Macro Analysis logo

Macro Analysis

OrganizationPopular
HKUDS
macro-analysis

Macroeconomic cycle positioning and central-bank policy interpretation, including GDP/CPI/PMI/rates/FX analysis, with output in the form of major-asset allocation tilts.

Overview

PublisherHKUDS
RepositoryVibe-Trading
Skill namemacro-analysis
Stars
33.6K
Forks
5.5K
Bundled files
Instructions only
LicenseMIT
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 HKUDS on GitHub. Read the source before you install it.

Installation

Install the Macro Analysis 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.
  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/HKUDS/Vibe-Trading.git /tmp/Vibe-Trading
mkdir -p .claude/skills
cp -r /tmp/Vibe-Trading/agent/src/skills/macro-analysis .claude/skills/macro-analysis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Macro Analysis 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 Macro Analysis 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 Macro Analysis 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.

Macroeconomic Analysis

Overview

Interprets macroeconomic data and central-bank policy, identifies the current economic-cycle stage, and derives major-asset allocation direction. Covers the three major economies of China (PBOC), the United States (Fed), and Europe (ECB).

Core Indicator System

Growth Indicators

IndicatorFrequencyKey ThresholdData Source
GDP YoYQuarterlyChina >5% = normal, <4% = weakNational Bureau of Statistics
Manufacturing PMIMonthly>50 = expansion, <50 = contraction, 49-51 = borderlineNBS / Caixin
Industrial productionMonthly>5% = normalNational Bureau of Statistics
Retail salesMonthly>8% = strong consumptionNational Bureau of Statistics
Fixed asset investmentMonthlyFocus on infrastructure vs real-estate componentsNational Bureau of Statistics

Inflation Indicators

IndicatorFrequencyKey ThresholdInterpretation
CPI YoYMonthly>3% = inflation pressure, <0% = deflation riskStrongly affected by the pork cycle, so core CPI is more reliable
PPI YoYMonthly>0% = improving corporate profits, <0% = deflation transmissionLeads CPI by 3-6 months
Core CPIMonthly>2% = demand-driven inflationExcludes food and energy
M2 YoYMonthly>10% = monetary easingThe M2-M1 spread reflects how active liquidity is

Rates and FX

IndicatorMeaningFocus
1Y / 5Y LPRLoan prime rateRate-cut signal
DR007Interbank 7-day repo rateFunding tightness / looseness
10Y government bond yieldRisk-free rate anchor<2.5% = loose, >3.5% = tight
USD/CNYExchange rate>7.3 = high depreciation pressure
US 10Y-2Y spreadTerm spreadInversion signals recession (leads by 12-18 months)

Four-Stage Economic Cycle Model

Merrill Lynch Clock Framework

        GDP↑ + CPI↓           GDP↑ + CPI↑
        ┌─────────┐           ┌─────────┐
        │ Recovery │ ────→    │ Overheat│
        │          │           │         │
        └────┬────┘           └────┬────┘
             ↑                     │
             │                     ↓
        ┌────┴────┐           ┌────┴────┐
        │Recession│ ←────     │Stagflat │
        │         │           │         │
        └─────────┘           └─────────┘
        GDP↓ + CPI↓           GDP↓ + CPI↑

Asset Performance by Stage

StageBest AssetSecond-Best AssetWorst AssetTypical Policy
RecoveryEquities (growth / small cap)CommoditiesBondsMonetary easing + fiscal stimulus
OverheatCommodities (oil / copper)Equities (cyclical / value)BondsHiking cycle begins
StagflationCash / short-duration bondsGoldEquitiesPolicy dilemma
RecessionBonds (long duration)GoldEquities / commoditiesRate cuts + quantitative easing

China-Specific Adjustments

  • Real-estate cycle: property sales / investment is a core variable in China's economy, and the policy response during downturns determines the turning point
  • Infrastructure offset: when property is weak, infrastructure often strengthens (countercyclical adjustment), so track the pace of special-bond issuance
  • Export orientation: external demand (US PMI / Eurozone PMI) affects manufacturing conditions
  • Policy-driven market: tone-setting from Politburo meetings / the Central Economic Work Conference matters more than the data itself

Central Bank Policy Analysis Framework

Federal Reserve (Fed)

Sequence to watch: FOMC statement → dot plot → Powell speech → meeting minutes

SignalHawkish (tightening)Dovish (easing)
Employment"labor market remains tight""softening in labor market"
Inflation"inflation remains elevated""inflation moving toward target"
Forward guidance"further tightening may be appropriate""rate cuts could be appropriate"
Balance sheetFaster / continued QTSlower QT / hints of QE

