← Back to Skills Marketplace
Cls News Scraper
by
ningjingzhiyuande
· GitHub ↗
· v1.0.0
1769
Downloads
1
Stars
11
Active Installs
1
Versions
Install in OpenClaw
/install cls-news-scraper
Description
Extract real-time stock-positive market news from Cailian Press filtered by time, sector, and event type for catalyst identification.
README (SKILL.md)
cls-news-scraper
Use this skill to pull real-time market news from Cailian Press (CLS) and extract stock-positive catalysts.
Inputs
- Time window (default: last 1 hour)
- Sector filter (default: 新能源, 消费)
- Event filter (default: 业绩预增, 重大合同, 政策扶持)
Procedure
- Collect latest CLS items from configured endpoint/source.
- Normalize fields: title, summary, ticker, company, published_at, source_url.
- Classify each item into event types.
- Keep only matched industries and event types.
- Output table rows for downstream scoring.
Output Schema
- ticker
- company
- catalyst
- source_url
- timestamp
- confidence
Usage Guidance
This skill appears coherent and low-risk, but it's underspecified. Before installing or enabling it: (1) Ask where and how the "configured endpoint/source" is provided — you should know which URL or API the agent will contact. (2) If the CLS source requires credentials, supply them only through documented, secure env/config mechanisms and verify the skill declares them. (3) Be aware the agent may perform network requests — limit or supervise autonomous runs if you do not want the agent calling external endpoints without oversight. (4) Test the skill in a controlled environment and review any outputs for sensitive data before using them in production. If you need higher assurance, request the skill author to document the exact endpoint, authentication method, and expected data format.
Capability Analysis
Type: OpenClaw Skill
Name: cls-news-scraper
Version: 1.0.0
The skill bundle consists only of metadata and a high-level description in `SKILL.md`. The `SKILL.md` outlines a procedure to collect real-time market news from Cailian Press (CLS) and extract catalysts, which aligns with the stated purpose of a news scraper. There are no instructions for data exfiltration, malicious execution, persistence, prompt injection against the agent, or any other indicators of intentional harmful behavior. The instruction to 'Collect latest CLS items from configured endpoint/source' is a necessary function for a scraper and does not specify malicious targets or unauthorized actions.
Capability Assessment
Purpose & Capability
The name and instructions match: the skill says it will pull CLS (Cailian Press) market news and extract catalysts. It does not declare any unrelated binaries, credentials, or system paths. Minor inconsistency: the instructions refer to a "configured endpoint/source" but the skill provides no mechanism (env vars, config paths, or install) for where that endpoint is set.
Instruction Scope
The runtime steps are limited to collecting items, normalizing fields, classifying events, filtering, and outputting rows — all within the stated purpose. However the collection step is underspecified (could be a web-scrape, API call, or other source). That vagueness gives the agent discretion to access arbitrary external endpoints unless the platform or user supplies explicit configuration or constraints.
Install Mechanism
No install spec and no code files — instruction-only. This is low-risk because nothing is written to disk by the skill itself.
Credentials
The skill requests no environment variables or credentials, which is proportionate. One caveat: if the CLS source requires an API key or authenticated access, the SKILL.md does not declare how such credentials would be provided, which is an omission but not necessarily malicious.
Persistence & Privilege
always is false (default) and the skill does not request system-wide changes or persistent installation. The agent may invoke the skill autonomously (platform default), which is expected behavior for skills.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install cls-news-scraper - After installation, invoke the skill by name or use
/cls-news-scraper - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of cls-news-scraper.
- Pulls real-time market news from Cailian Press (CLS).
- Extracts and classifies stock-positive catalysts based on event and sector filters.
- Outputs structured data: ticker, company, catalyst, source URL, timestamp, and confidence.
- Designed for easy filtering and downstream scoring.
Metadata
Frequently Asked Questions
What is Cls News Scraper?
Extract real-time stock-positive market news from Cailian Press filtered by time, sector, and event type for catalyst identification. It is an AI Agent Skill for Claude Code / OpenClaw, with 1769 downloads so far.
How do I install Cls News Scraper?
Run "/install cls-news-scraper" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Cls News Scraper free?
Yes, Cls News Scraper is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Cls News Scraper support?
Cls News Scraper is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Cls News Scraper?
It is built and maintained by ningjingzhiyuande (@ningjingzhiyuande); the current version is v1.0.0.
More Skills