Nix operational playbooks for package diffs, build debugging, closure analysis, dependency forensics, flake maintenance, and evaluation performance tuning. Use when comparing Nix build outputs, diagnosing derivation failures, finding unexpected runtime/build dependencies, inspecting closure size, maintaining flakes, or profiling slow NixOS/Home Manager/Nixvim evaluation.
Write idiomatic and maintainable Nix code. Use when creating or refactoring Nix expressions, Home Manager or NixOS modules, overlays, packages, and flake outputs, especially when deciding module merge semantics, binding locality, option defaults, and conditional structure.
Neovim Lua plugin development playbooks — project architecture, self lazy-loading, vim.g configuration, scoped commands and <Plug> keymaps, health checks, type-safe tooling, busted testing, and LuaRocks distribution. Use when writing or refactoring a Neovim Lua plugin, designing vim.g/setup config, deciding command/keymap APIs, adding checkhealth, configuring lua-ls/luacheck/stylua/LuaCATS, or setting up busted/nlua tests and SemVer LuaRocks releases.
Use for working with Jujutsu (jj) history workflows, including hunk-level split/squash/diffedit/restore via `jj-hunk-tool`.
GitHub issue triage, issue creation, PR review, and CI check-fix workflows using gh CLI.
Consolidates ultra-compressed communication, commit-message generation, PR review notes, and memory compression into one progressive-disclosure skill.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.