Fed decision function: core PCE > 2.5% → tightening bias; unemployment > 4.5% → easing bias; when the two conflict, focus on which deviation is larger

People's Bank of China (PBOC)

Toolbox:

ToolSignal StrengthImpact
RRR cutStrongReleases long-term liquidity, bullish for equities and bonds
Rate cuts (MLF/LPR)StrongReduces financing costs, bullish for growth stocks
OMO (reverse repo)MediumShort-term liquidity adjustment
PSL / relendingMediumTargeted support (infrastructure / real estate)
Window guidanceWeak but effectiveDirects credit allocation

European Central Bank (ECB)

Core variables: HICP (harmonized CPI), Eurozone PMI, Germany-France yield spread Special feature: large divergence among member economies, creating a "one size fits all" problem

Analysis Framework

Step 1: Data Collection and Current-State Description

Collect core indicators from the latest 3 months:
- China: PMI, CPI, PPI, M2, aggregate financing, LPR
- United States: nonfarm payrolls, CPI, core PCE, ISM PMI, Fed rate
- Global: oil, copper, US dollar index (DXY), VIX

Step 2: Cycle Positioning

Decision criteria:
1. GDP trend: accelerating / decelerating / topping / bottoming
2. Inflation trend: rising / falling / topping / bottoming
3. Policy direction: easing / neutral / tightening / turning
4. Composite stage: recovery / overheat / stagflation / recession
5. Cycle position: early / mid / late

Step 3: Policy Impact Assessment

1. Recent policy events (last 30 days)
2. Interpretation of policy intent (support growth / control inflation / contain risk)
3. Transmission paths to each asset class
4. Lag estimation (6-12 months for monetary policy, 3-6 months for fiscal policy)

Step 4: Asset Allocation Tilt

Based on cycle position and policy direction:
- Overweight / neutral / underweight: China A-shares / Hong Kong stocks / US equities / bonds / commodities / cash
- Style tilt: growth vs value, large cap vs small cap
- Sector preference: cyclical / defensive / growth

Output Format

markdown
## Macro Environment Assessment

### Snapshot of Core Data
| Indicator | Latest | Previous | Trend |
|------|--------|------|------|
| China PMI | 50.2 | 49.8 ||
| ... | ... | ... | ... |

### Economic Cycle Positioning
- **Current stage**: early recovery / mid-overheat / late stagflation / mid-recession
- **Core logic**: explain the basis in 2-3 sentences
- **Estimated remaining duration**: expected to last another X months

### Central Bank Policy Analysis
- **PBOC**: easing bias, likely another 25bp RRR cut in Q2
- **Fed**: hiking pause, watch the June dot plot
- **Policy conflicts**: whether there are conflicting policy signals worth attention

### Major Asset Allocation Tilt
| Asset | Recommendation | Logic |
|------|------|------|
| China A-shares | Overweight | Policy bottom confirmed + loose liquidity |
| Bonds | Neutral | Limited room for rates to fall further |
| Commodities | Underweight | Weak demand |
| Cash | Underweight | High opportunity cost |

### Risk Warnings
- Risk 1: ...
- Risk 2: ...

Notes

  1. Data timeliness: macro data is released with lags; PMI is the timeliest (start of month), GDP is the most delayed (quarter-end + 15 days)
  2. Do not predict precisely: macro analysis provides directional judgment, not exact levels or timing
  3. Focus on marginal change: direction and speed of change matter more than absolute levels
  4. China-specific feature: policy intent > economic data, and major meeting tone-setting has the highest priority
  5. Global linkage: the US dollar / US Treasury yields are global pricing anchors, and Fed policy affects global liquidity
  6. Avoid hindsight bias: analyze based on the information available at the time, not by reverse-engineering from future data

Frequently asked questions

What does the Macro Analysis AI skill do?

Macroeconomic cycle positioning and central-bank policy interpretation, including GDP/CPI/PMI/rates/FX analysis, with output in the form of major-asset allocation tilts.

Why use Macro Analysis on TypingMind?

Because you install it once and use it with any model. Macro Analysis 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 Macro Analysis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/macro-analysis. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Macro Analysis?

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 Macro Analysis?

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

Is the Macro Analysis AI skill free?

Yes. It is published on GitHub by HKUDS under the MIT 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 👇