Skip to content
Get packs

龙虎榜 Analyzer (LHB Analyzer)

Reads China A-share Dragon-Tiger List data to identify hot-money seats and institutional vs speculative flows

Source Download skill
Repository
wbh604/UZI-Skill
Stars
7,490
Licence
MIT
Files
3 files

What it does

When you ask about who is buying a Chinese A-share stock or what the recent Dragon-Tiger List (龙虎榜, a daily exchange disclosure of the biggest trading seats) looks like, the agent fetches that data through a bundled script, matches the brokerage seats against a database of about 22 well-known 'hot money' trader seats, and reports which ones are active, whether institutions or speculators dominate net buying, and how the stock ranks against peers on the same board. The output is a structured markdown report ending in a one-line verdict. It is a market-analysis aid, not a trading recommendation.

Great for

  • Retail or semi-professional investors who follow China A-share short-term trading and want a quick seat-level breakdown
  • Analysts studying hot-money and institutional behaviour on the Dragon-Tiger List
  • Developers who want a template for structured Chinese market-microstructure reports

Skip it if

  • Anyone relying on its verdict as investment advice: the seat labels are heuristic and the output presents them with confident wording, so acting on it can lead to real financial losses
  • Non-China-market users or non-Chinese-language workflows, since the data and seat names are specific to A-shares and Chinese-language sources

Try asking

  • “谁在买这只票？ (Who is buying this stock?)”
  • “最近龙虎榜怎么样？ (How has the Dragon-Tiger List looked recently?)”
  • “章盟主有没有上榜这只票？ (Did seat 章盟主 appear on this stock's list?)”
  • “这是不是某游资的票？ (Is this one of a particular hot-money trader's stocks?)”
Step-by-step guide: how to use 龙虎榜 Analyzer (LHB Analyzer)Install, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 3 original files, the MIT licence and an attribution note.

    lhb-analyzer.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip lhb-analyzer.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip lhb-analyzer.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Verify any seat identification against the official exchange disclosure before relying on it, since the seat-to-trader mapping is an interpretation and can be wrong.
  • Ask for the peer-board comparison explicitly if you want the leader ranking, and treat the 'conclusion' sentence as a summary of the data rather than a recommendation.
  • Review scripts/fetch_lhb.py and lib/seat_db.py yourself before running, because they were not among the files supplied for this assessment and the skill is documented to execute them.

What's inside

  • assets/seats-2026.json
  • references/seat-encyclopedia.md
  • SKILL.md

Redistributed unmodified from wbh604/UZI-Skill under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.