China Model Update logo

China Model Update

Community
jwangkun
china-model-update

Update A-share financial models with new quarterly data, management guidance, or macro changes. Reflects actuals, rolls estimates forward, flags material changes, and updates valuation. Adapted from the original model-update skill for Chinese market conventions and AkShare data. Triggers on "A股模型更新", "模型更新", "plug earnings into model", "update model for [company]", "刷新预测", or "更新财务模型".

Overview

Publisherjwangkun
Repositoryclaude-for-financial-services-cn
Skill namechina-model-update
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 Model Update 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-model-update
  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-model-update .claude/skills/china-model-update
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable China Model Update 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 Model Update 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 Model Update 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-model-update

Purpose

Update existing A股财务模型 with new data, ensuring all cells are traceable to sources and all changes are documented.

Data Sources

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

python
get_financials(ticker, "income", "quarterly")   → Q[X] actual results
get_financials(ticker, "balance", "quarterly")  → BS update
get_financials(ticker, "cashflow", "quarterly") → CF update
get_financials(ticker, "income", "annual")      → Full year update
get_quote(ticker)                               → Current market data
get_stock_info(ticker)                          → Any company changes

Secondary Sources

  • 巨潮资讯 — official filings for exact figures
  • 业绩说明会 transcript — management commentary
  • 管理层指引 — guidance from earnings calls
  • Wind / Choice / 同花顺 — consensus updates

Workflow

Step 1: Identify What Changed

Change triggers:

  • Quarterly earnings release (季报/年报)
  • Management guidance update (管理层指引调整)
  • Macro assumption change (rate, tax, policy)
  • Model error or refinement
  • M&A or restructuring event

Change log template:

DateChange TypeItemOld ValueNew ValueReason
Earnings updateRevenue FY25EXX亿XX亿Q1 actuals beat
GuidanceTax rate25%25%No change
MacroCapEx %5%6%New plant announced

Step 2: Update Historical Actuals

Quarterly actuals:

[Company] Q[X] 20XX Actuals (from AkShare / 巨潮):
- 营业收入: XXX亿 (YoY: +XX%)
- 毛利率: XX% (vs prior: XX%)
- 归母净利润: XXX亿 (YoY: +XX%)
- EPS: X.XX元
- 经营现金流: XXX亿

Update sequence:

  1. Drop Q[X] actuals into historical columns
  2. Verify sum checks (quarterly sum = annual)
  3. Update LTM (Last Twelve Months) calculations
  4. Check annual-to-quarter relationships

Step 3: Roll Forward Estimates

Revenue projections:

  • Update growth rates based on Q[X] performance
  • Consider:
    • Order backlog changes
    • New product ramp
    • Market share gains/losses
    • Capacity expansion

Margin projections:

  • Update gross margin based on actual trend
  • Update opex ratios based on actual leverage
  • Flag structural changes (input costs, pricing power)

Balance sheet projections:

  • Update working capital assumptions
  • Update debt schedule if refinancing occurred
  • Update CapEx plans

Step 4: Update Valuation

Market data refresh:

python
get_quote(ticker)  # Current price, PE, PB

Valuation metrics to update:

  • Current stock price and change
  • Trading multiple (PE, PB, EV/Sales, EV/EBITDA)
  • 52-week range position
  • Relative to sector median
  • Implied growth vs historical

DCF updates (if applicable):

  • Roll forward projections by one year
  • Update market data inputs (beta, risk-free rate, shares)
  • Update terminal growth if outlook changed

Step 5: Flag Material Changes

Change significance assessment:

ChangeThresholdAction
Revenue estimate±5%Update model, note driver
Net income estimate±10%Update model, revise target price
Margin estimate±100 bpsUpdate model, assess sustainability
CapEx estimate±20%Update model, check FCF impact
Multiple assumption±1xSensitivity check, document rationale

Red flags to highlight:

  • Revenue growth deceleration >500 bps
  • Margin compression >300 bps
  • Working capital deterioration
  • Debt increase >20% vs prior forecast
  • Management guidance lower than consensus

Step 6: Document Changes

Model update memo:

[公司名称]([代码])模型更新 [Date]

一、更新内容
   [Bullet list of changes made]

二、关键变动
   Revenue FY25E: [Old] → [New] ([Change]%)
   Net Income FY25E: [Old] → [New] ([Change]%)
   Driver: [Explanation]

三、估值影响
   新目标价: ¥XX.XX (之前 ¥XX.XX)
   调整幅度: +X% / -X%
   调整逻辑: [Brief rationale]

四、后续关注
   - [Next catalyst]
   - [Key metric to monitor]
   - [Risk factor]

Step 7: QC Checklist

Before finalizing:

  • All Q[X] actuals sourced from 巨潮 PDF or AkShare
  • Historical data matches reported figures exactly
  • All formulas intact (no broken references)
  • LTM calculations updated
  • Forward estimates reflect new information
  • Valuation inputs refreshed (price, shares, multiples)
  • Target price recalculated
  • Change log complete
  • Cell comments added for new inputs
  • Model balances correctly

China-Specific Update Considerations

Earnings Season Timing

ReportDeadlineTypical Release Window
Q1季报Apr 30Apr 1-30
中报Aug 31Aug 1-31
Q3季报Oct 31Oct 1-31
年报Apr 30Jan-Apr

Model update priority:

  • Annual report: Complete overhaul of historicals
  • Semi-annual: Major update, adjust full-year estimates
  • Quarterly: Incremental update, verify full-year trajectory

业绩预告 Integration

If company issued 业绩预告:

  • Use as directional signal before formal report
  • Adjust estimates if variance >20% from prior
  • Flag for detailed update when formal report arrives

Consensus Management

  • Update consensus assumptions based on new information
  • If company guidance differs from consensus, flag divergence
  • Note if management commentary suggests estimate revision

Regulatory Changes

Monitor for:

  • Tax rate changes (高新技术企业 reclassification)
  • Accounting standard updates
  • Industry-specific regulation impacts on assumptions
  • Dividend policy changes (影响 DCF terminal value)

Quality Checks

Before delivering:

  • All new actuals traceable to source
  • Formulas verified (no hardcodes in calculations)
  • Estimates logically consistent with new data
  • Valuation update reflects current market conditions
  • Changes documented in update memo
  • Model passes basic QC (balance checks, sum checks)

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 Model Update AI skill do?

Update A-share financial models with new quarterly data, management guidance, or macro changes. Reflects actuals, rolls estimates forward, flags material changes, and updates valuation. Adapted from the original model-update skill for Chinese market conventions and AkShare data. Triggers on "A股模型更新", "模型更新", "plug earnings into model", "update model for [company]", "刷新预测", or "更新财务模型".

Why use China Model Update on TypingMind?

Because you install it once and use it with any model. China Model Update 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 Model Update 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-model-update. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use China Model Update?

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 Model Update?

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

Is the China Model Update 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 👇