メニュー
Platform rules, Taiwan filter, date extraction, and known quirks for the NHK RSS scraper
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
Planning principles, model selection, and scope rules for the Architect agent
Implementation rules for database migrations, Python scrapers, and Next.js web for the Engineer agent
BaseScraper contract, field rules, and Peatix-specific conventions for the Scraper Expert agent
Scraper test execution rules, output validation criteria, and report format for the Tester agent
BaseScraper contract, field rules, and Peatix-specific conventions for the Scraper Expert agent
Platform rules and field mappings for the 誠品生活日本橋 (eslite spectrum Nihonbashi) scraper
| name | nhk_rss |
| description | Platform rules, Taiwan filter, date extraction, and known quirks for the NHK RSS scraper |
NHK (Japan Broadcasting Corporation) public RSS news feeds — no authentication required.
Feeds fetched:
https://www3.nhk.or.jp/rss/news/cat4.xml — international newshttps://www3.nhk.or.jp/rss/news/cat7.xml — culture/science| Event field | Source |
|---|---|
source_name | "nhk_rss" |
source_id | nhk_{md5(item_link)[:12]} |
source_url | <link> tag (falls back to <guid>) |
name_ja | <title> text |
raw_title | <title> text |
raw_description | "NHKニュース:\n\n{description_plain}" |
start_date | Extracted from description; fallback to pubDate |
category | ["report", "books_media"] |
original_language | "ja" |
TAIWAN_KEYWORDS = ["台湾", "台灣", "Taiwan", "taiwan"]
# Applied to: title + " " + description_plain_text
YYYY年MM月DD日 in descriptionYYYY/MM/DD in descriptionMM月DD日 in description → use pubDate year (adjust ±1 year for wrap)start_date will almost always fall back to pubDate; the annotator should not be expected to extract a precise event start date.