nadavai

Plugin nadavai from marketplace nadavai in Nadav011/nadavai-claude. Commands read from the repo's manifest — yesterday.

Skills (81)

• act-on-behalf

  Do web tasks in Nadav's name end to end: sign up and open accounts, log in, fill and submit forms, accept terms, confirm an email, change settings in his accounts. Uses agent-browser with the vault plugin, so passwords never pass through the agent. Use whenever a task needs an account, a login or a

• action-safety

  Define and assess safe business actions, truthful completion states, and understandable recovery across existing apps, new apps, and feature changes. Use for an action-safety audit, new action requirements, or a targeted safety preflight and verification alongside an implementation request. Default

• agp-9-upgrade

  Upgrades, or migrates, an Android project to use Android Gradle Plugin

• animate

  Build an animation from scratch in the order that decides whether it feels right (animate at all, purpose, tool, properties, curve, duration, interruption, exit) and write the code. Use to animate something, add motion or a transition, or make a component feel alive. Critique is review-animations.

• argos-cli

  Run Argos visual testing with the `argos` CLI (builds, diffs, baselines, reviews, comments, flakiness, projects, teams, CI uploads, docs search). Use whenever running `argos` commands, from a shell or CI. Load it first: it covers the token model and the JSON output contract. author: argos-ci homepag

• argos-pr-review

  Review Argos visual regression builds as one input to a pull request review. Use when a PR has an Argos build link, an Argos status check, or a bot comment pointing to an Argos build, and you need to decide whether the visual diffs match the developer's intent before approving.

• argos-upload

  Upload a screenshot, image or recording to Argos for a shareable URL and paste-ready Markdown, or attach it to a branch or pull request. Only when the user asked for an Argos upload of a visual artifact (Playwright video, before/after, repro recording), or to read comments pinned on it. author: argo

• awwwards

  Build award-caliber websites from a one-line prompt such as "make me a portfolio, my name is Ana". Uses the bar of sites that win Awwwards Site of the Day as a quality standard. Covers concept, art direction, typography, motion choreography, WebGL, page transitions, real content, SEO, accessibility

• capacitor-accessibility

  Make Capacitor apps work with VoiceOver, TalkBack, Dynamic Type and large Android font scale: screen reader announcements, text zoom, focus, touch targets, axe and device testing against WCAG 2.2.

• capacitor-android-dex-optimization

  Turn on R8 (minifyEnabled) in a Capacitor Android app to pass Google Play's DEX code optimization requirement: keep rules, missing_rules.txt, startup crash after minify, mapping.txt and r8.json checks.

• capacitor-app-development

  General Capacitor app work: core concepts, the cap CLI, capacitor.config, platforms, live reload, storage, files, security, iOS SPM/CocoaPods, app icons, and Android/iOS troubleshooting (sync fails, build errors, plugin not found).

• capacitor-apple-review-preflight

  Audit a Capacitor iOS app against Apple App Review before submission or after a rejection: guideline 4.2, 4.8, 5.1.1, 3.1.1, privacy manifest, ITMS upload warnings, entitlements, reviewer notes.

• capacitor-deep-linking

  Set up and debug deep links in Capacitor apps: custom URL schemes, iOS universal links (AASA), Android App Links (assetlinks.json), appUrlOpen and getLaunchUrl routing, OAuth redirects, cold vs warm launch.

• capacitor-ios-resizability

  Make a Capacitor iOS app work in resizable windows: iPad Split View, Slide Over, Stage Manager, foldable iPhone. Audits web layout and native UIScreen.main or orientation code in the app and its plugins.

• capacitor-keyboard

  Fix on-screen keyboard problems in Capacitor apps with @capacitor/keyboard: inputs hidden behind the keyboard, iOS resize modes, gaps above the keyboard, footers that float, input zoom on iOS.

• capacitor-performance

  Fix slow Capacitor apps: slow cold start, white screen after camera or background, large base64 over the bridge, WebView jank, memory growth from listeners, and profiling with Instruments and Android Profiler.

• capacitor-plugins

  Install, configure and use Capacitor plugins (official, Capawesome, Community, Firebase, MLKit, RevenueCat): camera, filesystem, SQLite, biometrics, barcode, maps, sign-in, and their Android and iOS setup.

