China Break Trace

Community

jwangkun

china-break-trace

Forensic financial analysis for A-share fund holdings and portfolio companies. Adapts the original break-trace skill for fund administration context and Chinese market standards. Triggers on "基金持仓核查", "持仓异常", "forensic fund analysis China", "持仓质量分析", or "investigate [fund] holdings".

Overview

Publisher	jwangkun
Repository	`claude-for-financial-services-cn`
Skill name	`china-break-trace`
Stars	834
Forks	132
Bundled files	Instructions only
License	Apache-2.0
Links	Skill source Repository

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 Break Trace AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
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-break-trace
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/jwangkun/claude-for-financial-services-cn/tree/main/agent-plugins/china-earnings-reviewer/skills/china-break-trace

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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-break-trace .claude/skills/china-break-trace

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable China Break Trace 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 Break Trace 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 Break Trace 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-break-trace

Purpose

Conduct 基金持仓核查 — forensic analysis of fund holdings and portfolio company financials for fund administrators.

Data Sources

Tier 0 — 万得 Wind（最全面付费数据）

覆盖：A股/港美股/基金/指数/债券/宏观/研报/分析（44个工具）
MCP 服务：wind-mcp（需 WIND_API_KEY 密钥，以 ak_ 开头）
优势：全市场覆盖面最广、数据最全面、包含研报和量化分析
密钥申请：https://aifinmarket.wind.com.cn/#/home

Tier 1 — 同花顺 iFind（付费精确数据）/ AkShare MCP（Tier-2 免费备选）

python
get_financials(ticker, "income")     → Portfolio company P&L
get_financials(ticker, "balance")    → Portfolio company BS
get_financials(ticker, "cashflow")   → Portfolio company CF
get_fund_data(fund_code)              → Fund holdings

Secondary Sources

巨潮 — portfolio company filings
基金季报/年报 — fund holdings disclosure
审计报告 — audit opinions

Workflow

Step 1: Review Fund Holdings

Holdings analysis:

Security	Ticker	Sector	Allocation	Rating	Risk Flags

Concentration analysis:

Metric	Value	Limit
Top 10 holdings %	XX%	Typically <50%
Single stock max	XX%	Typically <10%
Sector concentration	XX%

Step 2: Portfolio Company Analysis

For each significant holding:

Check	Result	Notes
Revenue quality	Pass/Warn/Fail
Profit quality	Pass/Warn/Fail
Cash flow	Pass/Warn/Fail
Balance sheet	Pass/Warn/Fail
Related party	Pass/Warn/Fail
Governance	Pass/Warn/Fail

Step 3: Red Flag Identification

Red flag categories:

Category	Red Flags
财务质量	Revenue inflation, profit manipulation, cash flow divergence
关联交易	High related party %, non-arm's length
治理问题	Ownership concentration, pledge risk
合规问题	Regulatory penalties, sanctions
流动性	Low liquidity, suspension risk

Step 4: Deep Dive on Concerns

Investigation protocol:

Flag	Investigation	Resolution
应收账款异常	Review aging, allowance
存货异常	Review turnover
关联交易	Review agreements
资金占用	Review related party balances
减值波动	Review timing and amounts

Step 5: Valuation Sanity Check

Holding valuation review:

Security	Price Source	Last Price	Valuation Method	Concern?

Valuation concerns:

停牌股票 (Suspended stocks)
ST股票 (Distressed)
流动性不足 (Low liquidity)
估值异常 (Unusual multiples)

Step 6: Compliance Review

Regulatory compliance:

Check	Fund	Status
Investment scope	Per contract
Concentration limits	Per regulation
Single stock limits	Typically <10%
Sector limits	Per contract
Liquidity requirements	Liquid assets %
Derivatives use	If applicable

Step 7: Action Recommendations

Recommendations:

Priority	Action	Security	Reason
High
Medium
Low

Step 8: Report

Report format:


【持仓核查报告】[Fund Name] [Date]

一、持仓概览
   [Holdings summary]

二、风险持仓识别
   [Flagged securities]

三、深度分析
   [Detailed findings]

四、合规检查
   [Compliance status]

五、建议措施
   [Recommendations]

China-Specific Considerations

Fund Disclosure Requirements

Requirement	Content
季报/半年报/年报	Full holdings disclosure
重大事项公告	Material changes
临时公告	Ad-hoc disclosures

Common Fund Holdings Issues

Issue	Detection	Action
持仓集中	Top 10 > 50%	Review
停牌股票	Suspended positions	Valuation review
退市风险	Delisting risk	Consider exit
ST持仓	Distressed securities	Review necessity
流动性不足	Hard to exit	Assess impact

Quality Checks

Before completing:

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

wind-only: Wind only, error if unavailable

wind-fallback: Wind first, fallback to iFind → AkShare

Frequently asked questions

What does the China Break Trace AI skill do?

Why use China Break Trace on TypingMind?

Because you install it once and use it with any model. China Break Trace 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 Break Trace 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-break-trace. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use China Break Trace?

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 Break Trace?

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

Is the China Break Trace 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

Constraint Driven Development

addyosmani

CommunityPopular

Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no…

Spec Driven Development

addyosmani

CommunityPopular

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and…

Ramp

Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporation, cards, account setup, and other financial actions.

Agent Agentic Payments

ruvnet

CommunityPopular

Agent skill for agentic-payments - invoke with $agent-agentic-payments

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

china-break-trace

Purpose

Data Sources

Tier 0 — 万得 Wind（最全面付费数据）

Tier 1 — 同花顺 iFind（付费精确数据）/ AkShare MCP（Tier-2 免费备选）

Secondary Sources

Workflow

Step 1: Review Fund Holdings

Step 2: Portfolio Company Analysis

Step 3: Red Flag Identification

Step 4: Deep Dive on Concerns

Step 5: Valuation Sanity Check

Step 6: Compliance Review

Step 7: Action Recommendations

Step 8: Report

China-Specific Considerations

Fund Disclosure Requirements

Common Fund Holdings Issues

Quality Checks

Frequently asked questions

Related AI Skills

Set up your own AI workspace now