daymade-sector-research

Researches A-share sectors via top gainers, announcements, and sentiment evidence grading.

1.4k|216|Updated Oct 22, 2025
One-click install
npx skills add https://github.com/daymade/claude-code-skills --skill daymade-sector-research
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: daymade-sector-research
Source: https://github.com/daymade/claude-code-skills/tree/main/daymade-financial/daymade-sector-research
Command: npx skills add https://github.com/daymade/claude-code-skills --skill daymade-sector-research

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Conducting sector-level investment research on Chinese A-share markets requires stitching together constituent stock lists, real-time quotes, corporate announcements, and market sentiment from fragmented public data sources, while avoiding fabricated or unverified conclusions.

Core Features & Use Cases

  • Top N Gainers Pipeline: Fetches East Money board constituents and Sina real-time snapshots to rank top N stocks by gain, with full-board distribution bucketing into CSV files.
  • Dual-Source Announcement Retrieval: Queries cninfo and East Money announcement APIs with cross-validation, week/month window bucketing, B-share to A-share code mapping, and zero-result widening checks.
  • Evidence-Graded Sentiment Analysis: Classifies market sentiment evidence into L1 (first-hand quotes), L2 (timestamped media), and L3 (unverified leads), with parallel agent orchestration and adversarial fresh-context verification.
  • Use Case: Ask for the top 10 pharmaceutical stocks today, their announcements from the past week and month, and an evidence-based sentiment judgment, delivered as a verified research report with explicit uncertainty annotations.

Quick Start

Ask the assistant to run a sector research workflow on an A-share industry, for example: give me today's top 10 gainers in the pharmaceutical sector, their announcements from the past week and month, and an evidence-based market sentiment assessment.

Frequently Asked Questions about daymade-sector-research

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I get the top gaining stocks in an A-share sector?

Run the top_n_pipeline.py script with an East Money board code like BK1216. It fetches board constituents from the push2 API, pulls Sina real-time snapshots, ranks by percentage gain, and writes top N, full-board quotes, and distribution CSVs.

How to query Chinese listed company announcements by date window?

Use the ann_query.py script with stock codes and an end date. It queries cninfo hisAnnouncement as the primary source and East Money np-anotice for cross-validation, bucketing results into one-week and one-month windows in a CSV output.

Does this skill support Beijing Stock Exchange and B-share stocks?

Yes. Beijing Stock Exchange codes (43/83/87/92 prefixes) are queried through the cninfo gfbj channel since bse.cn interfaces are unreliable. B-share codes (900/200) are automatically mapped to their corresponding A-share codes for announcement retrieval.

Why does announcement search return zero results for a stock?

Zero monthly results often indicate a wrong orgId parameter rather than genuinely no announcements. The script widens to a 90-day window and checks a second source; only when both confirm no recent filings does it conclude the stock truly has no announcements.

What are the limitations of the market sentiment judgment?

Sentiment conclusions only rest on L1 first-hand quotes and L2 timestamped media; unverified headlines are listed as pending leads only. Shenwan industry index real-time values and sector capital flow data are unavailable from public endpoints and are explicitly marked as not obtained.