agentleFS
JerryLiu369JerryLiu369/awesome-quant-skills/skills/china-markets/hithink-finance-market/SKILL.md

hithink-finance-market

Skill5 starsChanged 4 days agoMITView on GitHub

普通行情和本地行情派生能力。优先使用本地库覆盖的历史/面板能力,必要时走远端同花顺金融数据服务。

The file

Files
SKILL.md
<!-- Imported from: https://github.com/Hithink-Tech-Org/Financial-API Source Path: hithink-finance-cli/skills/hithink-finance-market/SKILL.md License: MIT Curated for awesome-quant-skills -->

name: hithink-finance-market description: '通过 hithink-finance CLI 查询 A 股实时价格、行情快照、集合竞价、历史 K 线、交易日历、复权因子和公司行动,导出本地历史行情面板。'

hithink-finance-market

普通行情和本地行情派生能力。优先使用本地库覆盖的历史/面板能力,必要时走远端同花顺金融数据服务。

前置条件表

条件操作
需要认证、共用输出或维护指引按需读取 共享规则,同会话已加载内容可复用
选定命令或版本变化用目标 schema <id> --format json 核对参数;命令未知时再读取 capabilities
需要执行下表某个命令先读取对应 reference 文件,不要只凭命令名猜参数
全市场、分页、多标的或长区间使用命令声明的 --output <path> 落盘,只报告摘要

快速决策

用户意图首选命令 / 路由
单票历史日线/K 线market history;--source auto 会在本地覆盖时走本地
多只 A 股历史 K 线market history-batch --thscodes <codes>;每批最多 10 个原始代码
实时或分页行情快照market snapshot
集合竞价实时/终态快照market auction-snapshot
集合竞价短期基准market auction-benchmark
交易日历market calendar
复权因子market adjustment-factors
公司行动/除权除息事件market corporate-actions
全市场区间面板/批量研究输入market panel --output <file>
涨跌停池、炸板池、连板、热股、龙虎榜、异动切到 hithink-finance-special-data

Shortcuts

命令何时使用
market adjustment-factors查询本地日级复权因子;需要本地库。
market auction-benchmarkQuery the short-term auction benchmark; omit date for the Asia/Shanghai current date and read resolved date/date_ms from data
market auction-snapshotQuery auction snapshots whose timestamp is the response assembly timestamp
market calendarQuery the one-year A-share trading calendar
market corporate-actionsQuery adjustment events
market historyQuery daily A-share history
market history-batchQuery daily A-share history for multiple thscodes
market panel需要本地库覆盖请求窗口;适合作为研究样本输入。
market snapshotQuery A-share price snapshots

原生命令与 schema

hithink-finance capabilities --format json
hithink-finance schema <capability-id> --format json
hithink-finance market <command> --help

schema 提供当前命令选项;reference 补充业务参数关系和验收方法。全局参数、凭据与输出约定见共享规则。

边界声明

  • 不提供投资建议、买卖判断或收益承诺;只返回数据或中立统计。
  • 全市场、长区间、多标的结果必须落盘,只汇报路径、行数和关键元信息。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.