design

Spawn a peer back-and-forth between Claude (max thinking) and Codex (high reasoning) on hard architecture decisions.

Generate a high-level weekly status report for a Basecamp project. Activity-first via the basecamp CLI; outputs a lean 3-section markdown report (TL;DR, blockers, gaps).

Git worktree management guidance and activity-tracking hooks for parallel AI agent workflows.

Pause execution and inspect runtime state via DAP. Attach to live processes by PID, no restart or code changes required.

Strips AI-tell patterns from text (em-dash overuse, inflated symbolism, rule of three, vague attributions, AI vocabulary, etc.) based on Wikipedia's 'Signs of AI writing' guide.

Reference vocabulary and principles for writing and editing Claude Code skills well. Skill by Matt Pocock, vendored.

Routes all delegable work (exploration, bulk reads, tests, mechanical edits, first-pass reviews, sweeps) from a Fable session to the Codex CLI via codex exec, spending Codex quota instead of Anthropic tokens.

Modern SwiftUI doctrine plus 7 recipes for Apple-platform development: no-ViewModel patterns, modular SwiftPM, Foundation Models on-device LLM, AppRouter navigation, iOS 26 Liquid Glass, encrypted push proxy, XcodeBuildMCP build verification, ObservableObject-to-Observable refactor.

Evaluate Claude Code skills against best practices. Tracks skill usage globally via hooks.

Core skills library: TDD, debugging, brainstorming, plan-writing, code-review patterns.