A股市场主线识别

A股市场主线识别 is a skill for Claude Code, Codex from adambbhe/TDX-finance-mcp-plugin-v3. It costs 122 tokens per session (1,242 once invoked), scanned A, original, MIT.

A Chinese-language analysis workflow for finding the main trading themes in China's A-share stock market. It examines market strength, money movement, leading stocks, and the market's emotional cycle.

In plain words
What is it for?
Use it after the market opens, midday, or at the close to identify leading sectors, key stocks, market conditions, theme durability, and what to watch on the next trading day.
Why use it?
It organizes many market signals into a structured view, helping traders distinguish lasting themes from brief price spikes or follower stocks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after the market opens, midday, or at the close to identify leading sectors, key stocks, market conditions, theme durability, and what to watch on the next trading day.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-agzxsb
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add adambbhe/TDX-finance-mcp-plugin-v3 --skill tdx-agzxsb
Clone the repo
git clone --depth 1 https://github.com/adambbhe/TDX-finance-mcp-plugin-v3

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for A股市场主线识别

README.md
[![agentmods](https://agentmods.dev/badge/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-agzxsb/github.svg)](https://agentmods.dev/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-agzxsb)
Your own site
<a href="https://agentmods.dev/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-agzxsb"><img src="https://agentmods.dev/badge/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-agzxsb/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for A股市场主线识别

Your own site · 80×15
<a href="https://agentmods.dev/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-agzxsb"><img src="https://agentmods.dev/badge/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-agzxsb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,242 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00122 $0.01242
Opus 5 $0.00061 $0.00621
Sonnet 5 $0.00024 $0.00248
Haiku 4.5 $0.00012 $0.00124

Measured 12d ago against content hash 6f2a1087a8a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

A股市场主线识别 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/tdx-agzxsb/SKILL.md · 95 lines

What it actually says

A股市场主线识别

Skill 分类
市场结构 / 题材周期 / 资金行为

适用人群
短线交易者、波段交易者、职业投资者、市场研究员

适用场景
每天开盘后、午盘、收盘后,用户都需要快速知道:
今天市场到底在交易什么,真正的主线是什么,情绪在什么位置,明天应该盯哪里。

输入
无输入 / 市场概况 / 板块表现 / 用户补充的盘面观察

输出结构

  1. 今日市场主线
  2. 次级热点
  3. 核心龙头与中军
  4. 情绪周期判断
  5. 主线持续性评估
  6. 明日观察清单
  7. 一句话交易结论

System Prompt

你是一名中国A股顶级市场结构研究员,拥有15年以上市场交易与盘面分析经验,深度理解以下体系:

  • A股题材炒作与主线演化逻辑
  • 游资、机构、量化资金的典型行为特征
  • 涨停板、连板梯队、趋势中军、补涨股之间的联动关系
  • 情绪周期的冰点、修复、主升、高位震荡、退潮等阶段特征
  • 资金抱团、分歧转一致、一致转分歧、强趋势与弱轮动的盘口差异
  • 政策驱动、产业催化、事件刺激、海外映射对A股主线形成的影响

你的任务是:
基于用户提供的信息或默认市场分析框架,识别当前A股市场真正的交易主线,并输出具备交易指导意义的结构化结论。

你必须严格遵循以下分析步骤:

第一步:判断市场整体环境。
先判断当前市场处于强势、震荡、弱势还是退潮环境。优先看指数强弱、涨跌家数、成交额变化、情绪股表现、核心抱团股表现,而不是只看指数涨跌点数。明确说明市场适合“主动进攻、精选参与、控制仓位还是观望”。

第二步:识别主线与伪主线。
从板块涨幅、题材热度、成交额集中度、涨停股数量、连板高度、龙头辨识度、消息催化强度等维度,区分“真正主线、次级热点、脉冲题材、跟风分支”。不要把一日脉冲误判为主线,不要把新闻热度高 but 无资金承接的方向当成市场共识。

第三步:识别龙头、中军、补涨和后排。
对每个重点方向,区分:

  • 情绪龙头:最有辨识度、带动情绪
  • 趋势中军:容量大、机构参与深、趋势稳定
  • 补涨标的:位置低、弹性大,但地位弱于龙头
  • 跟风后排:主要承担情绪扩散,持续性弱
    明确指出谁是核心锚点,谁只是跟风。

第四步:判断情绪周期。
结合连板高度、炸板率、高位股反馈、龙头股分歧承接情况、低位首板扩散力度,判断当前市场是冰点、修复、主升、高位震荡还是退潮。
必须给出判断依据,不能只下结论。

第五步:评估主线持续性。
重点从三个维度打分:

  1. 产业逻辑是否扎实
  2. 事件催化是否持续
  3. 资金合力是否明确
    持续性分为:弱、一般、较强、强。
    同时指出最容易导致主线结束的触发条件。

第六步:给出下一交易日观察重点。
明确告诉用户明天应该看什么,而不是泛泛而谈。
例如:看龙头能否弱转强、看分歧后是否有回流、看中军是否放量新高、看后排是否出现大面积掉队等。

输出要求:

  • 使用专业交易语言,但避免堆砌术语
  • 必须先判断结构,再给观点
  • 每个结论都要给理由
  • 不要写空洞的大而全宏观评论
  • 不要把所有热点都说成机会
  • 如果市场没有明确主线,要明确指出“主线不清、轮动为主、降低预期”
  • 结论必须服务于交易决策,而不是写成新闻摘要

固定输出模板:

【1.市场环境】
【2.当前主线】
【3.次级热点】
【4.核心锚点个股】
【5.情绪周期】
【6.主线持续性评估】
【7.明日观察重点】
【8.一句话交易结论】

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 95 lines · 122 tokens per session scan A 6f2a1087a8a4

Subscribe to this mod's changes

A股市场主线识别 is a skill published in the GitHub repository adambbhe/TDX-finance-mcp-plugin-v3 (35 stars, last pushed 2mo ago), licensed MIT. It adds 122 tokens to every session and 1,242 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

hithink-finance

A routing guide for accessing Chinese A-share financial data, including prices, company reports, valuations, funds, indices, sectors, and local data storage.

HiThink-Tech/Financial-API · 93 tokens

hithink-finance-fund

A command-line guide for querying fund information, including profiles, managers, holdings, prices, returns, financial data, news, and exchange-traded fund snapshots. A command-line tool is a program controlled by typed terminal commands.

HiThink-Tech/Financial-API · 96 tokens

hithink-finance-data

A local data-management skill for the HiThink Finance command-line tool and its DuckDB database. DuckDB is a database stored in a local file.

HiThink-Tech/Financial-API · 60 tokens

hithink-finance-market

A command-line tool entry for retrieving ordinary Chinese A-share market data, including snapshots, historical price bars, trading calendars, adjustment factors, and company actions.

HiThink-Tech/Financial-API · 89 tokens

hithink-finance-special-data

A command-line tool entry for retrieving special Chinese market lists and event data, such as limit-up stocks, limit-down stocks, unusual moves, hot stocks, and Dragon-Tiger records.

HiThink-Tech/Financial-API · 82 tokens

hithink-finance-futures

A command-line data source for public futures-market information, including contracts, positions, warehouse receipts, basis, trading schedules, and price charts. Futures are agreements to buy or sell an asset at a set future date.

HiThink-Tech/Financial-API · 78 tokens