Improve RSS ingest: source full article body, enforce article-scrap conventions#336
Merged
Conversation
…onventions RSS ingest passed only the URL to Claude and relied on WebFetch, which summarizes the page. Claude never saw the full article, so it linked terms that don't appear in it, and had no rule to preserve the article title or link to [[Blog]]. - Add mise-tasks/fetch-article-body: pull the entry's full body from the feed (content:encoded / summary), convert to Markdown. create-scrap saves it to article-body.md for Claude to Read, bypassing WebFetch's summary. Excerpt-only feeds (<1500 chars) emit nothing, so Claude falls back to WebFetch. - rss-to-scrap.yml: add mise-action and a body-fetch step to create-scrap, and update the prompt to treat article-body.md as the source of truth. - Prompt conventions: use the article title verbatim, keep article content in its own scrap rather than merging into concept scraps, and end with [[Blog|ブログ]]. - gitignore the transient article-body.md. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
RSS ingest の品質を3点改善する。
① フィード本文を情報源にする(WebFetch 要約のバイパス)
fetch-rssは URL/title だけを出力し、記事本文は WebFetch 頼みだった。WebFetch はページを要約して返すため、Claude が記事全文を把握できず、記事に登場しない用語まで scrap リンク化する問題があった。mise-tasks/fetch-article-body: フィードのcontent:encoded/summaryから本文を引き、Markdown 化して出力。create-scrapがarticle-body.mdに保存し、Claude がReadで全文を読む。② 記事タイトルを維持 / ③ [[Blog]] への集約
prompt にローカル規約を追記:記事タイトルをそのまま使う・記事内容を概念 scrap に混ぜない・末尾に
[[Blog|ブログ]]。タイトルはmatrix.article.titleを変数で渡し確定させ、WebFetch 取得のブレを回避。Why
Securing CI-CD...は本文に「CNCF ブログ記事」と書きながら[[Blog]]未リンク、GitHub Advisory Databaseは記事統計が概念 scrap に混入していた(後から手動分割 ed1b5e3)。設計メモ(レビュー向け)
run:ステップで実行。.claude/settings.jsonのpermissions.allowがBash(scraps:*)のみで Claude にmise runさせられないため。list-articlesは url/title のまま。全文は各create-scrapジョブが1記事分だけ取得し、job output 肥大を回避。検証
実フィードで
fetch-article-bodyを実行:🤖 Generated with Claude Code