Results for “visual-direction”

Set an ECC-specific frontend design direction for production UI work. Use when building or improving websites, dashboards, applications, components, landing pages, visual tools, or any web UI that needs stronger product-specific design judgment.

A creative-direction (taste) layer for music videos and short-form edits in the angelcore / cloud-trance / hyperpop visual family.

Delegates UI, UX, and visual design tasks to Grok 4.5 through a dedicated CLI, covering critique, art direction, HTML mockups, and SVG assets.

Set a deliberate visual direction before any UI is built — the single biggest lever against generic AI output. Derives a posture from product-soul/PRD/specs, scores a curated archetype palette, then generates 2-3 GENUINELY DISTINCT directions and compares them side-by-side before committing to one. Load when the user asks to pick an aesthetic, choose a design direction, decide what a UI should feel like, explore visual options, says "what should this look like", "make it feel like [Linear/Apple/ Duolingo]", "give me design directions", "explore some looks", or when frontend-design routes here. Replaces design-archetype. Sub-skill of frontend-design.

Draft a scene-by-scene video script with timing, visual direction, narration, and source attribution from upstream creator-media artifacts

Agent profile for art direction in 3D web design, product configurators, hero scenes, AR previews, and immersive visual interfaces.

Use for UI/UX and design-system work when Codex should convert visual direction or existing UI into reusable design tokens.

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

Provides a creative-direction layer for music videos and short-form edits, defining an angelcore/cloud-trance/hyperpop aesthetic with mood, color, light, and beat-synced editing grammar, and orchestrating video production skills into a pipeline.

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

Provides a frontend design mode for strong visual direction, UI polish, redesigns, landing pages, and production-grade interface work, including shadcn-based surfaces.

Define the visual identity of a game including art style, color palettes, character design language, environment aesthetics, and asset pipelines. Use when establishing the look and feel of a game project. Also trigger for "art style", "visual style", "game aesthetics", "color palette", "character art", "pixel art", or "game graphics".

Provides frontend design direction, design systems, visual philosophy, and production-grade UI styling for web interfaces, including layout critique, usability auditing, and asset generation.

Provides creative direction for HyperFrames videos, handling design specs, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand/style decisions.

Skeptical pushback on visual placement — both density and quality. Reads the annotated outline plus the visuals manifest and asks (a) whether the article hits the density target from editorial-principles-visuals.md, (b) whether each [VISUAL:...] earns its place, (c) whether sections without one would benefit. One revision pass on FAIL (BLOG_AGENT_VISUALS_REVISION_BUDGET, default 1).

Establish clear visual hierarchy through size, weight, color, spacing, and positioning to guide users through interfaces.

Visual Prompt Tuning

LLaVA-OneVision: Easy Visual Task Transfer

Build a visual sequence that proves, explains, and supports decisions.

Operate the VSS alert pipeline for real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, and camera onboarding.

Trains and fine-tunes vision models for object detection, image classification, and segmentation using Hugging Face Transformers on cloud GPUs, with automatic dataset validation and Hub persistence.

Evaluates text-to-image models on spatial relationship accuracy using the VISOR metric, separating object detection from spatial correctness to reveal biases like object priority and merging.

Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and production deployment with ONNX/TensorRT. Includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection frameworks. Use when building detection pipelines, training custom models, optimizing inference, or deploying vision systems.

Route frontend design and UI implementation prompts to the right design skills. Use for accessibility, frontend visual taste, redesigns, design systems, dashboards, motion, image-to-code, web/mobile image generation, Stitch, Vue conversion, UI demos, or CE frontend design.

Alignment

Visual Instruction Tuning

DriveLM: Driving with Graph Visual Question Answering

COCO: Microsoft COCO: Common Objects in Context

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Refactor SwiftUI views toward small, explicit, stable view types with MV data flow, dedicated subviews, and correct Observation usage.