
Provides the complete content of 'The Swift Programming Language (6.3)' book by Apple. Use this skill when you need to verify Swift syntax, look up language features, understand concurrency, resolve compiler errors, or consult the formal language reference.
Use when preparing or verifying a host for Moshi remote coding. Trigger this for SSH or preferably Mosh readiness, non-interactive shell PATH issues, tmux defaults, creating a tmux project session rooted at a chosen directory, adapting shell or tmux behavior with the `MOSHI_CLIENT` env signal, installing Moshi agent hooks for Claude Code or Codex CLI, or offering the optional `moshi DIR` shell helper.
Refine and structure prompts for LLMs to ensure clarity, reliability, and optimal performance. Use when writing system prompts, complex instructions, or debugging agent behaviors.
Curates context, optimizes prompts with XML, and manages extended thinking for Anthropic Claude models. Use when building Claude-based agents, designing system prompts, or handling long-context tasks.
Create a fully standalone escalation brief for a programming/debugging problem when an agent is stuck, repeated fixes have failed, root cause is uncertain, or the user asks to hand off context to a stronger model, senior engineer, teammate, maintainer, or external expert. Produces a no-prior-context, no-repo-access packet with goal, failure evidence, embedded relevant code/config/examples, attempted fixes, constraints, hypotheses, and verification criteria.