doge-shell

Use for doge-shell notebook, markdown rendering, output history, tm/out display, notebook_play, or terminal markdown work.

Use when working in the doge-shell repository or doge-shell リポジトリ. Routes to the right crate or narrower doge-shell skill, avoids broad reads, and chooses the smallest effective Rust validation command.

Use for doge-shell serve, static files, HTTP handlers, CORS, scanner, path validation, or web serving work.

Use for doge-shell builtin commands, proxy builtins, help, project, export, task, snippet, git builtins, or 組み込みコマンド work outside chat/MCP tools.

Use for doge-shell command palette, AI actions, diagnose, explain, suggest, argument_explainer, command_palette, ai_features, or コマンドパレット work.

Use for doge-shell Lisp, config.lisp, config loader, startup Lisp, stdlib, Lisp設定, 起動設定, include, or reload work. Narrows reads to Lisp/config startup paths.

Use for doge-shell completion, ghost text, suggestion, skim, fuzzy, TAB, 補完, 候補, サジェスト, or ゴーストテキスト behavior. Narrows reads to repl and completion code and keeps validation inside the doge-shell package.

Use for doge-shell validation planning, smallest-test selection, 検証, 最小テスト, or cargo test selection. Chooses the narrowest cargo command from package names, task type, and crate boundaries.

Use for doge-shell chatgpt, MCP, serve, tool, runtime skill, doctor, OpenAI client, チャット, ツール, スキル, or 診断 work. Narrows reads to builtin chat/MCP code and the OpenAI client crate.

Use for doge-shell environment, startup, direnv, project context, path activation, 環境変数, 起動処理, プロジェクトコンテキスト, or path work.

Use for doge-shell history, command timing, frecency, z ranking, 履歴, コマンド計測, frecency, or ranking work.

Use for investigation, review, audit, performance inspection, 調査, レビュー, 監査, or 性能確認 in doge-shell. Keeps work read-only first, avoids broad tests early, and narrows likely files before editing.

Use for doge-shell parser, AST, redirect, pipe, brace, expansion, パーサ, リダイレクト, パイプ, ブレース, or 展開 work. Narrows reads to parser code and keeps validation inside the doge-shell package.

Use for doge-shell process, PTY, job control, raw terminal, colored output, stdout rendering, プロセス, ジョブ, raw mode, or 端末出力 bugs. Keeps reads around process and terminal boundaries.

Use for doge-shell prompt, right prompt, transient prompt, terminal UI, renderer, プロンプト, 右プロンプト, transient, 端末描画, or layout bugs.

Use for doge-shell safety, guard, safe_run, command policy, approval, 安全確認, ガード, コマンドポリシー, or 実行制御 work.

Use when creating or editing runtime skills, Skill 作成, Skill 更新, or Codex/doge-shell skills from this repository. Helps keep SKILL.md short, put trigger text in frontmatter, and move detail into references or scripts.