China Idea Generation logo

China Idea Generation

Community
jwangkun
china-idea-generation

Systematic stock screening and investment idea sourcing for A-share markets. Combines quantitative screens, thematic research, and pattern recognition to surface new long and short ideas. Adapted from the original idea-generation skill for Chinese market conventions and data sources. Triggers on "A股选股", "股票筛选", "寻找机会", "stock screen China", "A-share ideas", "find ideas for Chinese stocks", or "screen for A-share opportunities".

Overview

Publisherjwangkun
Repositoryclaude-for-financial-services-cn
Skill namechina-idea-generation
Stars
834
Forks
132
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by jwangkun on GitHub. Read the source before you install it.

Installation

Install the China Idea Generation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/jwangkun/claude-for-financial-services-cn/tree/main/agent-plugins/china-earnings-reviewer/skills/china-idea-generation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jwangkun/claude-for-financial-services-cn.git /tmp/claude-for-financial-services-cn
mkdir -p .claude/skills
cp -r /tmp/claude-for-financial-services-cn/agent-plugins/china-earnings-reviewer/skills/china-idea-generation .claude/skills/china-idea-generation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable China Idea Generation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads China Idea Generation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so China Idea Generation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

china-idea-generation

Purpose

Systematically surface new A股投资机会 through quantitative screens, thematic analysis, and pattern recognition.

Data Sources

Primary: iFind MCP (Tier-1 付费) / AkShare MCP (Tier-2 免费备选)

python
get_market_overview()                    → Top gainers, losers, most active
get_quote(ticker)                        → Price, PE, PB, market cap
get_historical_data(ticker)              → Price trends, momentum
get_financials(ticker, "income")         → Financial metrics
get_financials(ticker, "balance")        → Balance sheet health
get_industry_stocks(industry="...")      → Peer comparison

Secondary Screening Data

DataSourceUse
龙虎榜 (Dragon-Tiger list)东方财富Unusual activity, institutional interest
北向资金 (Northbound flows)沪深港通Foreign investor sentiment
融资融券 (Margin trading)交易所Leverage and sentiment
股东人数变化巨潮Institutional accumulation/distribution
机构持仓季报/F10Fund ownership trends
大宗交易 (Block trades)交易所Smart money signals

Workflow

Step 1: Define Screen Criteria

Investment philosophy alignment:

  • Value vs Growth vs GARP vs Momentum
  • Market cap preference (large / mid / small)
  • Sector focus or sector-agnostic
  • Liquidity requirements (turnover threshold)
  • Risk tolerance (volatility, leverage, earnings stability)

Screen parameters (A-share specific):

ParameterTypical RangeNotes
PE (TTM)5-50xAvoid negative PE
PB0.5-5x<1x may indicate distress
PS0.5-5xFor high-growth unprofitable
Market cap>50亿Liquidity threshold
Daily turnover>5000万Tradability
ROE>10%Quality filter
Debt/Equity<100%Financial health
Revenue growth>10%Growth filter
EPS growth>15%Earnings momentum

Step 2: Quantitative Screens

Screen 1: Deep Value (深度价值)

Filters:
- PE (TTM) < 15x AND PB < 1.5x
- ROE > 10% (past 3 years average)
- Debt/Equity < 80%
- Revenue growth > 0% (not declining)
- Market cap > 30亿

Output: Value candidates with potential mispricing

Screen 2: Growth at Reasonable Price (GARP)

Filters:
- PEG < 1.0 (PE / growth rate)
- Revenue growth > 20%
- Gross margin > 30%
- ROE > 15%
- Market cap > 100亿

Output: Quality growth at reasonable multiples

Screen 3: Momentum (趋势跟踪)

Filters:
- Price above 20-day MA AND 60-day MA
- Price within 10% of 52-week high
- Volume above 20-day average
- RSI between 40-70 (not overbought)
- Upward earnings revision

Output: Momentum names in uptrends

Screen 4: Turnaround (困境反转)

Filters:
- Recent loss or margin compression
- New management / strategy announced
- Order book recovering
- Debt restructuring completed
- Insiders buying

Output: Potential turnaround candidates

Screen 5: Dividend Yield (高股息)

Filters:
- Dividend yield > 3%
- Payout ratio < 60%
- FCF positive and stable
- Debt/Equity < 100%
- Stable earnings history

Output: High-quality income names

Screen 6: Special Situations (事件驱动)

Filters:
- Lock-up expiry within 3 months (限售解禁)
- M&A announcement pending
- Regulatory catalyst (集采结果, etc.)
- Index inclusion/exclusion
- STAR/ChiNext eligibility

Output: Event-driven opportunities

Step 3: Thematic Research

Identify emerging themes:

Theme TypeExamples (A-share)Data Sources
Policy-driven国产替代, 新基建, 双碳政策文件, 部委公告
TechnologyAI应用, 自动驾驶, 机器人技术进展, 订单公告
Demographics老龄化, 少子化人口数据, 消费数据
Consumption消费升级, 国货崛起零售数据, 品牌调研
Industrial高端制造, 专精特新行业数据, 政策

Thematic screening approach:

  1. Define theme and investable universe
  2. Map A-share companies to theme
  3. Rank by exposure and quality
  4. Identify pure-plays vs beneficiaries

