Mobile

AI-native E2E testing orchestration for Claude Code. Use when creating, running, or managing end-to-end test scenarios with visual evidence capture. Activates for tasks involving E2E tests, browser automation testing, test scenario creation, test execution with screenshots, or checking test status.

Extract panel schedule data from images using constraint-first approach

Design and configure embedded Superset dashboards for internal tools and customer apps with theming, RLS, SSO, and scalable UX.

Create distinctive, production-grade iOS interfaces with SwiftUI. Use this skill when the user asks to build iOS screens, components, or views. Generates polished, native-feeling code that goes beyond generic templates while respecting Apple's Human Interface Guidelines.

Dynamic agent composition and management system. USE WHEN user says create custom agents, spin up custom agents, specialized agents, OR asks for agent personalities, available traits, agent voices. Handles custom agent creation, personality assignment, voice mapping, and parallel agent orchestration.

調査結果や分析レポートを4層構造（エグゼクティブサマリー→概要→詳細→Appendix）で整理し、意思決定者向けに構造化します。レポート作成時や既存ドキュメントの再構成時に使用してください。

Analyze code diffs and commit messages between current branch and target branch to generate comprehensive Pull Request descriptions in markdown format. Automatically selects appropriate PR template and creates structured, informative PR descriptions ready for submission.

This skill should be used after productive sessions to extract learnings and route them to appropriate Reusable Intelligence Infrastructure (RII) components. Use when corrections were made, format drift was fixed, new patterns emerged, or the user explicitly asks to "harvest learnings" or "capture session intelligence". Transforms one-time fixes into permanent organizational knowledge by implementing updates across multiple files.

LLM application and RAG system specialist. Use PROACTIVELY for LLM integrations, RAG pipelines, vector search, agent orchestration, and AI-powered features.

Terraform infrastructure-as-code safety practices. Enforces plan-before-apply workflow. Use when working with .tf files or infrastructure commands.

Apply a Research → Plan → Implement → Validate workflow with Copilot CLI, including context budgeting and persistent artifacts via /share.

**AUTO-TRIGGER when:**- Progress reaches 5% milestone (5%, 10%, 15%, 20%...)- User says "sync [module] to main"- User says "approve main sync"- User says "reconcile [module] with main"Manages two-phase sync from yolo to main: (1) WIP markers to prevent contributor conflicts, (2) code sync with CI reconciliation after production validation.Use proactively without asking permission when task matches skill purpose.

Automatically applies when writing Python functions that call async operations. Ensures proper async/await pattern usage (not asyncio.run) to prevent event loop errors.

Convert app.json to app.config.ts and manage multiple app variants (dev/staging/prod) in Expo projects using expo-dev-client. Use when introducing typed config, variant-specific identifiers/schemes/icons/env, or building custom dev clients.

Multi-agent code analysis orchestration using claudemem. Share claudemem output across parallel agents. Enables parallel investigation, consensus analysis, and role-based command mapping.

Connect to Beam AI workspace for agent management. Load when user mentions 'beam', 'beam agent', 'beam task', 'beam analytics', 'list agents', 'create task', or any Beam AI operations. Meta-skill that validates config, discovers agents, and routes to appropriate operations.

Write self-documenting code with minimal, helpful comments that explain large sections of logic without cluttering the codebase. When writing or editing any code files and deciding whether to add comments. When reviewing existing comments to ensure they remain relevant and helpful. When structuring code to be self-explanatory through clear naming and organization. When adding comments to explain complex logic or non-obvious implementation details. This skill applies universally to all code files to maintain clean, well-documented code.

COO 产品运营数据分析技能，使用 Playwright MCP 从 App Store Connect、小程序后台、小红书创作者中心等平台获取运营数据

LLM-only skill that analyzes a snapshot of a single disk or partition and generates a safe, structured cleanup plan. Identifies obvious junk, heavy folders, and proposes step-by-step actions to reclaim space without risking important data.

Implement accessibility for the .NET 8 WPF widget host app. Use when improving keyboard navigation, screen reader support, focus states, and color contrast in XAML and styles.