superskills

Daily repo health check — scans recent commits, CI failures, dependency drift, performance regressions, and untested code paths. Produces a grounded report with evidence-only findings and minimal, scoped fixes. Use when asked to "run daily QA", "daily repo check", "morning standup for the repo", "daily health report", or "check recent commits for bugs".

Infrastructure-as-Code security scan for changed deploy config — Dockerfiles, docker-compose, Terraform, Kubernetes/Helm, and CI/CD workflows. Flags misconfigurations and exposed secrets (root containers, open ingress, wildcard IAM, privileged pods, untrusted CI triggers). Static diff-scoped analysis (safe to auto-run); uses tfsec/checkov/hadolint/actionlint when present. Use when asked to "scan infra", "IaC scan", "check the Dockerfile/terraform/k8s", "CI security", or after changing deploy/infra config.

Comprehensive per-feature QA gate. Runs the full multi-dimensional quality fan-out (tests, correctness, security, DB, frontend perf, browser QA, coverage) scoped to the current branch's diff, then emits a pass/fail ship-readiness verdict. Run it when a feature is finished, before /finish-branch and /ship. Use when asked to "run full QA", "qa-full", "feature done — check it", "is this ready to ship", "pre-ship check", or "full quality gate".

Accessibility audit for frontend changes — WCAG 2.2 AA, screen-reader compatibility, keyboard navigation, focus management, ARIA correctness, color contrast, and reduced-motion. Static diff-scoped analysis (safe to auto-run) plus an optional dynamic axe pass against a running app. Use when asked to "check accessibility", "a11y audit", "screen reader check", "WCAG", "is this accessible", "keyboard navigation", "ARIA review", or after heavy frontend work.

Use when you have a spec or requirements for a multi-step task, before touching code. Produces an engineering plan complete with TDD tasks, DRY/SOLID/YAGNI principles, a required Test Plan & Verification section, and a coverage target — then auto-runs /plan-eng-review as an independent double-check before execution.

Use when implementing any feature or bugfix, before writing implementation code

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.

Upgrade superskills to the latest version. Pulls from GitHub, re-runs setup, and shows the version change. Use when asked to "upgrade superskills", "update superskills", or "get the latest version of superskills".

Edit any video by conversation. Transcribe, cut, color grade, generate overlay animations, burn subtitles — for talking heads, montages, tutorials, travel, interviews. No presets, no menus. Ask questions, confirm the plan, execute, iterate, persist. Production-correctness rules are hard; everything else is artistic freedom. Use when the user wants to "edit a video," "cut footage," "make a launch video," "burn captions," "add subtitles," "color grade," or process raw video files. Wraps browser-use/video-use. Requires ffmpeg + uv and one transcription backend: ElevenLabs Scribe (preferred — verbatim, diarization, audio events) OR local mlx-whisper on Apple Silicon (free, offline, no diarization). Auto-selects Scribe if `ELEVENLABS_API_KEY` is set, otherwise falls back to mlx-whisper.

Detect and fix design drift — the ad-hoc colors, spacing, type sizes, shadows, and duplicate component variants that accumulate outside the design system and harden into debt. Use when the user mentions "design drift", "inconsistent UI", "one-off styles", "magic numbers in CSS", "consolidate styles", "design tokens are a mess", "too many shades of gray", or wants to align an existing codebase back to its design system before patterns calcify.

Design like a high-end agency with exact fonts, spacing, shadows, card structures, and animations that make websites feel expensive — while avoiding the recognizable tells of AI-generated UI (side-tab borders, purple/cyan palettes, cream backgrounds, gradient text, icon-tile stacks) and using only open-licensed fonts. Use when the user wants premium visual quality, "make it look expensive", agency-level design, work that doesn't look AI-generated, or cinematic spatial rhythm.

Apply professional typographic rules to screen-based UI, including font selection that escapes the generic AI monoculture (no Inter/Roboto/Geist/Fraunces) using only open-licensed, free-for-commercial fonts. Use when generating any UI with visible text, choosing or replacing fonts, avoiding generic/AI-looking type, auditing typography violations, or when the user asks about font sizing, line height, spacing, quotes, dashes, or text formatting.

Implement a permanent cache-first strategy: check cache before hitting the DB, write to cache on first read, invalidate only when data changes. No TTL timeouts. Modeled on Play Framework's cache model. Use when asked to "add caching", "implement cache strategy", "cache DB results", or "reduce DB load".

Database performance audit — detects N+1 queries, missing indexes, join opportunities, slow queries, EXPLAIN analysis, and per-endpoint DB call counts. Use when asked to "optimize the database", "find slow queries", "check for N+1", "analyze query performance", or "audit DB calls".

Performance profiling — measures code execution time, DB call time, and identifies bottlenecks at both the application and database layer. Use when asked to "profile performance", "measure execution time", "find bottlenecks", "check response times", or "why is this slow".

