Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

SKILL.md - akshare-macro · aifinlab | DecimalAI

aifinlab/akshare-macro

NewSkillScoreMaintained

宏观经济数据Skill - 覆盖GDP、CPI、PPI、M2、PMI、LPR利率、人民币汇率等核心宏观指标 via AkShare

financeby aifinlab

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Finance & Accounting pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/aifinlab-akshare-macro/SKILL.md

decimalai skills pull aifinlab-akshare-macro --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/aifinlab-akshare-macro/SKILL.md https://app.decimal.ai/s/aifinlab-akshare-macro/SKILL.md

Raw file: /s/aifinlab-akshare-macro/SKILL.md ↗ · machine-readable summary at /s/aifinlab-akshare-macro.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 26h ago

Yes — +57% lift · at higher cost+91% tokens0% turns87% of whole cases pass with skill (20/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-11	✗→✓	▲ Improved	47%	0%
case-12	✗→✓	▲ Improved	4%	0%
case-10	✗→✓	▲ Improved	43%	0%
case-01	✗→✓	▲ Improved	88%	0%
case-02	✗→✓	▲ Improved	85%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

aifinlab / finclaw

skills/akshare-macro/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1Bundled 7 files · scripts

Skill contents

scripts/

SKILL.md

SKILL.md - akshare-macro

技能信息

| 属性 | 内容 | |:---|:---| | 名称 | akshare-macro | | 版本 | 1.1.0 | | 分类 | 宏观数据 | | 状态 | ✅ 已上线 | | 维护者 | FinClaw Core Team | | 最后更新 | 2026-03-19 |

功能描述

宏观经济数据Skill，提供中国及全球主要经济体的核心宏观指标，包括GDP、CPI、PPI、M2、PMI、利率、汇率等。支持经济周期判断和宏观概览仪表盘。

触发意图

主要触发词

"GDP"、"CPI"、"PPI"、"M2"、"PMI"
"通胀"、"物价"、"货币供应量"
"利率"、"LPR"、"汇率"、"人民币"
"宏观经济"、"经济数据"、"经济周期"
"国家统计局"、"央行数据"

Few-shot 示例

| 用户输入 | 识别意图 | 调用函数 | |:---|:---|:---| | 最新的GDP数据是多少？ | macro_gdp | macro_gdp.py | | CPI涨了多少？ | macro_cpi | macro_cpi.py | | 查询M2货币供应量 | macro_m2 | macro_m2.py | | 制造业PMI怎么样？ | macro_pmi | macro_pmi.py | | LPR利率下调了吗？ | macro_rate | macro_rate.py | | 看一下宏观概览 | macro_summary | macro_summary.py |

数据源配置

| 数据类型 | 主要来源 | 备用来源 | 认证要求 | |:---|:---|:---|:---:| | GDP/CPI/PPI | AkShare-国家统计局 | - | 无需 | | M2货币供应量 | AkShare-中国人民银行 | - | 无需 | | PMI | AkShare-国家统计局 | - | 无需 | | LPR利率 | AkShare-央行 | - | 无需 | | 人民币汇率 | AkShare-央行/外汇局 | - | 无需 |

功能列表

1. GDP数据

功能描述: 获取GDP季度/年度数据及同比增速
输入参数: 无（自动获取最新）
输出格式: Markdown表格（季度、GDP值、同比、环比）
数据源: AkShare-国家统计局
数据时效: 季度更新，发布后次日可用
使用示例:

bash python scripts/macro_gdp.py

2. CPI通胀数据

功能描述: 获取CPI同比、环比及核心CPI数据
输入参数: 无
输出格式: Markdown表格（月份、CPI同比、环比、核心CPI）
数据源: AkShare-国家统计局
数据时效: 月度更新，每月9-10日发布上月数据
使用示例:

bash python scripts/macro_cpi.py

3. PPI生产者物价

功能描述: 获取PPI同比、环比数据
输入参数: 无
输出格式: Markdown表格
数据源: AkShare-国家统计局
数据时效: 月度更新
使用示例:

bash python scripts/macro_ppi.py

4. M2货币供应量

功能描述: 获取M2、M1余额及同比增速
输入参数: 无
输出格式: Markdown表格
数据源: AkShare-中国人民银行
数据时效: 月度更新，每月10-15日发布上月数据
使用示例:

