菜单
Digest of the most interesting new posts on [REPLACE: TOPIC] from RSS feeds and the open web
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
Summary of the [REPLACE: CHANNEL_PLATFORM] channel [REPLACE: CHANNEL_NAME] — top [REPLACE: TOP_N_THREADS] threads + open questions
Price and volume tracker for [REPLACE: TOKEN_SYMBOL] with anomaly alerts above [REPLACE: ALERT_THRESHOLD_PCT]% movement
Watch Vercel deploys for [REPLACE: VERCEL_PROJECT] — alert on [REPLACE: ALERT_ON] in the last [REPLACE: LOOKBACK_HOURS] hours
Mention/keyword sweep on social platforms for [REPLACE: KEYWORDS] — trends, sentiment, top posts
5 concrete real-life actions, leverage-scored against open loops with specificity and anti-fluff gates
Curated AI-agent tweets, clustered into narratives with insight summaries
| name | [REPLACE: SKILL_NAME] |
| description | Digest of the most interesting new posts on [REPLACE: TOPIC] from RSS feeds and the open web |
${var} — Optional. Pass a different topic to override the default. If empty, digests [REPLACE: TOPIC].
Today is ${today}. Build a digest of the [REPLACE: MAX_ITEMS] most interesting new posts on [REPLACE: TOPIC].
Read sources — pull the last 24h of entries from each feed:
[REPLACE: FEED_URLS]
(Comma- or newline-separated list of RSS/Atom URLs.)
Use WebFetch to retrieve each feed and parse the entries. If a feed 404s or returns malformed XML, log a single warning line and skip that feed for this run.
Augment with web search — run a WebSearch for [REPLACE: TOPIC] latest and pick up to 5 fresh links published in the last 24h that aren't already in the feed results.
Score and rank — for each candidate, score on:
Drop anything obviously off-topic (the ${var} or [REPLACE: TOPIC] keyword should appear somewhere in title or summary).
Pick the top [REPLACE: MAX_ITEMS] — write articles/[REPLACE: SKILL_NAME]-${today}.md with one entry each:
### [Title](url)
*[Source · published date]*
2-3 sentences distilling the takeaway. No filler.
Notify via ./notify with:
*[REPLACE: TOPIC] digest — ${today}*
[N] picks. Top item: [shortened title].
Full digest: https://github.com/${GITHUB_REPOSITORY}/blob/main/articles/[REPLACE: SKILL_NAME]-${today}.md
Log — append to memory/logs/${today}.md:
## [REPLACE: SKILL_NAME]
- **Sources scanned**: N feeds + 1 web search
- **Items picked**: N (of M candidates)
- **Top source**: domain
- **Status**: DIGEST_OK | DIGEST_QUIET (no items) | DIGEST_DEGRADED (some feeds failed)
WebFetch and WebSearch are built-in Claude tools that bypass the GitHub Actions sandbox network gate. Use those for every external read in this skill — curl will frequently fail.
memory/topics/[REPLACE: SKILL_NAME]-seen.txt (append-only). Skip anything that's already in there.[REPLACE: MAX_ITEMS] items meet the bar, send fewer items — never pad with low-signal content.