brand-adaptation
Skill1 starsChanged 33 days agoMITView on GitHub
Governs the systematic adaptation and re-theming of a reference design's extracted DNA to match a target brand's identity, colors, typography, and assets while strictly preserving layout geometry, responsive flow, and interaction physics.
In this repository157 other files it gives its agents.
- agency-accounts-payable-agentSkill
- agency-agentic-identity-trust-architectSkill
- agency-agents-orchestratorSkill
- agency-automation-governance-architectSkill
- agency-business-strategistSkill
- agency-change-management-consultantSkill
- agency-chief-financial-officerSkill
- clone-websiteSkill
- agency-corporate-training-designerSkill
- agency-customer-serviceSkill
- agency-customer-success-managerSkill
- agency-data-consolidation-agentSkill
- agency-data-privacy-officerSkill
- agency-brand-guardianSkill
- design-dna-extractionSkill
- agency-image-prompt-engineerSkill
- agency-inclusive-visuals-specialistSkill
- agency-persona-walkthrough-specialistSkill
- agency-ui-designerSkill
- agency-ui-finish-gate-reviewerSkill
- agency-ux-architectSkill
- agency-ux-researcherSkill
- agency-visual-storytellerSkill
- agency-whimsy-injectorSkill
- agency-ai-data-remediation-engineerSkill
- agency-ai-engineerSkill
- agency-api-platform-engineerSkill
- agency-autonomous-optimization-architectSkill
- agency-backend-architectSkill
- agency-cms-developerSkill
- agency-codebase-onboarding-engineerSkill
- agency-code-reviewerSkill
- agency-database-optimizerSkill
- agency-database-reliability-engineerSkill
- agency-data-engineerSkill
- agency-data-visualization-engineerSkill
- agency-desktop-app-engineerSkill
- agency-devops-automatorSkill
- agency-drupal-performance-engineerSkill
- agency-drupal-shopping-cart-engineerSkill
- agency-email-intelligence-engineerSkill
- agency-embedded-firmware-engineerSkill
- agency-feishu-integration-developerSkill
- agency-filament-optimization-specialistSkill
- agency-finops-engineerSkill
- agency-frontend-developerSkill
- agency-gaussdb-expert-engineerSkill
- agency-git-workflow-masterSkill
- agency-internationalization-engineerSkill
- agency-identity-access-engineerSkill
- agency-incident-response-commanderSkill
- agency-iot-fleet-engineerSkill
- agency-it-service-managerSkill
- agency-llm-post-training-engineerSkill
- agency-minimal-change-engineerSkill
- agency-mobile-app-builderSkill
- agency-mobile-release-engineerSkill
- agency-multi-agent-systems-architectSkill
- agency-network-engineerSkill
- agency-orgscript-engineerSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Very specific: line 22
When substituting the reference font with your brand font, compensate for differing x-heights and ascender/descender metrics by fine-tuning …
- Distinctive: line 26
Ensure placeholder copy adheres to similar character lengths as the reference to prevent line wrapping anomalies.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.
Files
Brand Adaptation Skill
This skill governs transforming an extracted reference design into a custom-branded implementation. It ensures structural geometry and interaction fidelity are preserved while applying your custom brand tokens.
Core Principles
- Structural Edge Invariance:
- Sobel edge detection in
@mimera/visual-toolsmeasures structural boundaries, spatial alignments, and geometry independently of hue/saturation. - You can adapt brand colors while still running
bun mimera simulateto verify structural edge fidelity (aiming for >= 90% structural edge parity).
- Sobel edge detection in
- Deterministic Token Mapping:
- Define a 1-to-1 mapping from reference tokens to target brand tokens.
- Maintain contrast ratios and luminance hierarchy:
- Reference Dark Background -> Target Brand Dark Background
- Reference Primary Accent -> Target Brand Accent
- Reference Muted Surface -> Target Brand Surface
- Typography Substitution with Metric Compensation:
- When substituting the reference font with your brand font, compensate for differing x-heights and ascender/descender metrics by fine-tuning
line-heightandletter-spacing.
- When substituting the reference font with your brand font, compensate for differing x-heights and ascender/descender metrics by fine-tuning
- Asset & Copy Adaptation:
- Replace reference SVGs and brand logos with target SVG assets.
- Maintain the identical bounding box dimensions and
aspect-ratioto prevent layout shift. - Ensure placeholder copy adheres to similar character lengths as the reference to prevent line wrapping anomalies.
Workflow
[Extracted Reference DNA]
│
▼
┌───────────────────────────┐
│ Brand Token Transformation│
│ - Color palette remap │
│ - Font family remap │
│ - Logo / asset swap │
└───────────────────────────┘
│
▼
┌───────────────────────────┐
│ Geometry Preservation │
│ - Keep padding & margins │
│ - Keep flex/grid layout │
│ - Keep keyframe physics │
└───────────────────────────┘
│
▼
┌───────────────────────────┐
│ Structural Verification │
│ - Edge MSE >= 90% │
│ - Box alignment <= 2px dev│
└───────────────────────────┘Token Remapping Example
export const brandMapping = {
colors: {
// Reference token -> Brand token
"rgba(10, 10, 12, 1)": "var(--brand-dark-bg)",
"rgba(99, 102, 241, 1)": "var(--brand-primary-indigo)",
"rgba(255, 255, 255, 0.7)": "var(--brand-text-secondary)",
},
typography: {
displayFont: "'Cabinet Grotesk', system-ui, sans-serif",
bodyFont: "'Inter', system-ui, sans-serif",
},
assets: {
logo: "/assets/brand-logo.svg",
}
};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
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.

