Results for “visual-consistency”

Structured visual QA verdict for screenshot-to-reference comparisons

Structured visual QA verdict for screenshot-to-reference comparisons

Use when designing or building any user interface to ensure consistency, usability, and visual quality across all user-facing applications. This skill provides core UI/UX principles and standards for the enterprise ecosystem.

COCO: Microsoft COCO: Common Objects in Context

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).

Alignment

NLVR2: A Visual Reasoning Benchmark for Natural Language

Create systematic QA checklists to verify that design implementations match specifications across visual accuracy, layout, interaction, content, accessibility, and cross-platform categories.

Generates structured VGL JSON for Bria FIBO models, giving deterministic control over objects, lighting, camera, composition, and style instead of natural language prompts.

Validates rendered UI with browser or Playwright screenshots after implementation, redesign, responsive changes, or visual regressions.

Visual Instruction Tuning

Improved Baselines with Visual Instruction Tuning

Check a screen's brand expression by comparing it against mood, voice, and design token reference files, flagging divergences and suggesting corrections.

Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.

Mantis: Interleaved Multi-Image Instruction Tuning

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

Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. (gstack)

TextVQA: Towards Reasoning about Text in Images

DriveLM: Driving with Graph Visual Question Answering

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md. Identifying inconsistencies, duplications, ambiguities, and underspecified items.

Guardian of V.A.I.R.E. quality standards (Value/Agency/Identity/Resilience/Echo). Handles pre-release evaluation, scorecard assessment, and pass/fail determination. Use when UX quality gates are needed. Does not write code.

Design clear, accessible data visualizations with appropriate chart selection and styling.

LLaVA-NeXT: Improved Reasoning, OCR, and World Knowledge

SynthText: Synthetic Data for Text Detection

The craft of designing icons that communicate instantly across cultures, contexts, and scales. Icon design bridges semiotics, cognitive psychology, and visual craft to create symbols that users understand without thinking. Great icons are invisible in the best way - they convey meaning so naturally that users never pause to decode them. This skill covers icon grid systems, optical alignment, stroke consistency, metaphor selection, scalability across sizes, SVG optimization, and icon set coherence. The best icon designers understand that icons are a visual language - each icon must speak the same dialect while carrying its own distinct meaning. Use when "icon, iconography, symbol, glyph, icon set, icon library, pictogram, svg icon, icon grid, icon pack, feather icons, lucide, phosphor, heroicons, icon system, icon style, icons, iconography, svg, symbols, glyphs, pictograms, ui-icons, icon-set, visual-design, design-system" mentioned.