Claude Skills

Use when writing UI tests, recording interactions, tests have race conditions, timing dependencies, inconsistent pass/fail behavior, or XCTest UI tests are flaky - covers Recording UI Automation (WWDC 2025), condition-based waiting, network conditioning, multi-factor testing, crash debugging, and accessibility-first testing patterns

Use when CAAnimation completion handler doesn't fire, spring physics look wrong on device, animation duration mismatches actual time, gesture + animation interaction causes jank, or timing differs between simulator and real hardware - systematic CAAnimation diagnosis with CATransaction patterns, frame rate awareness, and device-specific behavior

Reference for App Store Connect crash analysis, TestFlight feedback, metrics dashboards, and data export workflows

subject not detected, hand pose missing landmarks, low confidence observations, Vision performance, coordinate conversion, VisionKit errors, observation nil, text not recognized, barcode not detected, DataScannerViewController not working, document scan issues

Vision framework API, VNDetectHumanHandPoseRequest, VNDetectHumanBodyPoseRequest, person segmentation, face detection, VNImageRequestHandler, recognized points, joint landmarks, VNRecognizeTextRequest, VNDetectBarcodesRequest, DataScannerViewController, VNDocumentCameraViewController, RecognizeDocumentsRequest

Use when encountering BUILD FAILED, test crashes, simulator hangs, stale builds, zombie xcodebuild processes, "Unable to boot simulator", "No such module" after SPM changes, or mysterious test failures despite no code changes - systematic environment-first diagnostics for iOS/macOS projects

Use when fixing VoiceOver issues, Dynamic Type violations, color contrast failures, touch target problems, keyboard navigation gaps, or Reduce Motion support - comprehensive accessibility diagnostics with WCAG compliance, Accessibility Inspector workflows, and App Store Review preparation for iOS/macOS

Use when implementing haptic feedback, Core Haptics patterns, audio-haptic synchronization, or debugging haptic issues - covers UIFeedbackGenerator, CHHapticEngine, AHAP patterns, and Apple's Causality-Harmony-Utility design principles from WWDC 2021

Always-on rule-oriented guidance for claude-plugin agents. Use to align behavior, tool usage, and model-specific defaults (GPT-5.2-code vs Opus 4.5) while avoiding deprecated bd/cass references.

Multi-agent coordination patterns for OpenCode swarm workflows. Use when work benefits from parallelization or coordination.

Augmented cognition layer that makes users smarter by connecting conversations to their persistent knowledge tree. Use proactively when topics arise that might have prior knowledge, and when users ask to remember, recall, search, or organize. Triggers on technical discussions, decision-making, project work, "remember this", "recall", "what do I know about", or any knowledge request.

Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns for attaching non-invasive metadata to Git objects.

Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.

Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development.

Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.

Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.