guard.git /tmp/design-continuity-guard
mkdir -p .claude/skills
cp -r /tmp/design-continuity-guard/design-continuity-guard .claude/skills/design-continuity-guard
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Design Continuity Guard 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 Design Continuity Guard 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 Design Continuity Guard 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.

Design Continuity Guard

Purpose

Keep new UI work native to the current page. Before changing styles, recover the site's existing color language, section rhythm, component grammar, and brand constraints; then reuse or extend them conservatively.

This skill is a guardrail, not a generic design generator. It should reduce random new colors, one-off gradients, mismatched components, and section backgrounds that break the page.

Fast Path

For a small style or content change:

  1. Read local memory and design notes if present: AGENTS.md, agents.md, DESIGN.md, design.md.
  2. Inspect the target section plus the previous and next visible sections.
  3. Inspect the CSS/SCSS/Tailwind tokens that already style those sections.
  4. Reuse existing variables, classes, gradients, and text colors whenever they fit.
  5. Verify the changed area in desktop and mobile if layout or contrast could change.

Do not invent a new palette for a localized change.

Visual Audit

Before adding a new section or changing a background:

  • Identify the page sequence: hero, proof, features, catalog, cases, FAQ, CTA, contacts, footer, etc.
  • Record each nearby section's background, heading color, text color, card surface, CTA style, and visual weight.
  • Determine the page rhythm: light/dark alternation, neutral/accent cadence, gradient placement, image-led sections, card density.
  • Find brand tokens: CSS custom properties, Tailwind theme values, repeated hex/rgb/hsl colors, named utility classes, button classes.
  • Check whether the target slot needs contrast, rest, or emphasis.

If the system is unclear, run the palette extractor:

bash
python3 /path/to/design-continuity-guard/scripts/extract_visual_palette.py --root .

Use its output as evidence, not as the only source of truth.

Decision Rules

  • Prefer existing CSS variables and reusable classes over new raw color values.
  • Add a new color only when no existing token covers the needed role and the user asked for a new visual direction.
  • Do not add a new gradient if the page already has a recognizable gradient language; reuse or adapt the existing gradient.
  • Do not make every new section accent-heavy. Preserve alternation between high-emphasis, neutral, and rest sections.
  • Avoid placing two visually heavy sections next to each other unless the current page already uses that pattern.
  • If a new section sits between two similar backgrounds, choose a compatible contrast layer or a subtle divider rather than a random accent.
  • If it sits between a neutral section and a CTA/accent section, usually keep the new section calmer than the CTA.
  • Maintain heading hierarchy: use existing heading colors, accent spans, eyebrow labels, and max-width patterns.
  • Maintain card grammar: border radius, border color, shadow, surface, icon background, and hover states should match nearby cards.
  • Check contrast when changing foreground/background. If contrast is uncertain, choose the more conservative existing pair.

Section Recommendation

When proposing or implementing a new section, decide these fields before editing:

text
Position:
Neighboring sections:
Section role: neutral / proof / feature / CTA / transition / content-heavy
Background:
Heading color:
Text color:
Accent:
Cards:
CTA:
Reusable classes/tokens:
What not to add:
Verification:

Keep this internal for implementation tasks unless the user asks for a recommendation first.

When To Read References

  • Read references/section-rhythm.md when adding, reordering, or moving a section.
  • Read references/color-audit.md when brand colors/tokens are unclear or CSS is large.
  • Read references/decision-rules.md when choosing between several plausible backgrounds or accent styles.

Verification

For visual changes:

  • Run the project's build or syntax check when available.
  • Use browser screenshots or inspection for desktop and mobile when section layout, background, heading color, or CTA changes.
  • Check the target section together with its previous and next sections, not in isolation.
  • If screenshots show a new block looking detached from the page, revise colors/classes before finalizing.

Memory Boundary

Follow the project's own AGENTS.md/agents.md rules for memory updates. Add or update design memory only when a stable visual rule was discovered, such as a canonical brand token, section rhythm rule, or deprecated color pattern. Do not save one-off experiments.

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 Design Continuity Guard AI skill do?

Preserve an existing website or app design system when adding, moving, or restyling sections, cards, headings, backgrounds, CTAs, forms, and other UI blocks. Use before frontend changes that affect colors, gradients, section backgrounds, typography colors, spacing rhythm, visual hierarchy, component grammar, or the order of page sections; use when Codex must infer brand rules from CSS/DESIGN.md/AGENTS.md and neighboring sections instead of inventing new styles.

Why use Design Continuity Guard on TypingMind?

Because you install it once and use it with any model. Design Continuity Guard 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 Design Continuity Guard in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/demiurg92/design-continuity-guard/tree/main/design-continuity-guard. 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 Design Continuity Guard?

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 Design Continuity Guard?

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

Is the Design Continuity Guard AI skill free?

Yes. It is published on GitHub by demiurg92 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 👇