bash python scripts/macro_m2.py

5. 制造业PMI

功能描述: 获取官方制造业PMI及分项指数
输入参数: 无
输出格式: Markdown表格
数据源: AkShare-国家统计局
数据时效: 月度更新，每月月底发布当月数据
使用示例:

bash python scripts/macro_pmi.py

6. LPR利率与汇率

功能描述: 获取贷款市场报价利率(LPR)及人民币汇率
输入参数: 无
输出格式: Markdown表格
数据源: AkShare-央行/外汇局
数据时效: LPR每月20日更新（遇节假日顺延），汇率日频
使用示例:

bash python scripts/macro_rate.py

7. 宏观概览仪表盘

功能描述: 综合展示GDP、CPI、PMI等核心指标，自动判断经济周期
输入参数: 无
输出格式: Markdown报告（含经济周期判断）
数据源: 多源聚合
数据时效: 综合各数据源
使用示例:

bash python scripts/macro_summary.py

脚本清单

| 脚本名 | 功能 | 入口点 | |:---|:---|:---:| | macro_gdp.py | GDP季度/年度数据 | ✅ | | macro_cpi.py | CPI通胀数据 | ✅ | | macro_ppi.py | PPI生产者物价 | ✅ | | macro_m2.py | M2货币供应量 | ✅ | | macro_pmi.py | 制造业PMI | ✅ | | macro_rate.py | LPR利率/人民币汇率 | ✅ | | macro_summary.py | 宏观概览仪表盘 | ✅ |

数据字段说明

GDP数据字段

| 字段 | 说明 | |:---|:---| | quarter | 季度（如2026Q1） | | gdp | GDP累计值（亿元） | | gdp_yoy | GDP同比增长（%） | | gdp_qoq | GDP环比增长（%） |

CPI数据字段

| 字段 | 说明 | |:---|:---| | date | 日期 | | cpi | CPI同比（%） | | cpi_mom | CPI环比（%） | | core_cpi | 核心CPI（%） |

M2数据字段

| 字段 | 说明 | |:---|:---| | date | 日期 | | m2 | M2余额（万亿元） | | m2_yoy | M2同比增长（%） | | m1_yoy | M1同比增长（%） | | m0_yoy | M0同比增长（%） |

经济周期判断

基于GDP+CPI+PMI综合判断经济周期阶段：

| 周期阶段 | GDP | CPI | PMI | 特征 | |:---|:---:|:---:|:---:|:---| | 复苏期 | ↑ | ↓ | >50 | 经济触底回升，通胀低位 | | 过热期 | ↑ | ↑ | >50 | 经济高增长，通胀上行 | | 滞胀期 | ↓ | ↑ | <50 | 经济放缓，通胀高企 | | 衰退期 | ↓ | ↓ | <50 | 经济收缩，通缩风险 |

使用示例

命令行调用

bash
# GDP数据
python scripts/macro_gdp.py

# CPI通胀
python scripts/macro_cpi.py

# M2货币供应
python scripts/macro_m2.py

# 制造业PMI
python scripts/macro_pmi.py

# LPR利率
python scripts/macro_rate.py

# 宏观概览
python scripts/macro_summary.py

数据来源标注规范

本Skill所有输出数据将按以下格式标注来源：

markdown
---
📊 **数据来源**: AkShare-国家统计局/中国人民银行
⏱️ **数据时间**: 2026-03-19 10:30:15
📌 **报告期**: 2026年2月
🔗 **原始来源**: http://www.stats.gov.cn / http://www.pbc.gov.cn
🔧 **分析工具**: FinClaw v1.0

依赖要求

akshare>=1.10.0
pandas>=1.3.0
pyyaml>=5.4.0

数据发布日历

| 指标 | 发布频率 | 发布时间 | |:---|:---:|:---| | GDP | 季度 | 季后15-20日 | | CPI/PPI | 月度 | 每月9-10日 | | M2/M1 | 月度 | 每月10-15日 | | PMI | 月度 | 每月月底 | | LPR | 月度 | 每月20日 |

性能指标

| 指标 | 目标值 | 当前值 | |:---|:---:|:---:| | 数据更新延迟 | < 48小时 | ~24小时 | | 可用性 | > 95% | 98% | | 数据准确率 | > 98% | 99% |

