LLM & Agents

Transform vague prompts into precise, well-structured specifications using EARS (Easy Approach to Requirements Syntax) methodology. This skill should be used when users provide loose requirements, ambiguous feature descriptions, or need to enhance prompts for AI-generated code, products, or documents. Triggers include requests to "optimize my prompt", "improve this requirement", "make this more specific", or when raw requirements lack detail and structure.

Coordinates subagent task distribution and collaboration. Controls scale determination and autonomous execution mode.

サブエージェントのタスク分担と連携を調整。規模判定と自律実行モードを制御。大規模タスク分割時に使用。

Applies Vitest test design and quality standards. Provides coverage requirements and mock usage guides. Use when writing unit tests.

Use when asking about 'FileProtectionType', 'file encryption iOS', 'NSFileProtection', 'data protection', 'secure file storage', 'encrypt files at rest', 'complete protection', 'file security' - comprehensive reference for iOS file encryption and data protection APIs

Use when asking 'where should I store this data', 'should I use SwiftData or files', 'CloudKit vs iCloud Drive', 'Documents vs Caches', 'local or cloud storage', 'how do I sync data', 'where do app files go' - comprehensive decision framework for all iOS storage options

Use when debugging 'files disappeared', 'data missing after restart', 'backup too large', 'can't save file', 'file not found', 'storage full error', 'file inaccessible when locked' - systematic local file storage diagnostics

Use when asking about 'purge files', 'storage pressure', 'disk space iOS', 'isExcludedFromBackup', 'URL resource values', 'volumeAvailableCapacity', 'low storage', 'file purging priority', 'cache management' - comprehensive reference for iOS storage management and URL resource value APIs

Use when implementing SwiftUI gestures (tap, drag, long press, magnification, rotation), composing gestures, managing gesture state, or debugging gesture conflicts - comprehensive patterns for gesture recognition, composition, accessibility, and cross-platform support

Use when implementing SwiftUI animations, understanding VectorArithmetic, using @Animatable macro, zoom transitions, UIKit/AppKit animation bridging, choosing between spring and timing curve animations, or debugging animation behavior - comprehensive animation reference from iOS 13 through iOS 26

Use when working with ANY data persistence, database, storage, CloudKit, migration, or serialization. Covers SwiftData, Core Data, GRDB, SQLite, CloudKit sync, file storage, Codable, migrations.

Use when creating SwiftData custom schema migrations with VersionedSchema and SchemaMigrationPlan - property type changes, relationship preservation (one-to-many, many-to-many), the willMigrate/didMigrate limitation, two-stage migration patterns, and testing migrations on real devices

Query the Sequence Read Archive (SRA), retrieve scientific publications, and analyze genomics metadata using the SRAgent toolkit. Supports accession conversion (GSE→SRX→SRR), BigQuery metadata queries, manuscript downloads from multiple sources, and scRNA-seq technology identification. Use when working with SRA/GEO datasets, finding publications, or analyzing single-cell sequencing experiments.

Coordinate multi-agent code review with specialized perspectives. Use when conducting code reviews, analyzing PRs, evaluating staged changes, or reviewing specific files. Handles security, performance, quality, and test coverage analysis with confidence scoring and actionable recommendations.

Execute implementation plans phase-by-phase with checkpoint validation.Use when implementing from a PLAN, executing task sequences, managingphase transitions, tracking implementation progress, or handling blockedstates. Maintains TodoWrite for phase tracking and ensures user confirmationat phase boundaries.

Apply consistent security, performance, and accessibility standards across all recommendations. Use when reviewing code, designing features, or validating implementations. Cross-cutting skill for all agents.

Generate structured agent prompts with FOCUS/EXCLUDE templates for task delegation. Use when breaking down complex tasks, launching parallel specialists, coordinating multiple agents, creating agent instructions, determining execution strategy, or preventing file path collisions. Handles task decomposition, parallel vs sequential logic, scope validation, and retry strategies.

Save and recall information across sessions. Use when you hear 'remember this', 'save to memory', 'add to your knowledge', or similar. Stores to Claude OS knowledge bases for persistent recall.

Use when user asks to leverage claude or claude code to do something (e.g. implement a feature design or review codes, etc). Provides non-interactive automation mode for hands-off task execution without approval prompts.

Unified Memory Contract for Flowbaby integration. Defines when and how to retrieve and store memory. Load at session start - memory is core to agent reasoning, not optional.