Philosophy: Reject AI convergence. Claude naturally samples from high-probability design patterns (Inter fonts, purple gradients, centered layouts). This creates generic "AI slop" - safe, predictable, and forgettable designs.
Core Principle: "Make unexpected choices that feel genuinely designed for the context."
Key Insight: Steerability as a feature - Claude responds dramatically to specific guidance pushing away from convention. Dominant colors with sharp accents outperform timid, evenly-distributed palettes. Bold maximalism and refined minimalism both work - the key is intentionality, not intensity.
Prerequisites
Project Type: Next.js or React application
Dependencies (installed as needed):
npm install @react-three/fiber @react-three/drei @react-three/postprocessing framer-motion three
Verification: scripts/dependency_check.sh
Anti-Convergence Protocol
NEVER Use (Explicit Rejection List)
Category
Rejected Patterns
Fonts
Inter, Roboto, Arial, Helvetica, system-ui
Colors
Purple gradients (#6366f1, #8b5cf6, #a78bfa on light backgrounds)
Layouts
Centered hero with symmetric two-column grid
Animations
Simple fade-ins without choreography
ALWAYS Verify (4 Questions)
Before implementing ANY design element:
Have I seen this pattern in 100 other websites? → If yes, choose differently
Is this choice safe or bold? → If safe, push further
Does this reflect the specific context, or is it generic? → Must be context-specific
Am I converging on a local maximum of safety? → Continuous pushback required
If answers are Yes/Safe/Generic/Converging → STOP and choose differently
Is the element 3D?
├─ Yes → React Three Fiber
│ └─ Need glow/glass? → MeshTransmissionMaterial + Bloom
│
└─ No → Framer Motion
└─ Triggered by scroll?
├─ Yes → useScroll + useTransform
└─ No → animate prop
Comprehensive Spring Framework and Spring Boot best practices including dependency injection patterns, bean lifecycle and scopes, REST API development, Spring Data JPA, service layer design, Spring Security, testing strategies, caching, AOP, async processing, error handling, and common anti-patte...
Deploys applications to cloud Kubernetes (AKS/GKE/DOKS) with CI/CD pipelines. Use when deploying to production, setting up GitHub Actions, troubleshooting deployments. Covers build-time vs runtime vars, architecture matching, and battle-tested debugging.
19-agent team structure, decision trees for agent selection, Haiku vs Sonnet model selection, and agent collaboration principles. Use when deciding which sub-agent to invoke, understanding team responsibilities, or learning multi-agent orchestration.
Converts architecture descriptions, module specs, or workflow docs into Mermaid diagrams. Use when visualizing brick module relationships, workflows (DDD, investigation), or system architecture. Supports: flowcharts, sequence diagrams, class diagrams, state machines, entity relationship diagrams,...
INVOKE FIRST before any code work. Validates git workflow (branch, issue, worklog) and checks approach. Use at START of every task and END before completing. Prevents skipped steps.
This skill should be used when working with browser-rendered artifacts (i.e. Bun, React/React Native) to proactively validate that development work on localhost is being built appropriately and to support debugging browser-rendered content. Use this skill after making frontend changes to verify t...
Monitor Docker workers, RQ queue health, and auto-scale workers (max 4). Use when: checking job progress, monitoring queue depth, scaling workers up/down, diagnosing slow processing, or waiting for jobs to complete. Referenced by data-quality skill during reprocessing.
This skill should be used when the user wants to bump the version number in the workspace. It updates versions across all pyproject.toml files (root, tde, and tda packages) and the CHANGELOG.md to keep them synchronized.