About northbound-flow-analyzer
A northbound capital-flow analysis skill for investment research and risk teams. It structures conclusions, evidence, risks, and monitoring points around confirmed inputs and available data, and flags data gaps rather than filling them in.
Key features
- 01Confirm assets, time window, and output format
- 02Fetch data through shared scripts as needed
- 03Organize evidence and conclusions using stated methods
- 04Provide risks, monitoring points, and next steps
- 05Label data dates, frequency, and definitions
Use cases
- 01Analyze northbound flows for selected assets or scopes
- 02Prepare research briefs or risk memos
- 03State analytical limits when data is unavailable
- 04Define follow-up monitoring points
Install
Copy the command and run it in a terminal.
$
npx skills add https:/ / github.com/ yuping322/ finskills --skill northbound-flow-analyzerAfter installing, type/northbound-flow-analyzerin Claude Code to confirm it loaded.
Bundled files
References and scripts installed along with SKILL.md.
LICENSE.txtreferences/data-queries.mdmethodology.mdoutput-template.mdDetails
From the project README北向资金分析器
扮演专业的投研/风控分析师。使用结构化框架完成该主题分析,并输出可复用的结论与监控要点。
工作流程
第一步:确认输入参数
与用户确认:标的/范围、时间窗口、输出偏好(列表打分 / 研究简报 / 备忘录),以及任何约束(如流动性、风险偏好)。
第二步:获取数据(按需)
- 数据获取:见
references/data-queries.md(先激活仓库根目录.venv,再用python运行共享脚本)。 - 若某类数据暂不可得:明确说明缺口,并向用户收集可替代输入(如自定义股票池、事件日期等)。
第三步:分析框架
- 先给出可解释的结论摘要(3–5条),再展开证据链。
- 指标口径、阈值与边界条件见
references/methodology.md。
第四步:输出
按 references/output-template.md 生成结构化结果,包含:关键数据、解释、风险与监控清单、下一步。
数据增强
如需实时市场数据支撑分析:请参见 references/data-queries.md,直接运行共享脚本(../findata-toolkit-cn/scripts/)。
重要注意事项
- 明确数据的日期/频率/口径;不确定时不要编造。
- A股特性:T+1、涨跌停、停牌与公告滞后可能显著影响可交易性与结论。
- 本技能输出仅供信息参考与教育目的,不构成投资建议。
Comments
Markdown supported