ClawHub

Daily Ai News

v0.1.0

Aggregates and summarizes the latest AI news from multiple sources including AI news websites and web search. Provides concise news briefs with direct links to original articles. Activates when user asks for 'today's AI news', 'AI updates', 'latest AI developments', or mentions wanting a 'daily AI briefing'.

⭐ 29· 5.6k·53 current·56 all-time
by@laurent-zhu
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (daily AI news aggregator) matches the instructions and reference lists: it fetches news sites, runs web searches, deduplicates, categorizes, and formats summaries. Required resources (none) are consistent with an instruction-only aggregator that relies on platform-provided web-reading/search tools.
ℹ
Instruction Scope
The SKILL.md gives a narrow, well-defined 4-phase workflow (fetch, filter, categorize, format) and a list of sensible sources and query templates. It assumes availability of platform tools named mcp__web_reader__webReader and WebSearch; if those tools do not exist or have different semantics (e.g., date-filter syntax), the skill may fail. It instructs only network fetches of public web content and does not request local files or sensitive data.
✓
Install Mechanism
No install spec and no code files—instruction-only—so nothing is written to disk or downloaded during install. This is low-risk and proportional for a simple aggregator.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. That is appropriate for a public-web news summarizer. There are no unexplained secret or credential requests.
✓
Persistence & Privilege
always:false and default agent invocation settings are used. The skill does not request permanent/system-wide privileges, nor does it modify other skills' config.
Assessment
This skill appears coherent and only needs platform web-reading/search capabilities. Before installing, confirm that your agent environment provides the named web-reading and search tools (mcp__web_reader__webReader and WebSearch) and that their date-filter/search syntax matches the SKILL.md templates. Be aware it will make external network requests to fetch articles (including potentially paywalled content or sites that block scraping). No credentials are requested, so there's no direct credential-exfiltration risk from the skill itself, but review your organization's policy on connecting agents to the public web and on storing or sharing fetched article content.

Like a lobster shell, security has layers — review code before you run it.

latestvk978d80c6gp6cc0my8zwxqzh8x80f4ec

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments