China Initiating Coverage logo

China Initiating Coverage

Community
jwangkun
china-initiating-coverage

Institutional-quality equity research initiation reports for A-share companies. Covers company analysis, financial modeling, valuation, chart preparation, and final report assembly. Adapted from the original initiating-coverage skill for Chinese market conventions, CAS accounting, and AkShare data sources. Triggers on "A股首次覆盖", "首次评级", "initiate coverage China", "initiate on [company]", "A股研究报告", or "start research on [company]".

Overview

Publisherjwangkun
Repositoryclaude-for-financial-services-cn
Skill namechina-initiating-coverage
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 Initiating Coverage 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-initiating-coverage
  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-initiating-coverage .claude/skills/china-initiating-coverage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable China Initiating Coverage 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 Initiating Coverage 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 Initiating Coverage 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-initiating-coverage

Purpose

Create institutional-quality A股首次覆盖研究报告, following Chinese sell-side research standards.

Data Sources

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

python
get_stock_info(ticker)                    → Company profile
get_quote(ticker)                        → Current valuation
get_historical_data(ticker)              → Trading history
get_financials(ticker, "income")         → Historical P&L
get_financials(ticker, "balance")        → Historical BS
get_financials(ticker, "cashflow")        → Historical CF
get_industry_stocks(industry="...")       → Peer companies

Secondary Sources

  • 巨潮资讯 — official filings (annual reports, prospectus)
  • 上交所 / 深交所 — listing documents, announcements
  • 公司官网 — investor relations, presentations
  • 慧博 / Wind / Choice — consensus estimates
  • 券商研报 — existing analyst coverage (if any)
  • 行业协会 — industry data

Workflow

Task 1: Company Research

Company overview:

  • Business description (主营业务)
  • History and development (发展历程)
  • Ownership structure (股权结构)
  • Management team (管理层)
  • Shareholder composition (股东构成)

Business segments:

SegmentRevenue %MarginGrowth Driver

Key questions to answer:

  1. What does the company do? How does it make money?
  2. What is its competitive advantage? (护城河)
  3. What are the key growth drivers?
  4. What are the main risks?
  5. Who are the comparable companies?

Task 2: Financial Modeling

Build a financial model (refer to china-3-statement-model skill):

Historical analysis (3-5 years):

Metric20202021202220232024E2025E2026E
Revenue (亿)
YoY Growth
Gross Margin
Operating Margin
Net Margin
ROE
Net Debt/EBITDA

Key modeling considerations (see china-3-statement-model):

  • CAS accounting standards
  • 25% tax rate (or 15% for 高新技术企业)
  • 千元 vs 元 unit normalization
  • 增值税 treatment
  • 商誉 flagging
  • R&D expense treatment

Task 3: Valuation Analysis

Build comprehensive valuation:

  1. DCF (refer to china-dcf skill)

    • WACC with CGB risk-free rate
    • 6-8% China ERP
    • 25% tax rate
    • CNY denominated
  2. Comparable companies (refer to china-comps skill)

    • Peer set from same 东方财富 industry
    • PE, PB, PS, EV/EBITDA multiples
    • Regression analysis if >5 peers
  3. Precedent transactions (if available)

    • China M&A comparable multiples
    • Control premium analysis
  4. Sum-of-the-parts (if multi-segment)

    • Segment-level DCF or multiples
    • Conglomerate discount assessment

Valuation summary:

MethodValue (元/股)WeightRationale
DCF
PE comps
PB comps
EV/EBITDA comps
SOTP
Implied target

Task 4: Chart Preparation

Required charts:

  1. Revenue & earnings history

    • 5-year historical + 3-year projected
    • Bar chart: Revenue
    • Overlay: Net income, margins
  2. Valuation multiple history

    • PE band (5-year)
    • PB band (5-year)
    • Current vs historical average
  3. Peer comparison

    • Scatter: Growth vs Multiple
    • Bar: Key metrics vs peers
  4. Share price chart

    • 2-year price history
    • Key events annotated

Chart standards:

