israel-news-rss
Skill2 starsChanged 3 days agoMITView on GitHub
Use when the user wants the latest Israeli news headlines from major outlets via RSS, in English or Hebrew. Aggregates Jerusalem Post, Times of Israel, and JNS (English) or Ynet, Maariv, Walla, Haaretz, and Globes (Hebrew), merges them by publication time, and returns a compact summary suitable for orchestrator context. Trigger phrases include "latest Israeli news", "what's happening in Israel right now", "Israeli headlines", "Hebrew news", "מה חדש בחדשות", "check Ynet / Jpost / ToI", "news from Israel in the last X hours".
In this repository20 other files it gives its agents.
- add-skill-to-pluginSkill
- ben-gurion-flight-boardSkill
- discover-israel-skillsSkill
- drug-co-il-lookupSkill
- environment-checkSkill
- fiber-availability-checkSkill
- home-front-command-guidelinesSkill
- install-israel-pluginsSkill
- israel-conferencesSkill
- israel-drugs-registry-lookupSkill
- jerusalem-council-meetingsSkill
- jerusalem-municipality-reportSkill
- kol-zchut-lookupSkill
- list-skillsSkill
- maccabi-medicine-lookupSkill
- medicine-availability-checkSkill
- miklatim-lookupSkill
- nsc-travel-threatSkill
- salary-conversionSkill
- update-plugin-readmeSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 75
If one feed is temporarily unreachable it's skipped with a [warn] on stderr.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Israel News — RSS Aggregator
Fetches and merges RSS feeds from major Israeli news outlets. Returns headlines, publication times, links, and short summaries sorted newest-first. No browser, no API keys, no geo-restriction issues.
Sources
English (--lang en)
jpost— Jerusalem Post front pagetoi— Times of Israeljns— Jewish News Syndicate
Hebrew (--lang he)
ynet— Ynet main feedmaariv— Maariv latest newswalla— Walla main feedhaaretz— Haaretzglobes— Globes business
Usage
python3 scripts/fetch_news.py --lang en # 50 English items, text output
python3 scripts/fetch_news.py --lang he --limit 100 # 100 Hebrew items
python3 scripts/fetch_news.py --lang en --since 6h # only last 6 hours
python3 scripts/fetch_news.py --lang he --source ynet # one source only
python3 scripts/fetch_news.py --lang en --json # JSON for orchestrationArguments
--lang {en,he}— language set to fetch. Defaulten.--limit N— max items returned after merge+sort. Default 50.--source KEY— restrict to a single source key (see lists above).--since WINDOW— drop items older than the window. Accepts30m,6h,2d.--json— emit JSON instead of the text digest.
When to use
- "Give me the latest Israeli news in English."
- "What are Ynet and Haaretz running right now?"
- "Pull the last 6 hours of headlines from Israel in Hebrew."
- "Summarize today's Jpost front page."
Output
Text mode prints a numbered list:
1. [jpost] Headline...
2026-04-23T20:26:51+00:00
https://...
Short summary snippet...JSON mode returns { lang, count, items: [{source, title, link, published, summary}, ...] } — ready to pipe into an LLM for summarization, clustering, or translation.
Passing to an orchestrator
The --json output is the intended handoff format. Typical pattern:
python3 scripts/fetch_news.py --lang he --limit 40 --since 12h --json > /tmp/news.jsonThen hand /tmp/news.json to Claude with a prompt like "summarize the top 5 stories, translate Hebrew headlines, and flag anything security-related."
Notes
- Feeds are plain RSS 2.0 / Atom-ish XML; parsed with stdlib (no
feedparserdependency). - If one feed is temporarily unreachable it's skipped with a
[warn]on stderr; the rest still return. - Publication times are normalized to UTC ISO-8601.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

