macro-data-brief

Macroeconomic Data Interpretation Briefing Generation Skill

Overview

This skill is used to automatically capture China's core macroeconomic data, conduct expectation comparisons, policy interpretation, and market impact analysis, and generate macro data interpretation briefings for investment professionals.

Data Acquisition Strategy

Core Data Sources

Gildata-AIData (gildata-aidata) As the primary data source, providing comprehensive macroeconomic data and investment research analysis tools:

Data Requirement	Recommended Tool	Description
Macro industry economic data	`MacroIndustryEDB`	PMI, CPI, PPI, social financing, M2, imports and exports, industrial value added, etc.
Macro analysis views	`MacroeconomicAnalysisViewpoints`	Analysis views on macro dimensions such as GDP, CPI, PMI, and policy in research reports
Macro public opinion	`MacroNewslist`	Macro public opinion, filtering economic forecasts and events by region and sentiment type
Policy meetings	`PolicyMeetingsList`	Dynamics and content of policy meetings in the domestic economic and financial field
Official speeches	`OfficialSpeechEventList`	Speeches and activity information of important domestic and international officials
Laws and regulations	`LawsRegulations`	Laws and regulations information, filtered by type and keywords
Whole-network public opinion	`NewsInfoList`	Whole-network public opinion, filtered by keywords, source, and sentiment type
Market public opinion	`MarketNewslist`	Market public opinion, filtered by market type

Data Acquisition Priority

Macro core data: Prioritize MacroIndustryEDB to query PMI, CPI, PPI, social financing, M2, etc.
Macro view interpretation: Prioritize MacroeconomicAnalysisViewpoints to obtain professional analysis views
Macro public opinion and policy: Prioritize MacroNewslist + PolicyMeetingsList
Web search as supplement: For market expectation values, latest policy details, etc., use web_search as supplement

Execution Process

Phase 1: Data Capture and Organization

Search for the latest macro data

Use gildata-aidata to query：
```
调用 gildata-aidata MacroIndustryEDB：
query: "PMI 制造业 非制造业 最新"
query: "CPI PPI 通胀 最新"
query: "社融 M2 M1 金融数据 最新"
query: "工业增加值 固定资产投资 社零 最新"
query: "进出口 贸易顺差 最新"
```
Use web_search to supplement：
- Example search keywords: "China PMI CPI PPI latest data market expectations", "China social financing M2 latest expectations"
- Prioritize obtaining data from official channels such as the National Bureau of Statistics, the People's Bank of China, and the General Administration of Customs, or from authoritative financial media
- Focus on obtaining market expectation values (consensus expectations/median)

Extract core indicators Focus on the following indicators (if released):

Indicator Category	Core Indicators
Business climate	Manufacturing PMI, non-manufacturing PMI, composite PMI
Inflation	CPI year-on-year/month-on-month, PPI year-on-year/month-on-month, core CPI
Finance	Aggregate financing increment, new RMB loans, M2 year-on-year, M1 year-on-year
Real economy	Industrial value added year-on-year, fixed asset investment year-on-year, total retail sales of consumer goods year-on-year
Foreign trade	Total imports and exports year-on-year, exports year-on-year, imports year-on-year, trade surplus
Other	Urban surveyed unemployment rate, real estate investment/sales data

Compare with market expectations
- Search for the market expectation values of each indicator (consensus forecast/median)
- Calculate the deviation between actual values and expected values (above expectations/below expectations/in line with expectations)

Phase 2: Data interpretation and analysis

Interpretation of data implications

Use gildata-aidata to query macroeconomic analysis views：
```
调用 gildata-aidata MacroeconomicAnalysisViewpoints：
query: "GDP 经济增长 最新分析"
query: "CPI 通胀 通缩 分析观点"
query: "PMI 景气度 分析观点"
query: "货币政策 财政政策 分析观点"
```
- Provide a brief interpretation of each core indicator
- Analyze the economic conditions reflected by the data (economic expansion/contraction, inflationary/deflationary pressures, etc.)
- Identify highlights and anomalies in the data (such as structural divergence, trend changes)
- Pay attention to multidimensional changes such as year-on-year, month-on-month, and two-year average growth rates
Expectation deviation analysis
- Analyze the reasons for deviations between actual data and market expectations
- Determine whether the deviation is a temporary disturbance or a trend signal
- Assess the indicative significance of the deviation for subsequent economic trends

Phase 3: Policy and market impact analysis

Policy transmission analysis

Use gildata-aidata to query policy information：
```
调用 gildata-aidata PolicyMeetingsList：
查询最新政策会议动态

调用 gildata-aidata OfficialSpeechEventList：
查询重要官员讲话及活动信息

调用 gildata-aidata LawsRegulations：
查询相关法律法规信息
```
Monetary policy dimension:
- Implications of the data for the central bank's monetary policy stance (easing/neutral/tightening)
- Judgment of the impact on specific policy tools such as RRR cuts, interest rate cuts, MLF/LPR operations, etc.
- Liquidity environment outlook (funding conditions tightness/easing, changes in the interest rate corridor)
Fiscal policy dimension:
- Implications of the data for the intensity and direction of fiscal policy (proactive/prudent/contractionary)
- Judgment of the impact on policies such as special bond issuance, the pace of fiscal expenditure, and tax and fee reductions
- Analysis of the relationship between infrastructure investment and fiscal support
Market impact assessment