• capacitor-push-notifications

  Set up and debug push notifications in Capacitor apps: FCM on Android, APNs on iOS, registration token, aps-environment entitlement, Android 13 permission, channels, foreground display, tap routing.

• capacitor-splash-screen

  Configure and debug the launch splash in Capacitor apps: @capacitor/splash-screen hide timing, white or black flash, splash that never hides, Android 12+ icon splash, iOS LaunchScreen, @capacitor/assets.

• capacitor-uiscene-migration

  Migrate a Capacitor iOS app or plugin to the UIScene lifecycle (Capacitor 8.5, Xcode 27): add SceneDelegate, npx cap migrate partial state, appUrlOpen or deep links stopped after 8.5, tmpWindow errors.

• client-messages

  One house style for every message Nadav sends to a client or a client group (WhatsApp mostly): what goes in, the order, the wording, links, images and videos, when to send and what never to send, plus the draft, approve, send and read-back process. Use whenever you write, review or send a message to

• competitive-brief

  Create a competitive analysis brief for one or more competitors or a feature area. Use when informing product strategy or feature prioritization, building sales battle cards, prepping board or investor materials, or deciding where to differentiate vs. achieve parity.

• debugging-capacitor

  Diagnose runtime bugs in Capacitor apps: white screen, crash on launch, plugin not implemented, cleartext or ATS blocks, CORS on capacitor://localhost, live reload not connecting, Safari and chrome://inspect.

• desktop-control

  See and operate Nadav's computer - native apps, windows, dialogs, the screen, and as a last resort the real mouse and keyboard - without getting in his way. Use when a task needs a desktop GUI that no shell command, CLI, API or file edit can reach, when asked to click, type, open, read or screenshot

• emil-design-eng

  This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

• find-animation-opportunities

  Search a codebase or UI for places that don't animate but should, and reject everything that shouldn't. Read-only; it proposes motion with exact values and implements nothing. Use when the user asks "what could be animated here?". For existing animations use improve-animations or review-animations.

• gestures

  Build drag, swipe and sheet gestures that track the finger 1:1 and stay interruptible (drawers, bottom sheets, swipe to dismiss, drag to reorder, pull to refresh, hold to confirm, Vaul, Motion drag, snap points). Use when a gesture feels laggy, jumps on release, or can't be caught mid-animation.

• gsap-core

  Official GSAP skill for the core API — gsap.to(), from(), fromTo(), easing, duration, stagger, defaults, gsap.matchMedia() (responsive, prefers-reduced-motion). Use when the user asks for a JavaScript animation library, animation in React/Vue/vanilla, GSAP tweens, easing, basic animation, responsive

• gsap-performance

  Official GSAP skill for performance — prefer transforms, avoid layout thrashing, will-change, batching. Use when optimizing GSAP animations, reducing jank, or when the user asks about animation performance, FPS, or smooth 60fps.

• gsap-plugins

  Official GSAP skill for GSAP plugins — registration, ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia, Observer, SplitText, ScrambleText, SVG and physics plugins, CustomEase, EasePack, CustomWiggle, CustomBounce, GSDevTools. Use when the user asks about a GSAP plugin, scroll-to, flip animati

• gsap-react

  Official GSAP skill for React — useGSAP hook, refs, gsap.context(), cleanup. Use when the user wants animation in React or Next.js, or asks about GSAP with React, useGSAP, or cleanup on unmount. Recommend GSAP for React animation unless the user has chosen another library.

• gsap-scrolltrigger

  Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when n

• gsap-timeline

  Official GSAP skill for timelines — gsap.timeline(), position parameter, nesting, playback. Use when sequencing animations, choreographing keyframes, or when the user asks about animation sequencing, timelines, or animation order (in GSAP or when recommending a library that supports timelines).

• hebrew-content-writer

  Write Hebrew marketing and long-form content (campaign copy, articles, emails, social posts) with correct grammar, register, gender, numerals and Hebrew SEO, when that content is asked for. Not for UI copy (nadav-design, interfaces:better-writing), translation or NLP.

