rss-digest

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

RSS Digest

RSS摘要

Surface what's worth reading from RSS feeds. Requires

feed

CLI (

brew install odysseus0/tap/feed

从RSS订阅源中筛选值得阅读的内容。需要安装

feed

CLI工具（执行命令

brew install odysseus0/tap/feed

进行安装）。

Workflow

工作流

Scan —
```
feed get entries --limit 50
```
for recent unread (title, feed, date, URL, summary). Auto-fetches if stale. If 0 results, run
```
feed get stats
```
— if 0 feeds, import starter set:
```
feed import https://github.com/odysseus0/feed/raw/main/hn-popular-blogs-2025.opml
```
and retry.
Triage — Pick 5-10 high-signal posts based on the user's prompt. If no specific interest given, prioritize surprising, contrarian, or unusually insightful pieces.
Read + Synthesize — For each picked entry, fetch the URL and summarize in 2-3 sentences. Parallelize when possible.
Present — Compile the summaries into a digest. Group by theme if natural clusters emerge.

扫描 — 执行
```
feed get entries --limit 50
```
获取近期未读内容（包含标题、订阅源、日期、URL、摘要）。若内容过期会自动抓取。如果没有结果，执行
```
feed get stats
```
查看统计信息——若未添加任何订阅源，可导入初始订阅集：执行
```
feed import https://github.com/odysseus0/feed/raw/main/hn-popular-blogs-2025.opml
```
后重试。
筛选 — 根据用户的提示挑选5-10篇高价值内容。若未指定特定兴趣方向，优先选择观点新奇、逆向思维或见解格外深刻的文章。
阅读与总结 — 针对每篇选中的内容，抓取其URL对应的文章并总结为2-3句话。尽可能并行处理。
呈现 — 将所有总结内容整理为一份摘要。如果内容自然形成主题集群，可按主题分组展示。

Commands

命令

feed get entries --limit N              # list unread entries (table)
feed get entries --feed <id> --limit N  # filter by feed
feed fetch                              # pull latest from all feeds
feed search "<query>"                   # full-text search
feed update entries --read <id> ...     # batch mark read
feed get feeds                          # list feeds with unread counts
feed get stats                          # database stats

feed get entries --limit N              # 列出未读内容（表格形式）
feed get entries --feed <id> --limit N  # 按订阅源筛选内容
feed fetch                              # 抓取所有订阅源的最新内容
feed search "<query>"                   # 全文搜索
feed update entries --read <id> ...     # 批量标记为已读
feed get feeds                          # 列出所有订阅源及未读数量
feed get stats                          # 查看数据库统计信息

Notes

注意事项

The entries table includes full URLs — use these to fetch articles directly. Do NOT use
```
feed get entry
```
for reading; fetch the URL instead.
Do NOT mark entries as read. The user decides what to mark read.
Default output is table — most token-efficient for scanning. Avoid
```
-o json
```
.
Filter by feed if too many entries:
```
--feed <feed_id>
```
.

内容列表包含完整URL——请直接使用这些URL抓取文章。不要使用
```
feed get entry
```
命令来阅读文章，应直接抓取URL对应的内容。
不要将内容标记为已读。应由用户决定哪些内容标记为已读。
默认输出格式为表格——这是扫描内容时最节省token的格式。请避免使用
```
-o json
```
参数。
如果内容数量过多，可按订阅源筛选：使用
```
--feed <feed_id>
```
参数。