agentleFS
dev-ikdev-ik/ai-design-rules/skills/reference-driven-design/SKILL.md

reference-driven-design

Skill3 starsChanged 37 days agoMITView on GitHub

Build an evidence-backed visual reference brief before UI concept or polish work. Use when a product needs a modern visual direction, category-aware references, comparative design analysis, or protection from generic AI-generated styling without copying a specific brand.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No source, screenshot, product behavior, or graph context is available.

    line 27
  2. Distinctive:

    No specific brand composition or proprietary asset is copied.

    line 99
  3. Very specific:

    Use product-designer if product direction or the primary action is unclear.

    line 115
  4. Very specific:

    Use design-evidence-researcher when current evidence is missing.

    line 116
  5. Very specific:

    Use visual-designer to convert the brief into hierarchy and token decisions.

    line 117
  6. Very specific:

    Use motion-designer when continuity or interaction feedback needs movement.

    line 118
  7. Very specific:

    Use prompt-architect to encode the direction into a graph-backed prompt.

    line 119

≈ “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

Reference-Driven Design Skill

Role

Translate current product and platform references into an abstract, traceable visual direction.

Mission

Improve visual judgment without turning taste, trends, or one admired product into unsupported design rules.

When To Use

  • A user asks for a more modern, polished, premium, expressive, or product-specific interface.
  • A new surface needs a visual direction before implementation.
  • Existing UI feels generic but the workflow and object model are already clear.
  • A prompt needs reference categories and explicit anti-copy constraints.

When Not To Use

  • Product direction, user goal, or object model is unresolved.
  • The task is a narrow visual bug with an existing token and component answer.
  • No source, screenshot, product behavior, or graph context is available; record a research gap first.

Inputs

  • Product goal, primary action, audience, and platform.
  • Current UI or implementation.
  • Existing components, tokens, and product design direction.
  • Focused graph context from npm run context.
  • Supplied references or traceable current product and platform evidence.

Process

  1. Resolve graph context for the target task.
  2. Classify the surface by product type, workflow density, platform, and emotional tone.
  3. Select two or three relevant reference families, not a single brand to imitate.
  4. For each source, separate observed behavior from interpretation.
  5. Extract reusable abstractions:
    • content and functional layers;
    • hierarchy and density;
    • typography and shape roles;
    • material and color meaning;
    • state and motion behavior;
    • responsive and input adaptation.
  6. Map recommendations to existing research, rules, patterns, and tokens.
  7. Mark unsupported ideas as observations or research needs instead of instructions.
  8. Define what must not be copied: branding, proprietary assets, distinctive composition, or platform-inappropriate effects.
  9. Hand the brief to visual-designer, motion-designer, or prompt-architect.

Output Format

## Reference Brief
- Product category:
- User goal:
- Platform and density:
- Evidence date:

## Reference Matrix
| Source | Observed behavior | Reusable abstraction | Limit |
| --- | --- | --- | --- |

## Visual Direction
- Content layer:
- Functional layer:
- Focal emphasis:
- Typography and shape:
- State and motion:
- Responsive adaptation:

## Graph Traceability
- Research:
- Rules:
- Patterns:
- Missing evidence:

## Anti-Copy Boundary
- Do not copy:
- Platform constraints:

## Handoff
- Next skill:
- Reason:

Quality Checklist

  • Recommendations come from observable source behavior.
  • At least two reference families are compared when the task is exploratory.
  • Product purpose determines expression level and density.
  • Content and primary action remain dominant.
  • Platform-specific materials have fallbacks.
  • The brief names unsupported ideas as gaps.
  • No specific brand composition or proprietary asset is copied.

Related Research

  • RESEARCH-00009 Expressive System UI In 2026
  • RESEARCH-00010 Motion As State Continuity
  • RESEARCH-00011 Contextual And Observable Agentic Interfaces

Related Rules

  • RULE-00008 / VIS-001 Semantic Tokens Only
  • RULE-00014 / VIS-002 Keep Expression Subordinate To Content
  • RULE-00015 / UX-004 Use Motion To Explain State Continuity

Handoff To Other Skills

  • Use product-designer if product direction or the primary action is unclear.
  • Use design-evidence-researcher when current evidence is missing.
  • Use visual-designer to convert the brief into hierarchy and token decisions.
  • Use motion-designer when continuity or interaction feedback needs movement.
  • Use prompt-architect to encode the direction into a graph-backed prompt.

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.