← Back to Skills Marketplace
czzlegend

F-AI 金融数据

by CZZLEGEND · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
216
Downloads
2
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install finloop-mktdata-skills
Description
提供全球股票、指数、基金、债券等多品类金融数据的实时与历史行情查询及公司基本面分析服务。
README (SKILL.md)

name

flp_mktdata(金融行情数据 skill)

description

本技能为 OpenClaw 提供一站式全球金融数据查询与分析能力。通过自然语言交互,可快速获取股票、指数、基金、债券等的实时、历史行情,同时深度覆盖上市及非上市公司的基本信息、财务指标、高管团队、股东结构、主营业务及融资记录。整合港股 IPO、外汇、大宗商品、虚拟资产等多品类数据,实现从行情监控到基本面研究的全流程智能支持。

功能特点

  • 基本面分析:ROE、毛利率、EPS 等核心指标
  • 全球资产覆盖:港美 A 股实时行情、外汇、基金、债券、大宗商品、虚拟资产等历史数据
  • 公司信息全景:上市/非上市公司基本信息、股东结构、主营构成分析

安装方式

npx finloop-mktdata-skills install finloop-mktdata-skill

指令

  1. 必须直接使用 HTTP 请求调用接口:使用 fetch、axios、curl 或其他 HTTP 客户端直接调用接口,禁止创建任何封装函数或 JS 文件。
  2. 禁止创建封装函数:不要创建任何 .js.ts 文件来封装接口调用,必须直接使用 HTTP 请求。
  3. 接口基础域名https://papi-uat.finloopg.com/flp-mktdata-hub(UAT;生产以实际为准)。
  4. 请求头Content-Type: application/json,Body 为 JSON。
  5. 响应格式:接口返回的数据结构需从响应中提取 dataresult 等业务字段;需检查状态码与错误信息。

能力与接口对应

用户意图 / 关键词示例 方法 路径 必填参数
股票/指数历史 K 线、某段时间走势、日 K/周 K POST /v1/stock/history code
股票实时价、最新价、涨跌幅、市值、成交量 POST /v1/stock/quote code
公司上市日、主营业务、行业、简介 POST /v1/stock/company/info ticker
公募基金名称、成立日、货币、注册地 POST /v1/fund/info isin
公募基金净值、单位净值、累计净值、某日/某段净值 POST /v1/fund/nav isin
债券名称、发行人、发行日、到期日、息率 POST /v1/bond/info isin
债券实时价、买卖价、收益率、应计利息 POST /v1/bond/latest-price isin
债券历史数据、某段时间价格走势 POST /v1/bond/history isin

完整 URL{Base URL} + 上表路径,例如 https://papi-uat.finloopg.com/flp-mktdata-hub/v1/stock/quote


接口摘要

1. 股票历史 K 线 — POST /v1/stock/history

  • 必填code(string,如 00700.HKAAPL.US600519.SH)。
  • 可选startDateendDateyyyy-MM-dd),ktype(默认 day),timenum(与 time 搭配),suspension(0/1)。
  • 返回data 数组,每项含 timeopenclosehighlowvoltotal

2. 股票实时/快照行情 — POST /v1/stock/quote

  • 必填code(string,如 00700.HKAAPL.US)。
  • 返回result 数组,每项含 quoteTimepricechgPctvolmktCapname 等。

3. 公司基本信息 — POST /v1/stock/company/info

  • 必填ticker(string,如 00700.HKAAPL.US)。
  • 返回:单条对象,含 listingDatecompanyNameindustryNamemainBusinessbrief 等。

4. 公募基金基本信息 — POST /v1/fund/info

  • 必填isin(string,如 HK0000584752)。
  • 返回:单条对象,含 isinnameCNnameENcurrencyinceptionDateregisteredRegion 等。

5. 公募基金净值 — POST /v1/fund/nav

  • 必填isin
  • 可选startDateendDateyyyy-MM-dd),或 navDate(单日;与区间同时传时以 navDate 为准)。
  • 返回data 数组,每项含 dateunitNavaccumNavtotal

6. 债券基本信息 — POST /v1/bond/info

  • 必填isin(如 US912810TV08)。
  • 返回:单条对象,含 isinnameissuerissueDatematurityDatecurrencycouponRate 等。

7. 债券实时行情 — POST /v1/bond/latest-price

  • 必填isin
  • 返回:单条对象,含 isinasOfDatemidPricebidPriceaskPricemidYield 等。

8. 债券历史数据 — POST /v1/bond/history

  • 必填isin
  • 可选startDateendDateyyyy-MM-dd);若仅填 startDate 则 endDate 默认当前日;均空则默认近一年。
  • 返回data 数组,每项含 datemidPrice 等;total

股票/指数代码格式

  • 港股:00700.HK
  • 美股:AAPL.US
  • A 股:600519.SH000001.SZ
  • 部分指数:HSI.HKDJI.USIXIC.USINX.US000001.SH399001.SZ399006.SZ000688.SH 等(详见接口文档)

