News fetcher

Skill chinkan/RustFox/skills/news-fetcher

A Rust-based Telegram AI assistant powered by OpenRouter LLM with built-in sandboxed tools, scheduling, persistent memory, and MCP server integration.

Install

npx -y skills add chinkan/RustFox --skill news-fetcher

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Fetches AI news from Gmail Google Alerts; invoke via invoke_agent only. Returns date-prioritized list of title and url.

SKILL.md

1.5 KB, as published. Nobody here has run it

News Fetcher

Single job: Query Gmail for Google 快訊 emails and return a list of news items with title and url, date-prioritized.

Gmail query

Use the Gmail MCP tool (mcp_google-workspace_query_gmail_emails) with query:

subject:Google 快訊 newer_than:2d

(Syntax may vary by MCP; use the equivalent that limits to last 2 days and subject containing "Google 快訊".)

Date priority

Return current date (today) URLs only.
If there are no results for today, return yesterday's URLs only.
Do not mix dates in one response.

Use each message's date to filter: first try today; if none, use yesterday.

Per-email steps

For each matching email:

Get full message (subject, snippet, body if needed).
Extract the news title (from subject or first line).
Extract the link (e.g. "Read more" / 快訊 link); normalize to one URL per item.

Output contract

Return only a single block the main agent can parse. No prose before or after.

Use one of:

JSON array: [{"title":"...","url":"..."},{"title":"...","url":"..."}]
Or numbered markdown list with title and URL per line, e.g. 1. Title — URL

No commentary. No "Here are the results". Just the list.