← 返回 Skills 市场
News Sentiment Analysis
作者
haohanyang92
· GitHub ↗
· v1.0.0
· MIT-0
754
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install news-sentiment-analysis
功能描述
区分"真利好"和"假利好"，避免追高被套。用于A股消息面分析。
使用说明 (SKILL.md)
消息面分级解读 Skill
核心能力
区分"真利好"和"假利好"，避免追高被套。
利好分级规则
一级利好（可重仓追涨）
- 国家级政策落地（如降息、行业扶持）
- 龙头股直接受益
- 操作建议：可重仓追涨
二级利好（轻仓参与）
- 行业事件（如产业链涨价、技术突破）
- 板块联动性强
- 操作建议：轻仓参与
无效利好（观望为主）
- 公司常规公告（如股东增持、战略合作）
- 无资金承接
- 操作建议：观望为主
实战规则
补贴类利好判断
看到"某公司获政府补贴"公告时：
- 判断补贴金额占净利润的比例
- 比例 \x3C 5% 为无效利好
- 再看板块资金流向
追高避坑
- 利好发布后已涨停2次以上，谨慎追
- 利好发布但无资金承接，及时止盈
触发场景
- "这个利好是真的吗"
- "能追吗"
- "这个公告是利好还是利空"
安全使用建议
This skill is an offline, prose guide (no code) describing how to judge A‑share news and appears internally consistent. Before using it: (1) remember it’s a heuristic, not financial advice—test it on known examples; (2) decide and control where your agent will fetch market/flow data (trusted APIs only), since the SKILL.md doesn’t specify sources; (3) monitor any autonomous runs if the agent is allowed to act on its own, and do not provide private credentials (none are required by this skill). If a future version adds installs, env vars, or remote endpoints, re‑review for coherence and safety.
功能分析
Type: OpenClaw Skill
Name: news-sentiment-analysis
Version: 1.0.0
The skill bundle consists entirely of metadata and instructional content in SKILL.md focused on providing heuristics for A-share stock market sentiment analysis. There is no executable code, no network activity, and no instructions that attempt to exfiltrate data or compromise the agent's security.
能力评估
Purpose & Capability
The name/description and the SKILL.md all describe the same task (classifying news as 'real' vs 'fake' positive signals for A‑shares). There are no unrelated env vars, binaries, or install actions requested.
Instruction Scope
The SKILL.md contains high‑level heuristics (e.g., check subsidy size relative to profit, review sector capital flows) but does not specify data sources or commands. It does not instruct reading local files, env vars, or sending data to external endpoints, but because it implies checking market/flow data an agent would need to fetch that data from somewhere—those data-source choices are not specified.
Install Mechanism
No install spec and no code files are present (instruction-only). Nothing will be written to disk or executed during install.
Credentials
The skill declares no required environment variables, credentials, or config paths; requested access is minimal and proportional to the stated purpose.
Persistence & Privilege
always is false and the skill does not request persistent or elevated platform privileges. It does not modify other skills or system configs.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install news-sentiment-analysis - 安装完成后，直接呼叫该 Skill 的名称或使用
/news-sentiment-analysis触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release of news-sentiment-analysis skill for A股消息面分析
- Distinguishes between genuine and superficial positive news to help users avoid buying at highs
- Provides graded analysis: top-level (strong buy), secondary (light buy), and ineffective (wait and see) positives
- Includes actionable rules for policymaking, sector events, and company announcements
- Features practical tips for evaluating government subsidies and avoiding traps after multiple price surges
- Supports scenarios like verifying positive news, buy/sell timing, and interpreting company announcements
元数据
常见问题
News Sentiment Analysis 是什么？
区分"真利好"和"假利好"，避免追高被套。用于A股消息面分析。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 754 次。
如何安装 News Sentiment Analysis？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install news-sentiment-analysis」即可一键安装，无需额外配置。
News Sentiment Analysis 是免费的吗？
是的，News Sentiment Analysis 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
News Sentiment Analysis 支持哪些平台？
News Sentiment Analysis 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 News Sentiment Analysis？
由 haohanyang92（@haohanyang92）开发并维护，当前版本 v1.0.0。
推荐 Skills