← 返回 Skills 市场
99
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install getmeastock
功能描述
全面的A股股票分析工具,提供7大核心模块(核心财务、技术指标、估值分析、股东持股、市场热度、券商盈利预测、K线图表)+ 财报、公告、新闻资讯和交易所互动问答的多维度分析。
使用说明 (SKILL.md)
运行方式(任选其一;OpenClaw 等渠道可自行选用 Python 或 Node):
- Python 3:
python3 scripts/prana_skill_client.py -m "…" [-t thread_id] [-b base_url] - Node.js 18+:先在包根目录执行
npm install,再执行node scripts/prana_skill_client.js -m "…" [-t thread_id] [-b base_url]
付费技能说明
若本技能为付费技能,支付成功后请访问 https://claw-uat.ebonex.io/api/order/skills 获取购买记录。
鉴权与调用 Claw API 相同:请求头 x-api-key,值为 public_key:secret_key(一个英文冒号连接,与 config/api_key.txt 中单行凭证格式一致)。
安全使用建议
This package is a thin client that forwards user input to a remote Prana/Claw service and will attempt to obtain and persist API credentials locally. Before installing or running it: 1) Verify the remote base URL (default is https://claw-uat.ebonex.io/) — ensure you trust that endpoint or override NEXT_PUBLIC_URL to a known production endpoint. 2) Prefer setting PRANA_SKILL_PUBLIC_KEY and PRANA_SKILL_SECRET_KEY (or PRANA_SKILL_API_KEY) instead of relying on the client's auto-fetch. 3) If you do allow auto-fetch, set PRANA_SKILL_SKIP_WRITE_API_KEY=1 to avoid persisting secrets to disk, or run in an isolated environment/VM. 4) Do not commit config/api_key.txt to source control. 5) Review the embedded ENCAPSULATION_EMBEDDED skill_key (getmeastock / getmeastock_public) and confirm it matches the service you expect. 6) Avoid running npm install / executing scripts from untrusted origins; inspect the scripts if provenance is unclear. If you need higher assurance about where data goes or who controls the backend, ask the skill provider for a verified homepage/origin and a production endpoint.
功能分析
Type: OpenClaw Skill
Name: getmeastock
Version: 1.0.0
The skill bundle acts as a 'thin client' designed to forward user queries to a remote stock analysis service at claw-uat.ebonex.io. The scripts (scripts/prana_skill_client.py and scripts/prana_skill_client.js) manage API authentication by reading from environment variables or a local configuration file (config/api_key.txt), and include a feature to auto-fetch and save API keys if they are missing. While the scripts require network and filesystem permissions, their behavior is transparent, well-documented, and strictly aligned with the stated purpose of providing an encapsulated interface to a remote AI agent.
能力评估
Purpose & Capability
The skill description promises A-share analysis but the bundle is a 'prana' encapsulation that contains no business logic locally; instead the provided Python/Node thin clients forward user requests to a remote service (using an embedded skill_key). That design is coherent for an encapsulated skill.
Instruction Scope
SKILL.md instructs running the thin client (Python or Node). The clients will read environment variables, read/write config/api_key.txt, auto-fetch API keys via GET /api/v1/api-keys, and POST user messages and skill_key to the remote Claw/Prana API. These operations are expected for a remote-executed skill but they do transmit user inputs and may persist credentials locally — users should be aware of that data flow.
Install Mechanism
No complex install spec; Node runner requires npm install to get a small 'yaml' dependency. No downloads from arbitrary URLs or extract operations are present in the package. This is low-to-moderate install risk, typical for a Node thin client.
Credentials
No required env vars are declared, but the scripts optionally use many environment variables (NEXT_PUBLIC_URL, PRANA_SKILL_PUBLIC_KEY/SECRET_KEY/PRANA_SKILL_API_KEY, ACCOUNT_ID, flags to disable auto-fetch or prevent writing to disk). The optional envs are relevant to credential management and endpoint selection, but the default behavior will attempt an unauthenticated GET to a default base URL to obtain API keys and will write credentials to config/api_key.txt unless configured otherwise — this is powerful and worth review.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform privileges, but both clients will persist API credentials into config/api_key.txt by default and will perform network calls. Persisting secrets to disk and automatic fetching of keys increases persistence of sensitive data on the host and should be considered by the user.
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 getmeastock - 安装完成后,直接呼叫该 Skill 的名称或使用
/getmeastock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 the "give-me-a-stock" skill (全面的A股股票分析工具)
- Provides 7 core modules: Core Financials, Technical Indicators, Valuation Analysis, Shareholder Holdings, Market Sentiment, Brokerage Forecasts, and K-Line Charts
- Supports multi-dimensional analysis with financial reports, announcements, news, and Q&A from exchanges
- Usage supported via Python 3 or Node.js 18+
- Includes authentication instructions for paid skill users
元数据
常见问题
getmeastock 是什么?
全面的A股股票分析工具,提供7大核心模块(核心财务、技术指标、估值分析、股东持股、市场热度、券商盈利预测、K线图表)+ 财报、公告、新闻资讯和交易所互动问答的多维度分析。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 99 次。
如何安装 getmeastock?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install getmeastock」即可一键安装,无需额外配置。
getmeastock 是免费的吗?
是的,getmeastock 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
getmeastock 支持哪些平台?
getmeastock 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 getmeastock?
由 luokeer52(@luokeer52)开发并维护,当前版本 v1.0.0。
推荐 Skills