Step 4: Technical Analysis

A-share technical considerations:

IndicatorUse
均线 (Moving averages)Trend direction (5/10/20/60/120 day)
MACDMomentum and trend changes
RSIOverbought/oversold
KDJShort-term momentum
成交量 (Volume)Confirmation of moves
龙虎榜Institutional activity
北向资金Foreign flows

Chart patterns to watch:

  • 突破 (breakout) — above resistance
  • 回踩 (pullback to support) — entry opportunity
  • 双底/头肩 (double bottom/head & shoulders) — reversal signals
  • 量价背离 (volume-price divergence) — trend exhaustion

Step 5: Fundamental Deep Dive

For each candidate:

  1. Business model review: How does company make money?
  2. Financial health: Balance sheet, cash flow, earnings quality
  3. Competitive position: Market share, moat, pricing power
  4. Management quality: Track record, capital allocation
  5. Valuation: vs peers, vs history, vs international peers
  6. Catalyst: What could re-rate the stock?

Red flag checklist:

  • 商誉占比过高 (>30% of equity)
  • 应收账款增速 > 收入增速
  • 经营现金流持续为负
  • 大股东质押比例过高 (>50%)
  • 审计意见非标准无保留
  • 频繁变更会计师事务所
  • 关联交易占比高

Step 6: Build the Ideas List

Standard format:

RankTickerCompanySectorIdea TypeThesisCatalystRiskConviction
{{RANK}}{{TICKER}}{{COMPANY_NAME}}{{SECTOR}}{{DIRECTION}}{{THESIS}}{{CATALYST}}{{RISK}}{{CONVICTION}}
Example600519贵州茅台白酒Long批价稳+动销旺+分红高Q1业绩超预期批价下行High
2........................

Conviction levels:

  • High: Strong thesis, clear catalyst, limited downside
  • Medium: Good thesis, catalyst timeline uncertain
  • Low: Exploratory, needs more research

Step 7: Monitor & Update

Ongoing tracking:

  • Weekly price and news updates
  • Catalyst tracking (china-catalyst-calendar)
  • Thesis validation / invalidation
  • Position sizing recommendations

Update triggers:

  • Earnings results
  • Material news (M&A, guidance, regulation)
  • Price moves >15% in a week
  • Thesis breaking or confirming

China-Specific Screening Considerations

Market Structure

FeatureScreening Implication
涨跌停限制Momentum may be interrupted
散户占比高Sentiment-driven overreactions common
政策敏感Regulatory risk premium in certain sectors
北向资金Track foreign flows for large-caps
龙虎榜Unusual activity signals
停牌 (Trading halt)Due diligence risk for suspended names

Common A-share Investment Styles

StyleDescriptionKey Metrics
价值投资Deep value, dividend, asset-basedPB, dividend yield, 破净
成长投资High growth, innovationRevenue growth, R&D intensity
主题投资Policy/trend themesCatalyst proximity, theme purity
技术分析Chart-based trading均线, MACD, 量价
量化策略Systematic, factor-basedMulti-factor models
打新IPO subscription中签率, 涨幅预期

Sector-Specific Screening

SectorScreening Focus
白酒批价趋势, 渠道库存, 回款, 品牌力
半导体产能利用率, 国产替代进度, 技术迭代
新能源产能过剩/出清, 技术路线, 补贴退坡影响
医药创新药管线, 集采中标, 国际化
银行NIM趋势, 不良率, 拨备, 估值 (破净)
房地产销售额, 融资能力, 土储质量
消费动销, 库存, 消费升级/降级趋势

Quality Checks

Before delivering ideas list:

  • Screen criteria documented and reproducible
  • Each candidate has fundamental backing
  • Catalysts identified for each idea
  • Risk factors clearly stated
  • Conviction levels assigned
  • Liquidity verified (tradable)
  • Regulatory/compliance review passed

Data Source Mode Switch: Set env var IFIND_DATA_SOURCE_MODE to control data source preference.

  • ifind-only (strict): Use iFind only, error if unavailable
  • ifind-fallback (default): iFind preferred, fallback to AkShare
  • akshare-only, wind-only (Wind only), wind-fallback (Wind first, fallback to iFind → AkShare): Skip iFind, use AkShare only

Frequently asked questions

What does the China Idea Generation AI skill do?

Systematic stock screening and investment idea sourcing for A-share markets. Combines quantitative screens, thematic research, and pattern recognition to surface new long and short ideas. Adapted from the original idea-generation skill for Chinese market conventions and data sources. Triggers on "A股选股", "股票筛选", "寻找机会", "stock screen China", "A-share ideas", "find ideas for Chinese stocks", or "screen for A-share opportunities".

Why use China Idea Generation on TypingMind?

Because you install it once and use it with any model. China Idea Generation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install China Idea Generation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jwangkun/claude-for-financial-services-cn/tree/main/agent-plugins/china-earnings-reviewer/skills/china-idea-generation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use China Idea Generation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with China Idea Generation?

As many as you like. As long as a model supports skills, you can use China Idea Generation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the China Idea Generation AI skill free?

Yes. It is published on GitHub by jwangkun under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