agentleFS
HaochenhustHaochenhust/ch-skills/skills/news-scanner/SKILL.md

news-scanner

Skill9 starsChanged 4 months agoMITView on GitHub

This skill should be used during daily research scanning, or when the user asks '最近有什么新消息', '扫描一下XX的最新动态', '帮我看看雪球上在聊什么'. Scans Xueqiu, Eastmoney, 10jqka, and web search for investment-related news filtered by the industry-chain keywords you track. Outputs HIGH/MEDIUM findings only — signal, not noise.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When researching a new industry chain

    line 14
  2. Distinctive:

    When a catalyst event just happened and you need the market reaction

    line 15
  3. Distinctive:

    Only report HIGH and MEDIUM findings.

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

News Scanner

Systematic news and sentiment scanning for the industry chains you track.

When to Use

  • Daily research passes (a few times per day)
  • When researching a new industry chain
  • When a catalyst event just happened and you need the market reaction

Workflow

Step 1: Load Keywords

Build a keyword list from the industry chains and key stocks you currently track (e.g. from your research-state / watchlist notes).

Step 2: Multi-Source Scan

For each tracked industry chain, search across platforms:

1. WebSearch: "{keyword} 研报 一致预期"          (analyst reports first)
2. WebSearch: "{keyword} site:xueqiu.com 2026"
3. WebSearch: "{keyword} site:eastmoney.com 2026"
4. WebSearch: "{keyword} 最新消息 {today's date}"
5. WebSearch: "{stock name} 研报 最新"

Step 3: Filter & Prioritize

Rate each finding:

  • HIGH: Directly affects your thesis or triggers a buy/sell signal
  • MEDIUM: Relevant background, updates your understanding
  • LOW: Noise, already known, or not actionable

Only report HIGH and MEDIUM findings.

Step 4: Output

For routine scans with nothing major: update your research log, don't message the user.

For significant findings:

## 信息扫描 — {date} {time}

### 重要发现
- [{HIGH/MEDIUM}] {source}: {summary} — 影响:{how it affects the thesis}

### 研究状态更新
- {track name}: 置信度 {unchanged/+5%/-5%} — 原因:{finding}

Platforms & Keywords

Default Search Targets

  • 雪球 (xueqiu.com) — retail sentiment, hot discussions
  • 东方财富 (eastmoney.com) — news, research reports
  • 同花顺 (10jqka.com.cn) — sector analysis
  • 券商研报 / 一致预期 — via general WebSearch
  • General web — for broader news coverage

Keyword Construction

From your tracked chains/stocks, build searches like:

  • Industry: "{细分材料}", "{细分器件}"
  • Companies: "{公司名A}", "{公司名B}"
  • Events: "{行业大会} 2026", "{龙头公司}"
  • Themes: "{产业链主题}"

Rules

  1. Don't repeat known information — check your notes before reporting
  2. Cite sources — every finding must have a URL or source name
  3. Signal, not noise — the user wants actionable intel, not a news digest
  4. Update your research log — every scan should at minimum leave a trace

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.