cubetiq/design
workflows/workflows/agent-environment-setup/platforms/copilot/skills/design/SKILL.md
Top-level design routing and critique skill for choosing the right system, web, mobile, or desktop design path, running audit-first diagnosis, and keeping downstream execution aligned to one clear contract.
$ install --global
skillsauthnpx skillsauth add cubetiq/cubis-foundry designInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 4, 2026, 10:49 AM216.1s19 files scanned
SKILL.md
- name:
- design
- description:
- Top-level design routing and critique skill for choosing the right system, web, mobile, or desktop design path, running audit-first diagnosis, and keeping downstream execution aligned to one clear contract.
Design
Purpose
Provide the routing and critique layer for design work once the UI-design intent is established. Use it directly for audit-first diagnosis or downstream of frontend-design when the task now needs route selection, critique language, and strict execution boundaries.
Working Model
Before any execution route is chosen, require four explicit inputs:
- style contract
- visual thesis
- content plan
- interaction thesis
Use these to keep the request focused on the real design problem instead of drifting into generic visual advice.
Normalize the brief before routing when the request is messy. Capture product, users, top tasks, target surfaces, states, accessibility target, motion tolerance, and brand adjectives using references/foundation.md, references/output-template.md, and assets/brief-template.json.
When to Use
- Diagnosing why a UI feels generic, inconsistent, or weak before making edits
- Choosing between browser-first, mobile-first, and desktop-first design execution
- Establishing or refreshing system-level visual direction before screen work
- Keeping multiple design improvements aligned under one direction
Instructions
- Start by classifying the request as routing, critique, systemization, browser execution, mobile execution, or desktop execution.
- Require the style contract plus the visual thesis, content plan, and interaction thesis before selecting the owning surface.
- Run audit-first when the interface already exists and quality is uncertain. Use the scoring cues in
references/scoring-rubric.md, identify the primary failure dimension, and route from that diagnosis instead of from taste alone. - Load
references/foundation.mdfirst when the task spans more than one surface so shared nouns, tokens, and state language are settled before platform-specific execution. - Use
../design-system/SKILL.mdwhen the canonical visual language, token language, or component vocabulary must be refreshed before screen work. - Choose
../web-ui-design/SKILL.mdfor browser-first execution,../mobile-ui-design/SKILL.mdfor phone-first execution, and../desktop-ui-design/SKILL.mdfor desktop-first execution. Do not flatten those surfaces into one copied layout. - Use
references/responsive-adaptive-systems.mdplus the surface-specific reference docs when the same product spans more than one surface family or major size class. - Keep this surface at the routing and critique layer: return the route, why it fits, the next owning surface, and the non-negotiable constraints.
- Use
references/execution-contract.mdandreferences/output-template.mdwhen the answer needs a stricter handoff contract.
Deterministic Helper
When the user needs a structured audit, adaptive matrix, or reusable prompt pack for multiple surfaces, use scripts/ui_blueprint_tool.py with assets/brief-template.json or assets/sample-brief.json instead of improvising the schema each time.
Route-First Constraints
- preserve the style contract the design direction depends on
- preserve the visual thesis the user actually needs
- preserve the content plan the layout must serve
- preserve the interaction thesis that changes how the UI feels
- reject generic advice that does not change the chosen route or the downstream artifact
Anti-patterns
- Do not give generic style advice detached from product purpose, state design, or interaction cost.
- Do not skip hierarchy, readability, or affordance in favor of pure aesthetics.
- Do not collapse routing, systemization, and execution into one blended answer.
- Do not bypass
frontend-designwhen the public request is still ambiguous and needs a clearer UI-design front door. - Do not keep users on the fragmented
frontend-design-*helper stack when a simpler route throughfrontend-design,design-system,web-ui-design,mobile-ui-design, ordesktop-ui-designis clearer.
Output Format
Return:
- The chosen design route
- The primary diagnosis or reason that route fits the task
- The next owning surface and exact artifact it should produce
- The non-negotiable anti-generic constraints that must survive downstream execution
References
../frontend-design/SKILL.mdreferences/scoring-rubric.mdreferences/foundation.mdreferences/design-directions.mdreferences/web-ui-design.mdreferences/mobile-app-ui-design.mdreferences/desktop-app-ui-design.mdreferences/responsive-adaptive-systems.mdreferences/output-template.mdreferences/agent-driven-ui.mdreferences/polish-accessibility-motion.mdreferences/visual-direction.mdreferences/design-tokens.mdreferences/execution-contract.md../design-system/SKILL.md../web-ui-design/SKILL.md../mobile-ui-design/SKILL.md../desktop-ui-design/SKILL.mdassets/brief-template.jsonassets/sample-brief.jsonscripts/ui_blueprint_tool.py
Related Skills
cubetiq/deep-research
tools
VerifiedTrustedCommunity
Use when investigating latest vendor behavior, comparing tools or platforms, verifying claims beyond the repo, or gathering external evidence before implementation.
1SKILL.mdUpdated Apr 4, 2026
cubetiq/database-design
documentation
VerifiedTrustedCommunity
Use when designing database schemas, normalization strategies, indexing plans, query optimization, and migration workflows for relational, document, or hybrid data stores.
1SKILL.mdUpdated Apr 4, 2026
cubetiq/csharp-best-practices
development
VerifiedTrustedCommunity
Use when writing, reviewing, or refactoring modern C#/.NET code, including minimal APIs, records, async streams, pattern matching, DI lifetimes, and memory-efficient performance tuning.
1SKILL.mdUpdated Apr 4, 2026
cubetiq/code-review
development
VerifiedTrustedCommunity
Use when conducting code reviews, building review checklists, calibrating review depth, providing structured feedback, or establishing team review practices. Covers review methodology, feedback patterns, automated checks, and batch review strategies.
1SKILL.mdUpdated Apr 4, 2026