China Thesis Tracker logo

China Thesis Tracker

Community
jwangkun
china-thesis-tracker

Maintain and update investment theses for A-share portfolio positions and watchlist names. Track key data points, catalysts, milestones, and thesis validity over time. Adapted from the original thesis-tracker skill for Chinese market conventions. Triggers on "A股持仓逻辑跟踪", "投资逻辑更新", "thesis check China", "update thesis for [company]", "is my thesis still intact", or "A股持仓复盘".

Overview

Publisherjwangkun
Repositoryclaude-for-financial-services-cn
Skill namechina-thesis-tracker
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 Thesis Tracker 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-thesis-tracker
  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-thesis-tracker .claude/skills/china-thesis-tracker
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable China Thesis Tracker 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 Thesis Tracker 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 Thesis Tracker 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-thesis-tracker

Purpose

Track and maintain A股投资逻辑/thesis for portfolio positions and watchlist names, ensuring thesis validity is continuously monitored.

Data Sources

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

python
get_quote(ticker)                        → Current price, valuation
get_historical_data(ticker)             → Price trajectory
get_financials(ticker, "income")         → Financial performance
# News (china-news MCP — separate server)
get_stock_news(ticker="{{TICKER}}")          → News affecting thesis
get_industry_stocks(industry="...")      → Peer context

Secondary Sources

  • 巨潮公告 — corporate actions and filings
  • 业绩说明会 — management commentary
  • 券商研报 — analyst updates
  • Wind / Choice — ownership and flow data

Workflow

Step 1: Define / Load Thesis

Thesis statement template:

公司:[Company]([Ticker])
行业:[Industry]
方向:[Long / Short / Watch]

核心投资逻辑 (3-5 bullet points):
1. [Key driver 1]
2. [Key driver 2]
3. [Key driver 3]

目标价:¥XX.XX (X% upside/downside)
时间 horizon:[6M / 1Y / 2Y]
置信度:[High / Medium / Low]

Thesis components:

ComponentDescriptionExample
核心逻辑 (Core thesis)Why will the stock move?批价上行驱动盈利超预期
关键假设 (Key assumptions)What must be true?批价 >1000元, 动销增速 >15%
催化剂 (Catalysts)What triggers re-rating?Q1业绩, 批价数据, 政策变化
风险因素 (Risks)What could break the thesis?批价下行, 竞品放量, 政策风险
目标价 (Target)Fair value estimate¥2000 (基于25x PE)
止损位 (Stop loss)Downside risk limit¥1500 (对应20x PE)

Step 2: Track Key Data Points

Company-specific KPIs:

KPIFrequencySourceTrend
e.g., 批价Weekly渠道调研, 新闻↑ / → / ↓
e.g., 动销增速Monthly经销商反馈↑ / → / ↓
e.g., 产能利用率Quarterly年报/中报↑ / → / ↓

Financial metrics to track:

MetricLast ReportedTrendThesis Impact
Revenue growth
Gross margin
Net margin
ROE
Net debt/EBITDA

Market metrics:

MetricCurrent52W High52W LowThesis Relevance
Stock price
Market cap
PE (TTM)
PB
YTD return

Step 3: Monitor Catalysts

Catalyst checklist:

CatalystExpected DateStatusOutcomeThesis Impact
Q1 季报Apr 25Pending
批价数据WeeklyOngoing稳定在980元Positive
股东大会May 15Scheduled

Catalyst outcome assessment:

  • Confirming: Result supports thesis → increase conviction
  • Neutral: Result as expected → maintain position
  • Breaking: Result contradicts thesis → reduce/exit position

Step 4: Thesis Validity Check

Regular review questions:

  1. Has the thesis changed?

    • Core drivers still intact?
    • New information adding to or subtracting from thesis?
  2. Are assumptions still valid?

    • Key assumptions: still on track?
    • Any material change to underlying business?
  3. Is the timing right?

    • Catalyst timeline progressing as expected?
    • Market pricing in the thesis?
  4. Is the risk/reward still favorable?