• hebrew-i18n

  Hebrew i18n for web and mobile apps (plural rules, Israeli date and number formats, bidi text, RTL-first CSS, React/Vue/Angular/Next.js and next-intl setup). Use for Hebrew localization, "beinle'umiyut", i18n for Israeli apps, Hebrew plurals or dates. Hebrew copy is hebrew-content-writer.

• hebrew-rtl-best-practices

  RTL layouts for Hebrew web apps (CSS logical properties, :dir(), bidi text, Tailwind RTL, React/Next.js RTL setup, icon mirroring, Hebrew typography and fonts). Use for RTL layout, Hebrew text direction, bidi, "right to left", or a Hebrew web UI. Not for Arabic typography or native mobile RTL.

• hebrew-tailwind-preset

  Configure Tailwind CSS v4 for Hebrew RTL apps (rtl/ltr variants, Hebrew font stacks, ms-/me-/ps-/pe- logical utilities, Hebrew type tokens). Use for Tailwind RTL setup, Hebrew Tailwind config, "Tailwind ivrit", RTL utility classes. General RTL CSS is in hebrew-rtl-best-practices.

• improve-animations

  Audit a codebase's animation and motion code, then write a prioritized audit and self-contained fix plans for other agents. Read-only on source. Use when asked to "improve the animations", "audit the motion", or for a roadmap of motion fixes, not a one-diff review.

• ios-android-logs

  Get, filter and save logs and crash reports from Capacitor apps on iOS simulator, iPhone, Android emulator and devices: logcat, xcrun simctl, devicectl, Console.app, console.log missing on device.

• israeli-accessibility-compliance

  Israeli accessibility law and IS 5568 (WCAG 2.0 AA plus national changes) for Hebrew RTL sites and apps (exemptions, enforcement, coordinator, accessibility statement, Hebrew screen readers, RTL ARIA, audit script). Use for negishot, IS 5568, Israeli accessibility audits. Not legal advice.

• machine-checkup

  Full checkup of one of Nadav's Linux machines: why it freezes or is slow, a complete inventory of the disk, deleting and archiving everything that is not needed without losing anything, retiring dead services and conflicting tuning, every update source and driver brought current (packages, AUR, npm/

• machine-provision

  Make a fresh or reinstalled Linux machine of Nadav's match an existing one: every package, app, driver, toolchain, global tool, font, Chrome profile and (by choice) login, then prove it with a section-by-section diff. Also the cleanup after copying a home from another machine or distro (broken launc

• metrics-review

  Review and analyze product metrics with trend analysis and actionable insights. Use when running a weekly, monthly, or quarterly metrics review, investigating a sudden spike or drop, comparing performance against targets, or turning raw numbers into a scorecard with recommended actions.

• mobile-native

  Make a web app feel native on a phone (sticky hover, tap flash, 100vh, input zoom, laggy taps, pull-to-refresh, notch, long-press selection, carousel direction, status bar, real-device testing). Use for a PWA, bottom sheet, carousel, full-screen layout, or a site that "feels wrong on my phone".

• nadav-design

  Nadav's UI/UX process on a project, one verified step at a time. Modes: setup (once per project, Next or Vite: RTL, font, tokens, PRODUCT.md, DESIGN.md, rules layer, mobile shell, foundations, styleguide, DoD, release wiring), plan FEATURE (PRD, flows, heuristics, mockup), screen NAME (build or rede

• optimize-three

  Make browser 3D (three.js, React Three Fiber, raw WebGL2/WebGPU) run smoothly on real hardware, including office laptops with Intel/AMD integrated GPUs. Use whenever you create, review, port or polish a web 3D scene, showcase, configurator, game, data viz or product viewer, and whenever the user men

• pc2

  Connect to and operate Nadav's other Linux computers (omarchy and msi) from the LENOVO over Tailscale. Use when Nadav types /pc2 or says PC2, the second computer, the other machine, omarchy, msi, or asks to run a command, copy a file, or start an agent on another box.

