Use when a JavaScript or TypeScript project's dependencies must be seen as they are in the code: the whole graph, what one module depends on, who depends on it, or its neighbourhood, at file or folder level. Produces a Mermaid graph document in aiview, parsed by a deterministic script, never inferred. Not for designing a module's interface (deepen-module).
日本語の概要は準備中です。原文の説明を表示しています。
実行スコア 未検証
インストール方法を見るインストールする前に、エージェントに与えられる指示の中身を確認できます。
The graph is parsed, never written by hand or guessed. scripts/graph.mjs runs dependency-cruiser over the code, with the project's own TypeScript, and turns the ask into options. The same options give the same graph on the same commit.
Translate the ask into options, then run it once:
node <skill-dir>/scripts/graph.mjs --root <the package's folder> [--from <path>] [--to <path>] [--focus <path> --depth <n>] [--steps <n>] [--level <n>] [--only <regex>] [--exclude <regex>] --title "<title>" --out <path>
--from that module or folder.--to it.--focus it, --depth the hops.--steps <n> follows imports only n steps from --from.--level 2 folds src/<area>/… into one node per area; the coarser view first, then open the part that matters.--exclude "tests|generated"; node_modules and Node's own modules are always out.The root is the folder holding the package's tsconfig.json (its extends resolves from there); in a monorepo, one package per graph. The first run installs dependency-cruiser and the project's TypeScript into a cache, needing the network once.
Through the aiview skill: kind report from YYYY-MM-DD-<subject>.dependency-graph.report.md, tags dependency-graph and the module, group the piece of work it serves. The script writes it at the path aiview path gives, with the commit, the counts and the command that makes it again. Open it and tell the person the URL. A graph over about a hundred nodes is folded with --level or narrowed before it is shown.
What the graph shows is said under it, in a few lines: the cycles, a dependency against the project's stated boundaries (its conventions file), a module far more depended on than the rest. Nothing beyond what the edges show.
まだレビューはありません。使ってみた感想をお寄せください。
ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。
まだコメントはありません。最初のコメントを書いてみませんか。
Use whenever a document is produced for the user to read and react to while it evolves: a brainstorm board, a plan, a design language, a prototype, a PR analysis, a review report, a live PDF. Also when a document must be registered, opened, listed, moved or retired, or a prototype's bindings checked. Not for code, tests or configuration, or any file nobody opens in a browser.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a person wants to think an idea through and keep the discussion: a feature, a tool choice, an architecture question, before a plan or without one, with the agent through an interview. Produces a board in aiview holding the decisions, the diagrams and what was investigated. Not for a swarm of seats working it (brainswarm), not for an implementation plan and not for bug fixes.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a person wants a swarm of role seats to work a topic on the swarm board under a chosen protocol: a brainstorm (ideas before any judgment), a debate (questions argued to decisions, a skeptic endorsing) or an editorial (one text drafted, read by seats standing for its readers, revised), a protocol or template the project keeps as a `protocol-<name>` skill (or an older `brainswarm-<name>` one), or a custom protocol recommended for the person's intent, or a seat's brief names a brainswarm protocol. Produces the run's record in aiview, written by the orchestrator alone. Not for one person thinking aloud with the agent (brainstorm, interview) and not for a plan's slices (execute-plan).
日本語の概要は準備中です。原文の説明を表示しています。
Use when dispatched to cold-read a plan, as an agent that was not in the conversation that wrote it, to say whether it can be carried out from the document alone. Produces what the reader would build, its questions, and a verdict, ready or not ready, repeated as the writer fixes the plan. Not for judging the design (interview, pr-review), not for the mechanical checks (aiview plan check, tracker check), and not for writing the plan (write-plan).
日本語の概要は準備中です。原文の説明を表示しています。
Use when code is hard to follow and is to be audited or reworked: long if/else or switch chains, cascades of type checks or parse attempts, kind fields compared to strings, flag parameters, deep nesting, a function hard to read. Also for complexity guardrails, or one long conditional function pasted. Produces a ranked audit of families, one family reworked behind characterization tests, or the guardrails.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a page is wanted to work on something with the person during development, fed the project's real data (comparing model answers, walking an agent call by call, measuring an output against its template), when such a workbench has to change, be reworked or its feed broke, or mid-session when turns went into aligning with the person on how to do a kind of work that recurs and real project data could show it. Produces the page in aiview, kind `workbench`, and the project's `workbench-<bench>` skill with its feed and operating steps. Not for designing a product screen (design-prototype) or verifying user stories (verification-skill-create).
日本語の概要は準備中です。原文の説明を表示しています。