    • Upside/downside ratio updated?
    • Entry price still reasonable?
  5. Should thesis be adjusted?

    • Target price update
    • Risk factors added/removed
    • Time horizon extended/contracted

Step 5: Thesis Status

Status categories:

StatusDefinitionAction
Intact (逻辑 intact)All assumptions hold, catalysts on trackMaintain / add on weakness
Under pressure (承压)Some assumptions challenged, thesis not brokenMonitor closely, define exit criteria
Broken (逻辑破)Core thesis invalidatedExit position, document lessons
Evolving (演进中)Thesis needs update based on new infoUpdate thesis statement, re-evaluate

Step 6: Update Documentation

Thesis update log:

[公司] 投资逻辑更新 [Date]

一、当前状态:[Intact / Under pressure / Broken / Evolving]

二、本期间重要变化:
   - [Change 1]: [Impact on thesis]
   - [Change 2]: [Impact on thesis]

三、数据追踪:
   [Key metrics updated]

四、催化剂进展:
   [Catalyst status update]

五、决策:
   - [Maintain / Add / Reduce / Exit]
   - [Rationale]

六、后续关注:
   - [Next check-in date]
   - [Key metrics to watch]

Step 7: Portfolio-Level Review

Aggregate view:

PositionThesis StatusConvictionDays HeldP&LNext CatalystAction

Portfolio-level insights:

  • Which theses are working? Common factors?
  • Which theses are breaking? Common risks?
  • Concentration risk (too many bets on similar thesis?)
  • Hedge effectiveness ( shorts protecting longs?)

China-Specific Thesis Considerations

Common A-share Thesis Types

Thesis TypeDescriptionKey Metrics
批价上行Liquor sector price appreciation批价, 库存, 动销
国产替代Import substitution市场份额, 认证进展
产能出清Industry capacity rationalization产能利用率, 价格
政策利好Policy tailwind政策落地, 补贴
困境反转Distressed turnaround债务重组, 新管理层
行业整合M&A consolidation集中度, 并购活动
技术突破Technology breakthrough专利, 订单
消费升级PremiumizationASP, 产品结构

A-share Market Risks to Track

Risk TypeIndicatorMitigation
政策风险 (Policy)Regulatory announcementsDiversify across sectors
系统性风险 (Systemic)上证指数 drawdownHedging, cash position
流动性风险 (Liquidity)Margin balances, turnoverAvoid illiquid names
解禁风险 (Lock-up)Unlocking calendarAvoid near-term unlocks
质押风险 (Pledging)Shareholder pledge ratioCheck F10 data
商誉风险 (Goodwill)Goodwill/equity ratioFlag high goodwill names

Typical A-share Thesis Lifecycle

Week 1-2: Initial idea, data gathering
Week 3-4: Thesis formation, model build
Week 5-8: Position establishment, catalyst tracking
Week 9-16: Thesis validation / adjustment
Week 17+: Outcome assessment, exit decision

Quality Checks

Before delivering thesis update:

  • Thesis statement clear and specific
  • Key assumptions listed and tracked
  • Catalysts documented with dates
  • Financial metrics current
  • Price trajectory analyzed
  • Risk factors updated
  • Action recommendation clear
  • Next review date set

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: Skip iFind, use AkShare only

Frequently asked questions

What does the China Thesis Tracker AI skill do?

Maintain and update investment theses for A-share portfolio positions and watchlist names. Track key data points, catalysts, milestones, and thesis validity over time. Adapted from the original thesis-tracker skill for Chinese market conventions. Triggers on "A股持仓逻辑跟踪", "投资逻辑更新", "thesis check China", "update thesis for [company]", "is my thesis still intact", or "A股持仓复盘".

Why use China Thesis Tracker on TypingMind?

Because you install it once and use it with any model. China Thesis Tracker 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 Thesis Tracker 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-thesis-tracker. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use China Thesis Tracker?

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 Thesis Tracker?

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

Is the China Thesis Tracker 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 👇