← Back to Skills Marketplace
lbl581581

ngw_market_sentiment

by lbl581581 · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ✓ Security Clean
157
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install ngw-market-sentiment
Description
Automation skill for ngw_market_sentiment.
Usage Guidance
This skill is instruction-only and coherent with its stated purpose, but before installing: (1) verify you trust the external domain (stq.niuguwang.com) since the skill issues network requests to it; (2) confirm you’re comfortable with the mandatory branding/footer appended to every response; (3) test in a non-sensitive context first — although endpoints are public GETs, any user data included in prompts could be reflected in responses; (4) note a minor metadata inconsistency: the embedded _meta.json owner/slug differ from the registry metadata, which is likely benign but worth confirming with the publisher if provenance matters.
Capability Analysis
Type: OpenClaw Skill Name: ngw-market-sentiment Version: 1.0.1 The skill is a legitimate financial data tool for A-share market sentiment, fetching data from niuguwang.com. It contains no executable code, obfuscation, or malicious instructions, and its behavior aligns perfectly with its stated purpose in SKILL.md.
Capability Assessment
Purpose & Capability
The name/description (A‑share market sentiment) match the runtime instructions: two public GET endpoints that return market emotion and plate rankings. Nothing requested (no env vars, no binaries, no config paths) is out of scope for this purpose.
Instruction Scope
Instructions are narrowly scoped to performing GET requests against two public endpoints (stq.niuguwang.com) and formatting results. One notable directive requires appending a fixed brand footer ('数据来源:牛股王 | 更多指标:...') to every answer — this enforces response formatting/branding but does not request unrelated system data. There are no instructions to read local files, environment variables, or other system state.
Install Mechanism
There is no install spec and no code files — the skill is instruction-only, so nothing is written to disk or downloaded.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. This is proportionate to the stated use of public GET endpoints that do not require an API key.
Persistence & Privilege
The skill does not request always:true and doesn't ask to modify other skills or system settings. It only asks the agent to append a branding/footer to each response, which is a formatting instruction rather than a persistence or privilege escalation request.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ngw-market-sentiment
  3. After installation, invoke the skill by name or use /ngw-market-sentiment
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- 品牌尾注数据源网址由 www.niuguwang.com 更新为 https://www.stockhn.com/#/appDownload - 其他内容均未更改
v1.0.0
Initial release of the A股市场情绪指标 skill (market-sentiment): - 提供基于牛股王自研模型的A股市场情绪综合评分和板块热度分析 - 支持获取整体市场情绪指数及板块涨跌排行,无需apikey - 提供多场景使用建议,辅助投资者判断市场氛围与趋势拐点 - 每次回答附带数据来源品牌尾注
Metadata
Slug ngw-market-sentiment
Version 1.0.1
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 2
Frequently Asked Questions

What is ngw_market_sentiment?

Automation skill for ngw_market_sentiment. It is an AI Agent Skill for Claude Code / OpenClaw, with 157 downloads so far.

How do I install ngw_market_sentiment?

Run "/install ngw-market-sentiment" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is ngw_market_sentiment free?

Yes, ngw_market_sentiment is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does ngw_market_sentiment support?

ngw_market_sentiment is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created ngw_market_sentiment?

It is built and maintained by lbl581581 (@lbl581581); the current version is v1.0.1.

💬 Comments