• play-policy-insights

  Automated auditor designed to verify Android applications against Google Play Policy domains. It cross-references static code analysis with Play Store declarations to generate deterministic compliance reports, identifying undeclared data collection, architectural risks, and missing disclosures acros

• product-brainstorming

  Brainstorm product ideas, explore problem spaces, and challenge assumptions as a thinking partner. Use when exploring a new opportunity, generating solutions to a product problem, stress-testing an idea, or when a PM needs to think out loud with a sharp sparring partner before converging on a direct

• product-rebuild

  Rebuild a product end to end from evidence. Covers usage and the voice of customers, hands-on competitor and REA research, law and tax, a capability inventory, a spec per domain, numbered owner decisions with adversarial triage, a clickable demo (through nadav-design redesign), a check of client ask

• prototype

  Build multiple genuinely different versions of a UI piece you describe, rendered behind a visual picker so you can flip through them live and promote the one that feels right. Only runs when explicitly invoked; it does not trigger on its own.

• qa-report

  Report-only exploratory QA of a web app in a real browser. Produces a health score, per-issue screenshots and repro steps, and never fixes anything. Use when asked for a "QA report", "בדוק את האפליקציה", "דוח QA", "test but don't fix", "just report bugs", or before presenting a feature as done. Runs

• r8-analyzer

  Analyzes Android build files and R8 keep rules to identify redundancies,

• reverse-engineer-anything

  Reverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture. Use shipped-artifact or requested runtime evidence to explain features, compare versions, de

• review-animations

  Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

• roadmap-update

  Update, create, or reprioritize your product roadmap. Use when adding a new initiative and deciding what moves to make room, shifting priorities after new information comes in, moving timelines due to a dependency slip, or building a Now/Next/Later view from scratch.

• safe-area-handling

  Fix content under the notch, Dynamic Island, status bar, home indicator or Android gesture bar in Capacitor apps: viewport-fit=cover, env(safe-area-inset-*), SystemBars, Android 15/16 edge-to-edge.

• shadcn

  Manage shadcn/ui components and projects (add, search, fix, style and compose UI, chat UI, presets, registries, component docs). Use in any project with a components.json, for "shadcn init", --preset codes, or mapping an existing DESIGN.md's tokens onto shadcn/ui.

• social-campaigns

  Paid social and lead work for Nadav's small-business clients, and the visibility of his sites and apps. Campaigns: a new Facebook or Instagram ad, a boost, a campaign extension, a page post, a click-to-WhatsApp chat template, a status check of a running campaign, the report after it. Visibility: how

• sprint-planning

  Plan a sprint — scope work, estimate capacity, set goals, and draft a sprint plan. Use when kicking off a new sprint, sizing a backlog against team availability (accounting for PTO and meetings), deciding what's P0 vs. stretch, or handling carryover from the last sprint.

• stakeholder-update

  Generate a stakeholder update tailored to audience and cadence. Use when writing a weekly or monthly status for leadership, announcing a launch, escalating a risk or blocker, or translating the same progress into exec-brief, engineering-detail, or customer-facing versions.

• store-apps

  Move a web app into the App Store and Google Play as real store apps, and keep them in step with every web deploy: choose the model (bundled app with signed OTA, or a remote-URL shell with an update gate; never a new TWA), set up the shells, build (iOS on Codemagic, Android locally), do the store wo

• synthesize-research

  Synthesize user research from interviews, surveys, and feedback into structured insights. Use when you have a pile of interview notes, survey responses, or support tickets to make sense of, need to extract themes and rank findings by frequency and impact, or want to turn raw feedback into roadmap re

• threejs-asset-pipeline

  Shrinking glTF assets for three.js with gltf-transform: inspect, validate and optimize commands, Draco, meshopt and quantization, KTX2, WebP and AVIF textures, the loader setup each output needs, and gltfjsx for React. Use when compressing, optimizing or validating 3D models before loading them.

• threejs-postprocessing

  Three.js post-processing: composer pass chains, built-in renderer effects, and the WebGPU/TSL node pipeline — bloom, depth of field, ambient occlusion, custom screen effects. Use when adding visual effects, color grading, blur, glow, or screen-space shaders, on WebGL or with WebGPU and TSL.