Use gildata-aidata to query market sentiment：
```
调用 gildata-aidata MacroNewslist：
查询宏观舆情，按情感类型筛选

调用 gildata-aidata MarketNewslist：
查询市场舆情
```
Stock market impact:
- Overall market sentiment impact (bullish/bearish/neutral)
- Analysis of benefiting/harmed sectors (such as inflation data benefiting resource stocks, social financing data benefiting finance and real estate, etc.)
- Style preference judgment (growth/value, large-cap/small-cap)
Bond market impact:
- Judgment of interest rate bond trends (bullish/bearish)
- Expectations for changes in the shape of the yield curve (steepening/flattening)
- Analysis of the impact on credit spreads

Phase 4: Report generation

Generate a Markdown-format briefing

Use the following template structure to generate the final report:

# 宏观经济数据解读简报

> 发布日期：YYYY-MM-DD
> 数据来源：Gildata-AIData、国家统计局、人民银行、海关总署等

---

## 一、核心数据概览

| 指标 | 实际值 | 预期值 | 前值 | 偏差方向 |
|------|--------|--------|------|----------|
| 制造业PMI | | | | |
| 非制造业PMI | | | | |
| CPI同比 | | | | |
| PPI同比 | | | | |
| 社融增量（亿元） | | | | |
| M2同比 | | | | |
| M1同比 | | | | |
| 新增人民币贷款（亿元） | | | | |
| 工业增加值同比 | | | | |
| 固定资产投资同比 | | | | |
| 社零同比 | | | | |
| 出口同比 | | | | |
| 进口同比 | | | | |

---

## 二、数据解读与预期偏差分析

### 2.1 景气度指标
（PMI数据解读，结合 MacroeconomicAnalysisViewpoints 分析观点...）

### 2.2 通胀指标
（CPI、PPI数据解读，分析通胀/通缩压力...）

### 2.3 金融与信用指标
（社融、M2、M1数据解读，分析信用扩张/收缩...）

### 2.4 实体经济指标
（工业增加值、固投、社零数据解读，分析经济内生动力...）

### 2.5 外贸指标
（进出口数据解读，分析外需变化...）

---

## 三、政策影响分析

### 3.1 货币政策展望
（结合 PolicyMeetingsList 和 OfficialSpeechEventList 分析...）
- 对央行货币政策的影响分析
- 降准/降息概率评估
- 流动性环境展望

### 3.2 财政政策展望
（结合 LawsRegulations 和政策会议分析...）
- 对财政政策的影响分析
- 专项债发行节奏
- 基建投资展望

---

## 四、市场影响评估

### 4.1 股市影响
（结合 MacroNewslist 和 MarketNewslist 分析...）
- 整体影响：利好/利空/中性
- 受益板块：[板块 1]、[板块 2]
- 受损板块：[板块 1]、[板块 2]
- 风格偏好：成长/价值

### 4.2 债市影响
- 利率债：利多/利空
- 收益率曲线：陡峭化/平坦化
- 信用利差：走阔/收窄

---

## 五、核心结论与投资启示

（总结核心观点，给出投资参考建议...）

### 核心观点
1. [观点 1]
2. [观点 2]
3. [观点 3]

### 投资启示
- [启示 1]
- [启示 2]

---

*免责声明：本报告仅供参考，不构成投资建议。*

Notes

Data timeliness: Prioritize the latest released monthly/quarterly data, and indicate the period to which the data belongs (such as "March 2026 data")
Sources of expected values: If accurate market consensus expectations cannot be obtained, reference may be made to forecasts from mainstream brokerage research reports or expected ranges summarized by financial media
Objectivity of interpretation: Data interpretation should remain objective and neutral, avoid over-inference, and distinguish facts from opinions
Uncertainty Disclosure: For areas with significant uncertainty or contradictory data, risks should be clearly indicated
Missing Data Handling: If some indicators are not released on the day, they can be marked as "not released" in the table or skipped
gildata-aidata Priority: All macroeconomic data queries should prioritize the gildata-aidata service; web_search is only used as a supplement to obtain market expectation values

Output Requirements

The report uses standard Markdown format
Data tables remain clearly aligned
Core conclusions should be concise and clear, suitable for quick reading
The report length should be controlled at 1500-2500 words, focusing on core information

Example Invocation

User input: "Today's macroeconomic data interpretation"

Skill execution:

Obtain macroeconomic data: gildata-aidata MacroIndustryEDB (PMI, CPI, PPI, social financing, M2, etc.)
Obtain macroeconomic views: gildata-aidata MacroeconomicAnalysisViewpoints
Obtain policy information: gildata-aidata PolicyMeetingsList + OfficialSpeechEventList
Obtain market sentiment: gildata-aidata MacroNewslist + MarketNewslist
Supplement expectation values: web_search to query market expectations
Write report: generate a Markdown-format macroeconomic data interpretation brief according to the template
Output report: display the complete report content directly in the conversation

Skill Update Log

2026-05-11 Update：

Core data source change: Change macroeconomic data queries to prioritize the gildata-aidata service
Added tool matrix: Establish a gildata-aidata tool query mapping table for macroeconomic data briefs (MacroIndustryEDB, MacroeconomicAnalysisViewpoints, MacroNewslist, PolicyMeetingsList, OfficialSpeechEventList, etc.)
Optimized data acquisition order: Clarify that gildata-aidata is prioritized for obtaining core macroeconomic data, and web_search is only used to supplement market expectation values
Removed eastmoney-mx dependency: The original skill used East Money Miaoxiang as the data source, and it is now fully replaced with gildata-aidata

Skill Version：v2.0
Last Updated：2026-05-11
Maintainer: Dianjin Intelligent Assistant