Loading...
Loading...
Found 10,205 Skills
When something goes wrong, the user must be able to recover or try again. Toasts, inline errors, banners, and notification patterns each have a specific role. Use when designing error states, success confirmations, async feedback, in-place editing, or any system that communicates state changes to the user.
Derive a full UI colour palette algorithmically from one or two brand colours. Darker and lighter variants for interactive states, desaturated greys from the brand hue for borders and backgrounds, and semantic colours that feel coherent with the brand rather than generic. Use when building a colour system from scratch or expanding a limited brand palette for UI use.
Tabs organise related content under a shared context — switching tabs swaps the view without leaving the page. Use when a screen has multiple distinct content areas that share a common header or action set, and when the user needs to switch between them frequently. Use when designing tabbed layouts, content panels, settings pages, detail views, or dashboards with multiple data views.
UI patterns borrowed from the physical world feel immediately intuitive — cards feel graspable, carousels feel scrollable, drawers feel pullable. Use real-world metaphors deliberately to reduce the learning curve and make interactions feel natural. Use when designing layout patterns, gestures, or navigation paradigms.
Use when writing, reviewing, debugging, or documenting LanceDB pipelines in Python or TypeScript, especially code that should work across local LanceDB OSS tables and remote LanceDB Enterprise/Cloud tables. Helps avoid non-portable full-table materialization, choose idiomatic query/search patterns, apply LanceDB performance defaults for ingestion, indexing, filtering, and diagnostics, and resolve connections to the remote server for Enterprise-only operations such as jobs.
Anti AI Slop: Design & Copy Rules. The core rules filter for AI coding agents. Load always to stop generic AI slop.
Implement, migrate, design, review, and troubleshoot haptic feedback with Software Mansion Pulsar across React Native, iOS, Android, Kotlin Multiplatform, Flutter, and Web. Use when the user names Pulsar; a Pulsar package such as react-native-pulsar, com.swmansion:pulsar, com.swmansion:pulsar-kmp, pulsar_haptics, or pulsar-haptics; a Pulsar import, preset, composer, setting, installation, migration, or runtime problem; or explicitly requests migration to Pulsar. Do not use for generic haptics, vibration, Core Haptics, browser Vibration API, expo-haptics, animation, audio, motion, or UI-polish work without Pulsar evidence or explicit Pulsar intent.
Complete onboarding guide for developers who are new to Detour, the open-source deferred deep linking SDK by Software Mansion. Use this skill whenever a user asks what Detour is, how to get started with Detour, how to set up deep linking with Detour, how to install the Detour SDK, how to configure the Detour dashboard, or how deferred deep linking works. Also use it when the user has no prior deep linking setup and wants to add deep links to their app. Covers everything from zero to production: account setup, dashboard configuration, Universal Links and App Links, platform SDK integration for React Native, iOS, Android, and Flutter, analytics, and architecture.
Use when creating or updating a requested static documentation artifact from established information without changing product behavior.
Use when the user mentions migrating deep links, switching away from Branch or AppsFlyer, replacing their deep linking SDK, setting up Detour deep linking for the first time, or asks how Branch/AppsFlyer concepts map to Detour. Covers the complete migration end to end - Detour Dashboard configuration, Universal Links and App Links setup, SDK swap with code examples, and analytics migration. Works across Android, iOS, React Native, and Flutter.
Multi-layer validation pattern - validates data at EVERY layer it passes through to make bugs structurally impossible, not just caught.
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.