estava-mobile-app

Analyzes a new project's codebase by asking targeted questions until it has enough context, then writes a rich initial memory vault — decisions, patterns, architecture, and a seeded MOC. Use when setting up memory for the first time on a project, or when the vault is empty and agents have no prior context.

Compress natural language memory files (CLAUDE.md, AGENTS.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or "compress memory file"

Provides a deep dual-assessment design critique combining AI design review with manual pattern analysis. Use when the user wants expert design feedback, heuristic evaluation, or a thorough UX critique.

Senior UI/UX Engineer. Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when building web components, pages, artifacts, dashboards, or applications — or any request for UI/UX work, styling, beautification, or frontend code. Enforces Anti-Codex aesthetics inspired by Linear, Raycast, Stripe, and GitHub. Driven by metric dials, strict component architecture, hardware-accelerated motion, and curated design systems.

Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.

Adapts a UI for a different context, device, or format — mobile, tablet, desktop, print, or email. Use when the interface works in one context but needs to work well in another.

Review a feature and enhance it with purposeful animations, micro-interactions, and motion effects that improve usability and delight. Use when the user mentions adding animation, transitions, micro-interactions, motion design, hover effects, or making the UI feel more alive.

Use when documenting, understanding, or reviewing a project's architecture — folder layout, data flow, API surface, database design, deployment setup, and key technical decisions. Provides a documentation template any project can fill in.

Use when creating a branch or reviewing branch names. Covers type prefixes (feat, fix, docs, chore, refactor, ci), naming rules (all lowercase, hyphens only, 2-5 words), branch lifecycle from cut to delete, and correct/wrong examples.

Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.

Use when writing or reviewing TypeScript, Svelte 5 components, or API routes. Covers strict mode requirements, rune syntax ($state, $derived, $effect, $props), naming conventions, file organisation, error handling, import ordering, load() function patterns, and what never to do.

Use when writing or reviewing commit messages. Covers type prefixes (feat, fix, docs, chore, ci), scope list, subject line rules (imperative mood, 72 chars max, no period), breaking changes with ! or BREAKING CHANGE footer, body/footer format, and good/bad examples.

Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context. Call with 'craft' for shape-then-build, 'teach' for design context setup, or 'extract' to pull reusable components and tokens into the design system.

Diagnoses and fixes spatial problems — spacing, visual hierarchy, grid structure, and rhythmic flow. Use when the interface feels cramped, cluttered, unbalanced, or lacks visual hierarchy.

Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.

Use when creating or reviewing pull requests. Covers PR title format (Conventional Commits), required issue reference, three-section description template (What changed / Why / How to test), 400-line diff limit, screenshot requirements for UI changes, squash merge strategy, and review requirements.

Runs a structured discovery interview and produces a design brief before any code is written. Use when about to build something new — a component, page, feature, or UI system — to align on design intent before implementation.

Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.

Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.

Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.

Diagnoses and fixes typography — font choices, type hierarchy, readability, scale, and consistency. Use when text feels hard to read, the hierarchy is unclear, or fonts feel generic or clashing.

Scores a UI across five quality dimensions and identifies priority issues. Use when the user asks for an audit, review, quality check, or wants to know what needs fixing in their interface.

Diagnoses and fixes UI performance across loading speed, rendering, animations, images, and bundle size. Use when the user mentions slow, laggy, janky, performance, bundle size, load time, or wants a faster, smoother experience.