Vague mood descriptions make visual direction difficult to communicate. Feeling Search uses a cached lexicon to suggest named styles and matching vocabulary, with optional paid cloud analysis.

Renovation choices can make everyday cleaning and storage more difficult. This guide uses a Chinese renovation knowledge base to suggest practical, room-specific alternatives.

Changing image text manually can require rebuilding fonts and backgrounds. This skill guides MakeItSay edits that replace or remove selected lines while preserving their appearance.

Flat images combine subjects, text, and backgrounds, making separate edits difficult. This skill guides Unmerge processing to return positioned PNG layers with reconstructed hidden areas.

Creating consistent visual assets across formats requires repeated research and setup. This skill combines searchable design references, asset generators, and HTML workflows.

Separate interface reviews can duplicate issues and obscure the most important fixes. This skill coordinates specialist reviews into one evidence-based report ranked by user impact.

Les interfaces générées génériques semblent souvent prévisibles et faibles. Cette compétence guide Claude, Codex et Claude Code vers une conception frontend distinctive et prête pour la production.

Recréer manuellement le langage visuel d’un site public est lent et source d’incohérences. Cette compétence extrait des couleurs, polices, espacements, rayons, ombres et fichiers de tokens de départ à examiner.

Lip-sync workflows require different models for existing videos, portraits, and scripts. This skill selects a suitable RunComfy route and prepares the corresponding CLI workflow.

Short video generation requires clear motion prompts and valid model settings. This skill guides HappyHorse 1.0 requests through RunComfy with documented settings and audio direction.

Targeted image edits can change details you want to preserve. This skill provides RunComfy commands and focused prompts for background changes, text replacement, and reference-based composition.

Generic image prompts often produce polished illustrations instead of quick industrial design sketches. This skill combines four style variants, rendering settings, ink post-processing, and measurements for more consistent sketchbook pages.

Video production requires coordinating creative direction, generated assets, timing, and delivery. This skill guides Hypit workflows from reference analysis to editable composition and reviewed exports.

Les équipes livrent souvent des interfaces incohérentes parce que les tokens, les composants et la documentation évoluent séparément. Cette compétence fournit à Claude, Codex et Claude Code des recommandations structurées pour des design systems évolutifs.

Mobile teams often design from isolated inspiration and miss the patterns that shape successful app journeys. This skill guides structured research of top-grossing apps, screens, flows, and UI elements before implementation.

Mobile interfaces often feel inconsistent when controls, navigation, motion, and loading states are designed separately. This skill provides one practical Expo and React Native workflow.

Les équipes produisent souvent des documents dont les couleurs, la typographie, la mise en page et les messages manquent de cohérence. Cette compétence applique les normes Acme et vérifie si le contenu présente des violations courantes de la marque.

Product teams can build quickly before testing their assumptions. This skill reviews user needs, evidence, and business viability to define a bounded next step.

La modélisation Grasshopper peut nécessiter de nombreuses étapes répétées liées aux composants, aux connexions et aux paramètres. Cette skill transforme des notes de conception structurées en fichiers de workflow exécutables et en actions MCP locales.

Poor furniture sizing and storage choices can make a home dining room difficult to use. This skill uses Chinese renovation references to guide practical decisions.