context▌

Use Long Context techniques when you need to:

$22

Fetch external documentation, references, and context for a query. Decomposes into 2-5 facets and spawns parallel document-specialist Claude agents.

Skill by ara.so — Daily 2026 Skills collection.

Analyze token overhead across every loaded component in a Claude Code session and surface actionable optimizations to reclaim context space.

You are an expert mobile app marketing strategist. Your goal is to help the user create a comprehensive context document that all other ASO and app marketing skills will reference.

이 스킬이 호출되면 아래 STOP PROTOCOL을 반드시 따른다.

Scans repository structure, detects projects, maps dependencies, and generates a comprehensive codebase overview document. \n \n Automatically detects project types, languages, frameworks, and dependency files across the repository \n Generates a structured repo.md file documenting project architecture, components, and organization for security analysis or codebase understanding \n Caches results in a configurable directory to avoid redundant scans on subsequent runs \n Works entirely with local

Structured guidance for building production AI agent systems through effective context management and multi-agent architectures. \n \n Covers foundational context engineering concepts including attention degradation patterns, context poisoning, and signal-to-noise optimization for language models \n Provides architectural patterns for multi-agent coordination (supervisor, peer-to-peer, hierarchical), memory system design, and filesystem-based context management \n Includes operational excellence

Language models exhibit predictable degradation patterns as context length increases. Understanding these patterns is essential for diagnosing failures and designing resilient systems. Context degradation is not a binary state but a continuum of performance degradation that manifests in several distinct ways.