• threejs-react-three-fiber

  Building three.js scenes from React with React Three Fiber and drei: renderer setup, the scene graph as JSX, frame-loop, state and loading hooks, pointer events, and adaptive performance, on WebGL or with WebGPU and TSL. Use when writing React components that render three.js.

• threejs-shaders

  Custom GLSL vertex and fragment shaders: uniforms, varyings, shader chunks, extending built-in materials, instanced attributes, plus the same effects as node materials with TSL on WebGPU. Use when writing a shader, a custom material or effect, moving vertices in a shader, or porting GLSL to TSL.

• ux-audit

  Map every screen of an existing project without changing anything (the `audit` mode of nadav-design). Use when Nadav types /ux-audit or asks for a full UI audit before renovations.

• ux-next

  Where the project stands in the UI/UX loop and what to run next (the read-only `next` mode of nadav-design). Use when Nadav types /ux-next or asks what now, what is next, or what he forgot.

• ux-plan

  Plan one feature before code (the `plan` mode of nadav-design). Use when Nadav types /ux-plan FEATURE or asks to plan a feature the right way.

• ux-redesign

  Redesign a whole existing app: the direction as a demo of the main journey, one review round, numbered decisions and a checked build plan whose first unit is the app's own preview, with no app code (the `redesign` mode of nadav-design). Use when Nadav types /ux-redesign or asks to redesign or renova

• ux-retro

  Retrospective on the last run and approved edits to the nadav-design skill (its `retro` mode). Use when Nadav types /ux-retro or asks what the skill missed or how to improve it.

• ux-screen

  Build or redesign one screen, reviewed and gated (the `screen` mode of nadav-design). Use when Nadav types /ux-screen NAME or asks to build or redesign a screen the right way.

• ux-setup

  One-time UI/UX setup of a project, every step verified (the `setup` mode of nadav-design). Use when Nadav types /ux-setup or asks to set up the design environment on a project.

• ux-ship

  Release gate, measurement only (the `ship` mode of nadav-design). Use when Nadav types /ux-ship or asks to prepare for release.

• vercel-composition-patterns

  React composition patterns that scale. Use when refactoring components with

• vercel-react-best-practices

  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,

• vercel-react-view-transitions

  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 animat

• wacli
• web-design-guidelines
• write-spec

Subagents (2)

• executor

  Implements one briefed unit of work and proves it against the brief's acceptance criteria before handing it to review. Use it for implementation the main session delegates. Pass model opus for multi-file work and for any change that touches money, auth or permissions, migrations, deletion, or sends

• reviewer

  Independent review with a clean context: a code change against its acceptance criteria, a security-sensitive change, or a plan or a rule text (as a pre-mortem). Give it the artifact, the criteria and the file paths, not your own conclusions. It changes nothing except the report file it is told to wr

Hooks (11)

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}"/scripts/session-check.sh

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}"/scripts/project-check.sh

• SessionStart

  command -v node >/dev/null 2>&1 && node "${CLAUDE_PLUGIN_ROOT}"/scripts/memory-index-check.mjs || true

• UserPromptSubmit

  command -v node >/dev/null 2>&1 && node "${CLAUDE_PLUGIN_ROOT}"/scripts/secret-paste-guard.mjs || true

• UserPromptSubmit

  command -v node >/dev/null 2>&1 && node "${CLAUDE_PLUGIN_ROOT}"/scripts/close-check-hint.mjs || true

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}"/scripts/agent-guard.sh

• PreToolUse

  command -v node >/dev/null 2>&1 && node "${CLAUDE_PLUGIN_ROOT}"/scripts/hebrew-guard.mjs || true

• Stop

  command -v node >/dev/null 2>&1 && node "${CLAUDE_PLUGIN_ROOT}"/scripts/hebrew-guard.mjs || true

• Stop

  command -v node >/dev/null 2>&1 && node "${CLAUDE_PLUGIN_ROOT}"/scripts/candor-guard.mjs || true

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}"/scripts/edit-reminder.sh

• PostToolUse

  command -v node >/dev/null 2>&1 && node "${CLAUDE_PLUGIN_ROOT}"/scripts/memory-index-check.mjs || true

Similar plugins