Adjust communication style based on whether the user is in a relational (exploratory, hedging) or transactional (direct, technical) mode. Use when calibrating response tone, level of scaffolding, or how much to acknowledge context before answering.

Generate App Store and Google Play marketing screenshots using Next.js. Use when the user wants to create app store screenshots, marketing screenshots, or device mockup exports for iOS, iPad, or Android.

Bence's code style, tech stack, and workflow conventions

React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

Conduct systematic visual audits of existing applications and produce phased, implementation-ready design plans. Use when the user requests UI audits, visual design improvements, interface polishing, design consistency reviews, or says "make it look better" or "UI polish".

Run a structured 5-day process to prototype, test, and validate product ideas with real users. Use when the user mentions "design sprint", "validate in a week", "rapid prototype", "test with users", "de-risk before building", "GV sprint", "prototype testing", or "design workshop". Also trigger when a team needs to make a critical product decision quickly, resolve stakeholder disagreements, or test risky ideas before investing in development. Covers mapping, sketching, deciding, prototyping, and testing. For ongoing experimentation, see lean-startup. For customer job analysis, see jobs-to-be-done.

Senior UI/UX engineering system that enforces metric-based design rules, strict component architecture, CSS hardware acceleration, and balanced design engineering. Use when building premium frontend interfaces, dashboards, or SaaS UIs. Combats generic AI design patterns.

UI polish, component design, animation decisions, and invisible details that make software feel great. Encodes Emil Kowalski's philosophy on design engineering. Use when the user wants to improve animation quality, polish UI interactions, or understand what makes interfaces feel "right".

Override default LLM truncation behavior to enforce complete code generation. Use when the user asks for complete files, all components, or full implementations and you're likely to truncate. Treat partial output as broken output.

Design habit-forming product loops using the Hook Model (Trigger, Action, Variable Reward, Investment). Use when the user mentions "users arent coming back", "engagement loops", "habit formation", "push notifications", "variable rewards", "daily active users", "habit zone", or "user retention loops". Also trigger when designing notification strategies, building streaks or progress systems, or analyzing why users stop using a product after initial signup. Covers ethics evaluation and onboarding for habits. For friction reduction and B=MAP, see improve-retention. For viral sharing, see contagious.

Systematic architectural thinking that emphasizes irreplaceable human capabilities. Use when designing system architecture, making technology decisions, navigating constraints, or decomposing problems for AI execution. Covers domain modeling, systems thinking, constraint navigation, and AI-aware decomposition.

Skill for interface design (dashboards, admin panels, SaaS apps, tools) focusing on craft and consistency. Use when building product interfaces, internal tools, or complex UI systems that require intentional design decisions about hierarchy, layout, and component behavior.

iOS and Swift development expert covering Swift best practices, SwiftUI patterns, Human Interface Guidelines compliance, accessibility audits, navigation patterns, and app architecture. Use when building iOS apps, reviewing Swift code, or planning app architecture.

Create clean editorial-style interfaces with warm monochrome palette, typographic contrast, flat bento grids, and muted pastels. Use when the user wants minimalist design, editorial style, clean typography-driven UI, or "less is more" aesthetic.

Evaluate systems through an entropy/negentropy lens — is this system decaying or growing? Use when making architecture decisions, evaluating system health, or when the user mentions "entropy", "negentropy", "technical debt", "system decay", or "tacit knowledge".

Design grassroots-first campaigns for organizations facing spending disadvantages against well-funded competitors. Use when planning a launch campaign, growth strategy, or marketing with limited budget vs established competitors.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.

Guide for implementing smooth, native-feeling animations using React's View Transition API (`<ViewTransition>` component, `addTransitionType`, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter/exit of components, animate list reorder, implement directional (forward/back) navigation animations, or integrate view transitions in Next.js. Also use when the user mentions view transitions, `startViewTransition`, `ViewTransition`, transition types, or asks about animating between UI states in React without third-party animation libraries.

Upgrade existing websites and apps to premium quality by auditing current design and applying high-end standards. Use when the user wants to redesign, "make it look more professional", "upgrade the design", or remove generic AI aesthetics from an existing project.

Design AI-first interfaces that build ongoing relationships through memory, trust evolution, and collaborative planning. Use when designing agentic UX, memory-aware interfaces, or relationship-centric product experiences. NOT for general UI/UX tasks.

Software architecture and UI/UX principles for building genuinely new solutions, not derivative work. Use when designing features, architecting software, brainstorming apps, reviewing designs, or during strategy discussions. Focuses on first-principles thinking, simplicity where it matters, and creating rather than commenting.

Schedule alarms and countdown timers in iOS apps using AlarmKit. Use when implementing alarm functionality, timer features, AlarmKit integration, snooze/stop controls, Dynamic Island alarm displays, or focus mode override. Requires iOS 18+.