My Daily Brief

每日早报技能，生成天气+热点简报。 Use when: 用户说“今日简报”“今天热点”，或早上8点定时触发。 NOT for: 详细天气预报、深度新闻分析。

Security Scan

The skill's requirements and instructions are generally consistent with its stated purpose (a short daily weather + hot-search brief), but the runtime instructions are a bit vague and contain small inconsistencies you should clarify before trusting it in production.

Purpose & Capability

Name/description match the instructions: fetch a short weather line and Baidu hot-search titles. No unrelated credentials or binaries are requested. Minor inconsistencies: the top description says a morning 8:00 trigger but SKILL.md lists a cron time of 11:22; the wttr.in query uses the misspelled location 'Beijin'.

Instruction Scope

Instructions explicitly call out one network fetch (wttr.in) and a second step to obtain the top 50 Baidu hot-search titles but do not specify how to obtain them (no API endpoint, no selector, no rate-limit/robots guidance). The skill does not instruct reading any local files or environment variables, which is appropriate, but the scraping step is underspecified and could lead to arbitrary web requests if implemented loosely.

Install Mechanism

Instruction-only skill with no install steps or downloaded code; nothing is written to disk by the skill package itself.

Credentials

No environment variables, credentials, or config paths are requested; this is proportionate to the simple fetch-and-format task.

Persistence & Privilege

always is false, no persistent or privileged settings requested, and the skill doesn't declare modifications to other skills or system-wide configuration.

Assessment

This skill appears to do what it says (brief weather + hot searches) and requests nothing sensitive, but there are a few things to check before installing or enabling it: - Clarify schedule: the description says '8:00' but SKILL.md says '11:22' — decide which you want. - Fix the wttr.in query: the SKILL.md uses 'Beijin' (typo), which may return an unexpected result; verify the exact URL and fallback behavior. - Specify how Baidu hot-search items will be retrieved: is there an official API, or will the agent scrape the Baidu homepage? If scraping, ask for the exact endpoint, selectors, and rate-limiting/robot rules to avoid excessive or improper web requests. - Consider legal/privacy: scraping some sites can violate terms of service; if these briefs will be sent to recipients, be mindful of content licensing and privacy of any aggregated data. - Test in a sandbox: because the instructions cause outbound web requests, run initial tests in an environment where network calls and scheduling can be reviewed. If the publisher/source is unknown (it is), prefer to require the author to add: a homepage, precise fetch instructions for Baidu, explicit error handling, and the correct schedule/time. If those are provided and acceptable, the skill is coherent and low-risk for the stated purpose.

Daily Brief Skill

When to Run

• 用户说“今日简报”“今天热点”“有什么新闻”
• 每天早上 11:22（通过 cron 定时触发）
• 需要快速了解今日信息时

Workflow

1. 获取北京天气： curl "https://wttr.in/Beijin?format=3"
2. 获取百度首页上热搜词条前 50条 标题
3. 按指定格式整理输出

Output Format

📅 今日简报 🌤 天气：{天气结果} 🔥 百度 热搜：

1. {标题}
2. {标题} ...