メニュー
Use when an agent needs to inspect, search, or quote a large text file such as a log, CI output, JSON dump, generated report, or other non-workspace text without reading the whole file into context.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use before changing existing indexed files with Miller edit, especially symbol rewrites, text replacements, renames, or refactors.
Use when an agent needs extractor-recognized code-shape facts such as routes, htmx attributes, Alpine directives, SQL DDL/DML, or data-document structure.
Use when starting a Miller task, choosing a Miller tool, or choosing a Miller search mode.
Use when tracing Miller bridge paths in supported providers: dotnet-web URL literals and fetch/axios client requests to ASP.NET signals, client requests to Next.js route handlers or Nuxt server routes, Next.js/Nuxt route references to file routes, Vue/React references to route definitions, or backend-http client requests to Express/FastAPI/Flask/Django/Spring/Go/gin/echo/Rails/NestJS/Laravel/Phoenix/axum/actix/Symfony/Ktor route facts.
Use when orienting on an unfamiliar code area with Miller, explaining a module, finding entry points, or gathering context before a change.
Use when assessing blast radius with Miller, choosing tests for a change, answering who uses a symbol, or planning a refactor.
| name | miller-large-file |
| description | Use when an agent needs to inspect, search, or quote a large text file such as a log, CI output, JSON dump, generated report, or other non-workspace text without reading the whole file into context. |
Use Miller's content tool instead of cat, full-file reads, or broad shell output when a text file may be large enough to waste context.
content(operation: "import", path: "/absolute/path/to/file")miller content import /absolute/path/to/filecontent(operation: "search", query: "error text")miller content search "error text"content(operation: "read", source_id: "...", line: 120, context_lines: 10)miller content read --source-id ... --line 120 --context-lines 10content(operation: "list")content(operation: "remove", source_id: "...")context_lines small and increase it only when the first bounded window is insufficient.max_bytes only when you intentionally want to import a file over the default cap.