通用注意事项

  1. 必须直接使用 HTTP 请求:✅ 直接使用 fetch、axios、curl 调用;❌ 禁止创建封装函数或 JS/TS 文件。
  2. Base URLhttps://papi-uat.finloopg.com/flp-mktdata-hub(UAT);生产以实际为准。
  3. 错误处理:检查 HTTP 状态码和响应体中的错误信息。
  4. 调用示例
    • fetch('https://papi-uat.finloopg.com/flp-mktdata-hub/v1/stock/quote', { method: 'POST', headers: { 'Content-Type': 'application/json' }, body: JSON.stringify({ code: '00700.HK' }) })
    • curl -X POST 'https://papi-uat.finloopg.com/flp-mktdata-hub/v1/stock/quote' -H 'Content-Type: application/json' -d '{"code":"00700.HK"}'
    • ❌ 创建 api/mktdata.ts 等封装文件并 import 调用。

相关文档

  • 详细接口文档references/REFERENCE.md(与 flp_mktdata_skill_spec.md 一致,含完整参数、返回字段及问句示例)
Usage Guidance
This package appears to be a straightforward market-data skill bundle, but check these before installing: 1) Confirm the API host: the docs point to a UAT base URL (https://papi-uat.finloopg.com/...). Make sure you intend to call UAT versus a production endpoint. 2) Authentication: there are no API key or credential fields in the manifest or SKILL.md—verify whether the API actually requires an auth token and how to provide it safely. 3) Review local install: npx install will copy files into your project's .agents/skills directory and will prompt before overwriting; run the installer from a directory where this is acceptable. 4) Strange restrictions and minor copy/paste errors (e.g., publish.sh mentions a different package) are likely benign but indicate the package may be lightly maintained—inspect the files locally before running network calls. If you need higher assurance, ask the publisher for a production base URL, authentication details, and source repository.
Capability Analysis
Type: OpenClaw Skill Name: finloop-mktdata-skills Version: 1.0.0 The skill bundle provides a standard interface for an AI agent to query financial market data (stocks, funds, bonds) from a specified API endpoint (papi-uat.finloopg.com). The installation logic in 'lib/install.js' and 'bin/finloop-skills.js' is a straightforward file-copying utility that moves local skill assets into the agent's workspace. The instructions in 'SKILL.md' contain functional constraints (e.g., requiring direct HTTP calls instead of creating wrapper files) which appear intended to simplify agent behavior rather than facilitate an attack.
Capability Assessment
Purpose & Capability
Name/description match the provided SKILL.md and reference docs. The package contains a manifest, docs, and an installer that copies the skill into a local .agents/skills folder—consistent with installing a skills bundle for market-data queries.
Instruction Scope
Instructions require direct HTTP POSTs to https://papi-uat.finloopg.com/flp-mktdata-hub and explicitly forbid creating local JS/TS wrapper files. Direct POSTs to the external UAT host are coherent for an API-based data skill, but the ban on wrappers is unusual (limits agent implementation flexibility) and the docs do not mention any authentication or API keys—verify whether the API requires credentials.
Install Mechanism
No remote downloads or package installs. The included lib/install.js and bin/finloop-skills.js copy the skill bundle into a .agents/skills directory under the current working directory. This writes files locally but does not fetch external code—reasonable for a local skill installer.
Credentials
The skill declares no required env vars, binaries, or config paths. That aligns with the supplied SKILL.md which shows unauthenticated example calls, though absence of any auth mention is surprising for a market-data API and should be confirmed.
Persistence & Privilege
always is false and the installer only writes into the project's .agents directory (with a user prompt on overwrite). The skill does not request system-wide privileges or modify other skills' configs.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install finloop-mktdata-skills
  3. After installation, invoke the skill by name or use /finloop-mktdata-skills
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of flp_mktdata (金融行情数据 skill) providing one-stop global financial market data and analysis via natural language. - Supports real-time and historical data for stocks, indices, funds, bonds, commodities, and virtual assets. - Offers comprehensive company information (including both public and private firms), key financials, executive teams, shareholder structures, and business summaries. - Enforces direct HTTP requests for all interfaces; prohibits wrapper functions or JS/TS encapsulation. - Provides detailed API instructions, including required parameters, URL formats, and error handling guidance.
Metadata
Slug finloop-mktdata-skills
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is F-AI 金融数据?

提供全球股票、指数、基金、债券等多品类金融数据的实时与历史行情查询及公司基本面分析服务。 It is an AI Agent Skill for Claude Code / OpenClaw, with 216 downloads so far.

How do I install F-AI 金融数据?

Run "/install finloop-mktdata-skills" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is F-AI 金融数据 free?

Yes, F-AI 金融数据 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does F-AI 金融数据 support?

F-AI 金融数据 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created F-AI 金融数据?

It is built and maintained by CZZLEGEND (@czzlegend); the current version is v1.0.0.

💬 Comments