Battery Market Watch

电池行业国际市场动态监控系统。监控中国、美国、印度、俄罗斯、韩国的政策补贴、法规、安全事件和行业投资动态,优先使用官方/行业 RSS 与 Google News RSS 获取稳定新闻源,再抓取详情、分类利好利空并生成偏证券研究风格的周报。支持非中文新闻的原文摘要、中文翻译、以及每条新闻的单条行业解读。用户要求"运...

Security Scan

Skill generally does what its description says (collects battery news and builds reports) but there are consistency gaps you should understand before installing—notably undeclared API env vars and an undocumented local-LLM network call.

Purpose & Capability

Name/description match the code: scripts search RSS/Google News/NewsAPI/GNews, fetch article details, analyze sentiment, and generate Markdown/Word reports. The requested dependencies (httpx, curl-cffi, python-docx) are consistent with the stated functionality. No unrelated cloud credentials or binaries are requested. Minor note: the package includes code for optional NewsAPI / GNews usage, which is appropriate for a news-collection skill.

Instruction Scope

SKILL.md instructs running the included scripts and describes the workflow, which matches the code. However, the code will perform network requests to arbitrary news URLs (expected), write parsed data and reports to a local data/ directory (expected), and — importantly — analyze_sentiment.py attempts to call a local LLM at http://localhost:11434. The SKILL.md does not document this local-LLM dependency or what data is sent to it. The code does not attempt to read unrelated system files, but it does send news content (potentially sensitive if you feed private URLs) over the network to remote sites discovered via RSS/search.

Install Mechanism

This is an instruction-only skill with bundled scripts and a requirements.txt. There is no automated install spec; users must install Python deps manually (pip). No external binary downloads or obscure URLs are used. That lowers risk but requires the user to run package installs themselves in a safe/isolated environment.

Credentials

The skill does not declare required environment variables in the metadata, yet multiple scripts reference optional API keys via environment variables (GNEWS_API_KEY in scripts/search_gnews.py and NEWS_API_KEY in scripts/search_news_api.py). Those are optional but absent from declared requirements — an inconsistency. Also analyze_sentiment.py will attempt to POST article content to a local service (http://localhost:11434). While local, this is a data flow that the user should be aware of because it transmits the news content to another process running on the host.

Persistence & Privilege

The skill is not always-enabled, does not request system-wide configuration changes, and does not modify other skills. It writes outputs to an internal data/ directory (news JSON, markdown, docx) which is expected for this use case.

What to consider before installing

This skill appears to implement the described news-monitoring and report-generation workflow, but review the following before installing: - Environment variables: the code reads GNEWS_API_KEY and NEWS_API_KEY from the environment though the skill metadata does not declare them. Only set those keys if you trust the API provider and you understand rate limits and data sharing. - Local LLM call: scripts/analyze_sentiment.py will POST news content to http://localhost:11434 by default (calls a local Ollama/vLLM-like API). If you do not run a local LLM, the code falls back to a template, but if you do run one, be aware that parsed article text and titles will be sent to that local service. Ensure the local service is trusted and isolated if the content is sensitive. - Network activity and data written: the scripts fetch arbitrary news URLs discovered via RSS and web search and write parsed outputs to data/*.json/.md/.docx. Run the skill in an isolated environment (dedicated VM/container) if you are concerned about network exposure or want to limit what the system fetches. - Dependency installation: there is no automated install spec; install requirements.txt in a virtual environment and audit third-party packages if you require higher assurance. - If you need higher assurance: ask the maintainer for explicit documentation of optional API keys and local-LLM behavior, or request a version that documents all environment variables and network endpoints. If you can't obtain that, treat API keys and enabling a local LLM cautiously.

电池行业国际市场动态监控 Skill

工作流

[Step 1] scripts/search_news.py
  先抓 RSS,再抓 Google News RSS,不够再回退搜索页

[Step 2] scripts/fetch_detail.py
  抓详情页正文、日期,并做初步类型/情绪分类

[Step 3] scripts/analyze_sentiment.py
  汇总利好/利空/中性,写影响分析

[Step 4] scripts/generate_report.py
  生成偏证券研究简报风格的 Markdown 和 Word 周报

关键文件

• config.json:国家、关键词、RSS、过滤词、输出上限
• scripts/search_news.py:核心搜索入口,已经重构
• scripts/fetch_detail.py:详情抽取
• scripts/analyze_sentiment.py:分析汇总
• scripts/generate_report.py:报告生成

运行方式

手动全流程

按顺序运行:

py scripts/search_news.py
py scripts/fetch_detail.py
py scripts/analyze_sentiment.py
py scripts/generate_report.py

快速联调

py scripts/quick_test.py

报告特点

• 非中文新闻保留原文摘要 + 中文翻译
• 每条新闻带单条行业解读
• 报告加入投资结论 / 风险提示
• Word/Markdown 统一按更偏研究简报结构输出,并对重点词做高亮

输出结果

• 原始新闻:data/news_raw_YYYYMMDD.json
• 详情解析:data/news_parsed_YYYYMMDD.json
• 分析结果:data/news_analyzed_YYYYMMDD.json
• 分析摘要:data/news_analysis_YYYYMMDD.md
• 周报:data/周报_YYYYMMDD.md
• Word周报:data/周报_YYYYMMDD.docx

适用场景

• 每周五生成五国电池市场周报
• 跟踪补贴、法规、召回、火灾、扩产投资
• 快速看某国最近电池政策风向