行動開發

Add a new environment variable to the application. Use when adding configuration for external services, feature flags, or application settings. Triggers on "add env", "environment variable", "config variable".

Persist data with Core Data - models, contexts, fetch requests, migrations, SwiftData

Capture and develop fleeting ideas via Apple Notes inbox. AI expands rough concepts into detailed plans, evaluates potential with scoring (feasibility, impact, effort), and organizes by type (Patent, Startup, Business, Project). Triggers - "process ideas", "show ideas", "expand idea", "evaluate idea", "new idea", "brainstorm", "idea inbox", "show patents", "show startups", "link ideas", "search ideas".

Mobile app UX/UI best practices for smartphone interfaces. Use for designing touch-friendly interfaces, mobile navigation patterns, gesture handling, and optimizing user experience on small screens. Triggers on requests for mobile UX, app design, touch interfaces, mobile patterns, or smartphone UI best practices.

Coordinate structured thinking and multi-agent parallel execution for complex tasks. Use when tackling multi-step projects, planning parallel work, breaking down complex problems, coordinating specialist tasks, facing architectural decisions, or when user mentions "workflow", "orchestration", "multi-step", "coordinate", "parallel execution", "structured thinking", "break this down", "plan this out", "how should I approach", or needs help planning complex implementations.

Analyze LangGraph application architecture, identify bottlenecks, and propose multiple improvement strategies

This skill should be used when looking up Kyverno Helm chart versions, release dates, and corresponding app versions from Artifact Hub. Use for version planning, upgrade decisions, and release timeline analysis.

Kubernetes deployment strategies and workload patterns for production-grade applications. Use when deploying to Kubernetes, implementing rollout strategies, or designing cloud-native application architectures.

Use before creating new stories or when user asks "check for conflicts", "find duplicates", "review story overlaps", or "detect story conflicts" - scans story-tree database to identify duplicate stories, scope overlaps, and competing approaches using lightweight text similarity (no external dependencies).

Universal vulnerability detection patterns applicable across all programming languages. Includes hardcoded secrets, SQL/command injection, path traversal, and configuration file patterns.

Use when user wants to set up slime mold exploration strategy with parallel autonomy branches for genetic algorithm approach to problem-solving

Generate campaign taxonomy CSV updates for Google Ads campaigns. Use when identifying campaigns that need taxonomy mapping, detecting vertical mismatches in mixed-vertical accounts, or creating properly formatted taxonomy CSV files for ingestion. Triggers on requests involving campaign taxonomy, budget attribution, vertical classification, or taxonomy CSV generation.

Use when asked to visualize sales territories, coverage areas, service regions, or geographic boundaries on interactive maps.

Apply domain constraints and professional rules; use when asked to comply with enterprise, legal, or scientific standards.

Map architectural structure by analyzing what depends on what to reveal coupling patterns, layering violations, and circular dependencies. Use when: (1) coupling is characterized without having mapped actual import and call relationships, (2) architectural layers are reasoned about based on directory structure rather than verified dependency flow, (3) module extraction or movement is considered without measuring how much coupling exists and in which direction, (4) dependency structure is discussed without explaining which modules are central hubs versus peripheral leaves.

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

Launch the Adventure Engine application for an adventure project. Use when the user wants to "enter" a world, "start" or "launch" an adventure session, or begin interactive gameplay. Fires off the application in the background using the current working directory as the adventure project root.

This skill should be used when the user asks to "record session", "log interactions", "track session activity", "audit Claude usage", "create session logs", or when session recording is enabled. Provides instructions for the hybrid recording approach where Claude self-reports summaries of completed work.

Branch the current Claude Code session into a new tmux session using --resume. Creates a parallel conversation that can diverge independently. Use when you want to explore an alternative approach without losing your current context.

Define boundaries where claims or recommendations apply versus break down. Use when: (1) asked to define scope or boundaries, (2) claim presented as universal truth, (3) explaining why pattern works here but not there, (4) advice given without specifying applicable context.