  • Dark theme or light theme (consistent with firm template)
  • Chinese labels where appropriate
  • Source: AkShare historical data
  • Include A-share specific markers (涨跌停, 财报日期)

Task 5: Report Assembly

Standard A-share initiation report format:

【XX证券】[公司名称]([代码])首次覆盖报告:[评级]

投资要点:
  - [3-5 bullet investment highlights]
  - 目标价:¥XX.XX (X% upside/downside)
  - 评级:买入/增持/中性/减持/卖出

一、投资逻辑
   [Core thesis, 2-3 paragraphs]

二、公司分析
   - 业务概述
   - 竞争优势
   - 管理团队
   - 股权结构

三、行业分析
   - 市场规模与增速
   - 竞争格局
   - 政策环境
   - 发展趋势

四、财务分析
   - 历史财务表现
   - 盈利驱动因素
   - 财务健康度
   - 关键假设

五、估值分析
   - 估值方法概述
   - DCF analysis
   - Comparable companies
   - Valuation summary
   - Target price derivation

六、风险提示
   - [Company-specific risks]
   - [Industry risks]
   - [Market risks]
   - [Policy risks]

附录:
   - 财务报表预测
   - 详细估值模型
   - 公司资料

Report length:

  • Summary: 1 page
  • Full report: 15-30 pages
  • Financial model appendix: 10-15 pages

China-Specific Considerations

Rating Conventions (A-share)

RatingChinese EquivalentImplied Return
Buy买入>15% upside
Overweight / Accumulate增持5-15% upside
Neutral / Hold中性-5% to +5%
Underweight / Reduce减持-5% to -15%
Sell卖出<-15% downside

Note: Some firms use 5-point scale (买入/增持/中性/减持/卖出), others use 3-point (买入/增持/减持).

Coverage Initiation Practices

Pre-initiation checklist:

  • Company filings reviewed (年报, 招股说明书)
  • Management meeting completed (if possible)
  • Industry research thorough
  • Peer comparison complete
  • Financial model built and validated
  • Valuation analysis complete
  • Conflicts of interest disclosed

Common initation triggers:

  • New IPO (新股)
  • IPO quiet period expiry (typically 30-180 days)
  • Market cap reaches coverage threshold
  • New sector coverage mandate
  • Material corporate action (M&A, restructuring)

China-Specific Risks to Highlight

Risk CategoryExamples
政策风险Regulatory changes, industry policy shifts
市场风险A-share volatility, retail sentiment
流动性风险Low float, low turnover
公司治理Related party transactions, pledge risk
行业风险Overcapacity, demand cyclicality
汇率风险For exporters/importers
商誉减值Goodwill impairment risk
质押风险Share pledge unwinding

Regulatory Compliance

Chinese regulatory requirements for research:

  • 投资者适当性管理 (suitability)
  • 利益冲突披露 (conflict of interest)
  • 研究报告留痕 (research record retention)
  • 静默期规定 (quiet period before IPOs)
  • 预测免责声明 (disclaimer on estimates)

Quality Checks

Before delivering:

  • All financial data sourced from AkShare / 巨潮
  • Financial model balanced and validated
  • Valuation analysis comprehensive
  • Peer comparison adequate (>3 peers)
  • Rating and target price justified
  • Risk factors comprehensive
  • Report follows standard format
  • All citations complete
  • Compliance disclosures included

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 Initiating Coverage AI skill do?

Institutional-quality equity research initiation reports for A-share companies. Covers company analysis, financial modeling, valuation, chart preparation, and final report assembly. Adapted from the original initiating-coverage skill for Chinese market conventions, CAS accounting, and AkShare data sources. Triggers on "A股首次覆盖", "首次评级", "initiate coverage China", "initiate on [company]", "A股研究报告", or "start research on [company]".

Why use China Initiating Coverage on TypingMind?

Because you install it once and use it with any model. China Initiating Coverage 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 Initiating Coverage 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-initiating-coverage. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use China Initiating Coverage?

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 Initiating Coverage?

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

Is the China Initiating Coverage 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 👇