菜单
Fetch RSS feeds and generate AI-summarized daily digests
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Session-end memory discipline. Detects which projects were touched, writes updates to WORKBENCH.md (volatile state) + skills + persistent memory, and proposes CLAUDE.md edits. Two-tier — obvious low-blast-radius writes are applied automatically and reported; evergreen/destructive changes ask first. Use when the user says "/wrap", "wrap up", "end of session", "let's close out", or when the session is clearly winding down.
When the user is writing the story portion of a launch video or demo and needs the framing where the founder pretends to BE the ICP experiencing the problem, then uses the product on-camera. Also use when the user mentions "demo story", "show don't tell", "day-in-the-life demo", "roleplay demo", "founder as customer", or "first person launch video". This is the story frame, not the full script.
When the user needs a 3-5 word opening hook for a product launch video — the first second of on-screen text or voice that stops the scroll. Also use when the user mentions "hook for my video", "first second", "opening line", "tagline", "one-liner for launch", or "catchphrase". Produces 10+ hook candidates, not one answer.
When a user wants to grow an X (Twitter) account from zero before a product launch, or asks how to get first followers, warm up the algorithm, hit ~500-1,000 followers, or prepare an account to make a launch video land. Also use when the user mentions "new X account", "warm up my Twitter", "first 1000 followers", "building in public strategy", "X growth", or "engagement before launch".
When the user is planning, scripting, or editing a product launch video for X (Twitter) and needs the structure. Also use when the user mentions "launch video", "demo video", "product launch on X", "60 second demo", "how to structure a launch", or "my launch video isn't working". Produces a beat-by-beat timing sheet, not copy.
When the user has X (Twitter) content that performed well and wants to relay it to LinkedIn 1-2 weeks later with reframing. Also use when the user mentions "repost to LinkedIn", "LinkedIn version of my tweet", "X to LinkedIn", "delayed repost", "LinkedIn for non-tech audience", or "LinkedIn relay". Also use when the user's ICP is non-tech and X is secondary — LinkedIn is the primary channel and this skill produces the content.
| name | rss-digest |
| description | Fetch RSS feeds and generate AI-summarized daily digests |
| version | 0.1.0 |
| tools | ["Bash"] |
Fetches RSS/Atom feeds, filters by keywords, and generates AI-summarized digests.
# Digest from a single feed
bun run rss-digest/scripts/digest.ts --url <feed-url>
# Digest from feeds.json config (incremental — auto-calculates since lastRun)
bun run rss-digest/scripts/digest.ts --feeds feeds.json
# Digest from OPML export
bun run rss-digest/scripts/digest.ts --opml feeds.opml --hours 48
# Raw article list (no AI summary)
bun run rss-digest/scripts/digest.ts --feeds feeds.json --raw
{
"feeds": [
"https://example.com/feed",
"https://another.com/rss"
],
"lastRun": "2026-02-18T00:00:00Z",
"keywords": ["education", "AI"],
"noKeywords": ["sponsored", "advertisement"]
}
GEMINI_API_KEY environment variableoutput/digests/ by defaultWhen using --feeds, the script reads lastRun from the config and only fetches articles published since then. After running, it updates lastRun automatically. Never manually specify --hours unless overriding.
Markdown digest with executive summary, themed article groups, and "Worth Reading" highlights.