agentleFS
markoblogomarkoblogo/abvx-agent-skills/skills/design-register-bootstrap/SKILL.md

design-register-bootstrap

Skill16 starsChanged 5 months agoMITView on GitHub

Establish frontend design context before implementation, including creator intent and preserve-theirs constraints. Use when a project lacks a clear PRODUCT.md or DESIGN.md, when the model needs to distinguish brand surfaces from product UI, or when design direction keeps drifting because audience, intent, register, anti-references, and visual constraints are not explicit.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 11 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not treat these as interchangeable.

    line 30
  2. Distinctive:

    Write a compact design register:

    line 37
  3. Distinctive:

    If context files are missing, create or update:

    line 49
  4. Very specific:

    Ask one clarifying question only when either the branch between brand and product is genuinely unclear or creator intent is too vague to …

    line 54
  5. Distinctive:

    Use the register as a constraint system for later frontend work.

    line 57
  6. Distinctive:

    When working inline, summarize:

    line 61
  7. Distinctive:

    When creating files, prefer concise machine-usable docs over long essays.

    line 73
  8. Distinctive:

    Do not default every warm or “premium” brief to beige paper backgrounds.

    line 80
  9. Distinctive:

    Do not default every technical product to dark mode.

    line 81
  10. Distinctive:

    Do not choose palette or typography before writing the surface classification.

    line 82
  11. Distinctive:

    If existing project tokens are coherent, preserve them and document them instead of replacing them.

    line 83
  12. Distinctive:

    If the repo already has a stable design system, this skill should describe and reinforce it, not invent a second one.

    line 84

≈ “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

Design Register Bootstrap

Set the design register before styling anything substantial.

This skill exists for cases where the model is about to generate UI from vague vibes, default templates, or half-remembered brand intent.

Use For

  • new frontend projects without PRODUCT.md or DESIGN.md;
  • redesigns where the surface is unclear: marketing brand page vs. app/product UI;
  • teams that keep getting mismatched typography, palette, density, or motion across tasks;
  • sessions where the agent should create or refresh design context before implementation.

Core Rule

Classify the surface first:

  • brand: marketing site, landing page, portfolio, campaign, editorial page, investor page, event page;
  • product: dashboard, admin UI, internal tool, settings, onboarding flow, forms, data-heavy app shell.

Do not treat these as interchangeable. Brand surfaces can lead with identity and emotion. Product surfaces must optimize comprehension, workflow, and control clarity.

Workflow

  1. Read current evidence:
    • project files, CSS tokens, component library, screenshots, references, user brief;
    • any existing PRODUCT.md, DESIGN.md, brand notes, or design tokens.
  2. Write a compact design register:
    • surface type: brand or product;
    • audience;
    • first-screen job;
    • creator intent: what the person is actually trying to make possible;
    • preserve-theirs: what must remain recognizably theirs;
    • brand/product lane;
    • anti-references: what this should explicitly not resemble;
    • color strategy: restrained, committed, full palette, or drenched;
    • typography direction;
    • motion tolerance;
    • density and radius rules.
  3. If context files are missing, create or update:
    • PRODUCT.md for audience, product lane, workflow, tone, creator intent, preserve-theirs, and anti-references;
    • DESIGN.md for colors, typography, spacing, component patterns, creator intent, preserve-theirs, and do/don't rules.
  4. Ask one clarifying question only when either the branch between brand and product is genuinely unclear or creator intent is too vague to guide a real design choice. If neither blocks a real choice, move.
  5. Use the register as a constraint system for later frontend work. Do not restyle pages in the same pass unless the task explicitly includes implementation.

Output Shape

When working inline, summarize:

  • register
  • audience
  • creator intent
  • design thesis
  • preserve-theirs
  • anti-references
  • color strategy
  • typography direction
  • motion and density

When creating files, prefer concise machine-usable docs over long essays.

Guardrails

  • Skip this skill when an existing design register is coherent and the task only needs implementation or a narrow visual fix; preserve the existing context instead of recreating it.
  • Do not default every warm or “premium” brief to beige paper backgrounds.
  • Do not default every technical product to dark mode.
  • Do not choose palette or typography before writing the surface classification.
  • If existing project tokens are coherent, preserve them and document them instead of replacing them.
  • If the repo already has a stable design system, this skill should describe and reinforce it, not invent a second one.

Final Report

Include:

  • whether the surface was classified as brand or product;
  • files created or updated;
  • unresolved uncertainty;
  • downstream skills recommended, such as frontend-taste-layer, frontend-product-builder, or web-quality-audit.

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.