AGENT SKILL
web
search the web, and read the page at a URL
- License 许可
- MIT
- 最近更新
- 2026-10-28
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- web
- description
- search the web, and read the page at a URL
02 资源文件 4
- 脚本__init__.py660 B
- 脚本fetch.py6.8 KB
- 脚本media.py15.8 KB
- 脚本search.py2.9 KB
03 SKILL.md 正文
- Having a URL and searching for it are different problems. A URL or a post id is an address —
fetch_urlreads it.web_searchfinds an address you don't have yet. Searching for an address cannot work, however many times you rephrase it. - A link appearing in conversation is not by itself a reason to fetch it. But before you act on one — summarizing it, filing it, judging it, describing what it is — read it. Producing a description of a page you have not opened is the failure to avoid, not leaving a link unread.
- Never describe a page you could not read. If
fetch_urlfails, say so plainly, record the bare URL, and ask the owner what it was. A guessed description that lands in memory outlives the conversation and is worse than an admitted gap — this has already happened twice, and both times the guess was wrong. - Never infer a page's content from the conversation around it. The link the owner sent before this one tells you nothing about this one; two links in a row are not by the same author.
- When a search does not find what you need, stop and say so. Rephrasing the same query repeatedly costs real money and does not turn an unanswerable search into an answerable one.
04 同仓库更多 Skills
travel
trips, saved places, per-trip wishlists, and hourly itineraries
★ 0
system
media stack health and library overview across services
★ 0
sonarr
TV library — search, add, monitor seasons/episodes, delete
★ 0
radarr
movie library — search, add, monitor, delete, quality profiles
★ 0
prowlarr
indexer search — query configured indexers for releases
★ 0
jellyseerr
media requests — search and request movies/TV via Jellyseerr
★ 0