Sports News

Quick Start

Prefer the CLI — it avoids Python import path issues:

sports-skills news fetch_items

--google_news

--query

=

"Arsenal transfer"

--limit

=

5

sports-skills news fetch_feed

--url

=

"https://feeds.bbci.co.uk/sport/football/rss.xml"

Python SDK (alternative):

from

sports_skills

import

news

articles

=

news

.

fetch_items

(

google_news

=

True

,

query

=

"Arsenal transfer news"

,

limit

=

10

)

feed

=

news

.

fetch_feed

(

url

=

"https://feeds.bbci.co.uk/sport/football/rss.xml"

)

Important Notes

google_news=True

requires a

query

.

Without a query, Google News has nothing to search.

url

and

google_news

are mutually exclusive.

Use one or the other, not both.

Always use

sort_by_date=True

for recency queries to show newest articles first.

Before complex fetches, run the parameter validator:

bash scripts/validate_params.sh [args]

For detailed reference data, see the files in the

references/

directory.

Choosing Dates

Derive the current date from the system prompt's date (e.g.,

currentDate: 2026-02-16

means today is 2026-02-16).

If the user specifies a date range

, use it as-is.

If the user says "recent", "latest", "this week", or doesn't specify a timeframe

Derive

after

from the system date. For "this week", use

after = today - 7 days

. For "recent" or "latest", use

after = today - 3 days

.

Never hardcode dates in commands.

Always derive them from the system date.

Always use

sort_by_date=True

for recency queries to show newest articles first.

Commands

Command

Required

Optional

Description

fetch_feed

url

Fetch an RSS/Atom feed by URL

fetch_items

google_news, query, url, limit, after, before, sort_by_date

Fetch news items from Google News or an RSS feed

fetch_items

with

google_news=True

requires

query

. Returns Google News articles matching the search.

fetch_items

with

url

fetches items from a specific RSS/Atom feed URL.

fetch_feed

fetches and returns the full feed metadata plus recent entries. Workflows Workflow: Breaking News Check fetch_items --google_news --query="" --limit=5 --sort_by_date=True Present headlines with source and date. Workflow: Topic Deep-Dive fetch_items --google_news --query="" --after=<7_days_ago> --sort_by_date=True --limit=10 For curated sources, also try fetch_feed --url="" . Cross-reference both for comprehensive coverage. Workflow: Weekly Sports Roundup For each sport of interest, fetch_items --google_news --query=" results" --after=<7_days_ago> --limit=5 . Aggregate and present by sport. Examples User: "What's the latest Arsenal transfer news?" Call fetch_items(google_news=True, query="Arsenal transfer news", limit=10) Present headlines with source, date, and links User: "Show me BBC Sport football headlines" Call fetch_feed(url="https://feeds.bbci.co.uk/sport/football/rss.xml") Present feed title, last updated, and recent entries User: "Any Champions League news from this week?" Derive after from system date: today minus 7 days Call fetch_items(google_news=True, query="Champions League", after=, sort_by_date=True, limit=10) Present articles filtered to the last 7 days, sorted newest first Commands that DO NOT exist — never call these get_news — does not exist. Use fetch_feed (for RSS) or fetch_items (for Google News search). search_news — does not exist. Use fetch_items with google_news=True and a query parameter. get_headlines — does not exist. Use fetch_items with google_news=True . If a command is not listed in the Commands section above, it does not exist. Error Handling & Fallbacks If Google News returns empty, ensure google_news=True AND query are both set. Try broader keywords. If RSS feed returns error, feed may be down. Use Google News as fallback. If articles are old, use after parameter with date and sort_by_date=True . Never fabricate news headlines or article content. If no results, state so.