Skip to main content

readable-spec

Reads web platform specifications via WebFetch — uses the multipage HTML variant for the WHATWG HTML spec, anchor-targeted section reads for W3C TR documents and TC39 / ECMAScript. Returns the relevant section rather than the whole spec, since these documents are too large for a single fetch. Use when the URL is on *.spec.whatwg.org, w3.org/TR/, or tc39.es.

ソース情報

リポジトリ
yamadashy/agent-readable
ソースの最終更新活動
2026年5月9日 15:39
検出された SKILL.md の言語
英語
スター
4
フォーク
0

インストール方法

デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。

ソースファイルを確認

インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。

SKILL.md を表示中

SKILL.md
ソースの指示 · 読み取り専用プレビュー
name
readable-spec
description
Reads web platform specifications via WebFetch — uses the multipage HTML variant for the WHATWG HTML spec, anchor-targeted section reads for W3C TR documents and TC39 / ECMAScript. Returns the relevant section rather than the whole spec, since these documents are too large for a single fetch. Use when the URL is on *.spec.whatwg.org, w3.org/TR/, or tc39.es.
# Web Spec Reader Specs are usually large single-page HTML documents. WebFetch them in sections rather than expecting the full body in one response. ## WHATWG (CC BY 4.0) Examples: `html.spec.whatwg.org`, `url.spec.whatwg.org`, `dom.spec.whatwg.org`. The HTML spec has a multipage variant that is much friendlier to fetch: ``` https://html.spec.whatwg.org/multipage/{section}.html ``` Use the table of contents at `https://html.spec.whatwg.org/multipage/` to find the right section URL, then WebFetch that page. ## W3C (`w3.org/TR/{shortname}`) Read with WebFetch, optionally appending an anchor: ``` https://www.w3.org/TR/{shortname}/#{anchor} ``` W3C documents are licensed for reading and reference; do not republish or redistribute large excerpts. ## TC39 / ECMAScript (`tc39.es/ecma262`) ``` https://tc39.es/ecma262/#sec-{section-id} ``` Section IDs are stable; the user often supplies one directly. ## Strategy 1. Identify the spec and target section from the URL. 2. WebFetch with a tight prompt focused on the specific question. 3. If the page is too large to digest, jump to the anchor or table-of-contents subsection. ## Reference - WHATWG IPR / license: https://whatwg.org/ipr-policy - W3C document license: https://www.w3.org/copyright/document-license-2023/ - TC39 / ECMAScript: https://tc39.es/ecma262/
GitHubで見る