How do I install the News Cards skill?

Run npx skillmds@latest add chuk-development/news-cards in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is News Cards safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with News Cards?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is News Cards free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published News Cards?

chuk-development (@chuk-development) published this skill. Their other Agent Skills are listed on their SkillMD profile.

News Cards by chuk-development — Agent Skill

Name: News Cards
Author: chuk-development

News Cards

Fetches time-sensitive news and renders it as a <news> card block with thumbnail, publisher and age. Use when the user asks for the latest, news, today, breaking, recent, aktuell, neu, heute, Schlagzeilen — load this before emitting a <news> block.

File contents

News cards

The app renders a <news> block as polished article cards (thumbnail, title, publisher, summary, tap-to-open). It is an output tag, not a tool: write the JSON directly in your response text.

Workflow

Call web_search with type: "news" and a matching freshness:
- pd — past day ("today", "breaking", "heute", "gerade")
- pw — past week ("this week", "diese Woche")
- pm — past month
- py — past year The news mode returns publisher, age and thumbnail directly, so no separate crawl is needed just to build the cards.
For German or DE-specific queries, also pass country: "DE" and search_lang: "de" so the SERP is localized.
Emit exactly one <news> block built from the results.
Only call web_crawl afterwards when the user asks for full article detail — the cards already carry the summary.

Format

Fields per item

title: headline (required)
url: article URL (required)
publisher: source name, e.g. "Reuters" (optional)
age: e.g. "3 hours ago", "1 day ago" (optional)
thumbnail: image URL from the search result's thumbnail_url (optional)
summary: 1-2 sentences, taken from the result description (optional)
breaking: true when the result is flagged BREAKING (optional)

Rules

Only include fields that came from web_search type:"news" results. Never fabricate URLs, publishers or thumbnails.
Do NOT also list the same articles as markdown — the cards contain everything. A short intro sentence above the block is fine.
Emit at most one <news> block per response.
Put the block at the very END of your answer and stop after </news>.

---name: news-cardsdescription: Fetches time-sensitive news and renders it as a <news> card block with thumbnail, publisher and age. Use when the user asks for the latest, news, today, breaking, recent, aktuell, neu, heute, Schlagzeilen — load this before emitting a <news> block.---# News cardsThe app renders a `<news>` block as polished article cards (thumbnail, title,publisher, summary, tap-to-open). It is an output tag, not a tool: write theJSON directly in your response text.## Workflow1. Call `web_search` with `type: "news"` and a matching `freshness`: - `pd` — past day ("today", "breaking", "heute", "gerade") - `pw` — past week ("this week", "diese Woche") - `pm` — past month - `py` — past year The news mode returns publisher, age and thumbnail directly, so no separate crawl is needed just to build the cards.2. For German or DE-specific queries, also pass `country: "DE"` and `search_lang: "de"` so the SERP is localized.3. Emit exactly one `<news>` block built from the results.4. Only call `web_crawl` afterwards when the user asks for full article detail — the cards already carry the summary.## Format<news>{"items":[{"title":"Qualcomm surges on OpenAI tie-up","publisher":"Reuters","age":"3 hours ago","url":"https://www.reuters.com/...","thumbnail":"https://...","summary":"Qualcomm shares jump 13% on reports of a partnership with OpenAI and MediaTek to develop AI smartphone processors.","breaking":false}]}</news>## Fields per item- `title`: headline (required)- `url`: article URL (required)- `publisher`: source name, e.g. "Reuters" (optional)- `age`: e.g. "3 hours ago", "1 day ago" (optional)- `thumbnail`: image URL from the search result's `thumbnail_url` (optional)- `summary`: 1-2 sentences, taken from the result description (optional)- `breaking`: true when the result is flagged BREAKING (optional)## Rules- Only include fields that came from `web_search type:"news"` results. Never fabricate URLs, publishers or thumbnails.- Do NOT also list the same articles as markdown — the cards contain everything. A short intro sentence above the block is fine.- Emit at most one `<news>` block per response.- Put the block at the very END of your answer and stop after `</news>`.

Frequently asked questions