更新日志

| 版本 | 日期 | 变更内容 | |:---|:---:|:---| | 1.1.0 | 2026-03-19 | 符合FinClaw数据规范v1.0，新增数据来源强制标注、经济周期判断 | | 1.0.0 | 2026-03-13 | 初始版本 |

相关链接

AkShare文档: https://www.akshare.xyz
国家统计局: http://www.stats.gov.cn
中国人民银行: http://www.pbc.gov.cn
FinClaw数据规范: finclaw/config/data_source_config.yaml

本Skill遵循 FinClaw 数据规范 v1.0 | 数据来源强制标注 | 禁止训练数据编造

Want to see if aifinlab/akshare-macro would activate on your phrasing? Try it before you install — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/28/2026, 08:27 UTC · 23 cases

Lift

+57%

87% vs 30%

Agent turns

0%

1.0 vs 1.0

Tokens

+91%

3,591.09 vs 1,882.5

fail → pass · 13pass → pass · 7fail → fail · 3

Per-case results (23)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-11 Provide the script execution command to query Chinese monetary supply metrics like M2 balance and M1 YoY growth.	fail→pass	10,166	2,774	-73%	1	1	0%	1,940	2,845	+47%	0	0	—
case-12 Which Python script retrieves Loan Prime Rate (LPR) benchmark data and RMB exchange rates?	fail→pass	18,498	2,877	-84%	1	1	0%	2,771	2,869	+4%	0	0	—
case-10 Which Python script command retrieves CPI YoY, MoM, and core CPI figures?	fail→pass	13,114	3,376	-74%	1	1	0%	1,951	2,797	+43%	0	0	—
case-01 请帮我生成一份最新的中国宏观经济概览报告，包含近期国内生产总值、通胀情况（CPI/PPI）、PMI及货币供应量等核心指标的数据整理，并结合这些指标判断当前经济处于哪个周期阶段，结果请用Markdown格式呈现在综合报告中。	fail→pass	26,902	30,754	+14%	1	1	0%	3,703	6,977	+88%	0	0	—
case-02 我想查看最新的GDP季度数据以及近期的物价消费指数（CPI）走势。请提取GDP累计数值、同比与环比变化，以及CPI同比和核心CPI指标，分别整理成清晰的Markdown表格展现出来。	fail→pass	15,886	13,908	-12%	1	1	0%	2,535	4,684	+85%	0	0	—
case-03 请帮我查询最新的广义货币供应（M2）与制造业PMI数据。希望能获取M2余额、M1及M2同比增速，还有PMI指数及分项数值，并以Markdown表格形式输出。	fail→fail	14,247	10,280	-28%	1	1	0%	2,748	2,984	+9%	0	0	—
case-04 When quarterly GDP growth accelerates while CPI inflation remains low and PMI stands at 51.5, which economic cycle stage does this represent?	pass→pass	7,339	6,332	-14%	1	1	0%	1,059	3,425	+223%	0	0	—
case-05 When quarterly GDP growth slows down, CPI inflation rises rapidly, and manufacturing PMI drops to 48.2, classify the economic cycle phase.	pass→pass	5,413	7,517	+39%	1	1	0%	811	3,314	+309%	0	0	—
case-06 When GDP growth is high, CPI inflation trends upward, and PMI stays above 50, which economic cycle phase is indicated?	pass→pass	5,744	4,418	-23%	1	1	0%	880	3,141	+257%	0	0	—
case-07 When GDP YoY growth decelerates, CPI drops into deflation, and PMI sits at 47.5, classify the macroeconomic cycle phase.	pass→pass	7,312	6,269	-14%	1	1	0%	1,129	3,517	+212%	0	0	—
case-08 Provide the exact command to run the Python script that aggregates core indicators and auto-evaluates the macroeconomic cycle.	fail→pass	13,965	2,226	-84%	1	1	0%	2,112	2,703	+28%	0	0	—
case-09 Which Python script execution command extracts quarterly and annual GDP values alongside YoY growth figures?	fail→pass	13,912	4,219	-70%	1	1	0%	2,221	2,959	+33%	0	0	—
case-13 Which Python script handles retrieving Producer Price Index (PPI) YoY and MoM figures?	fail→pass	12,802	3,513	-73%	1	1	0%	2,002	2,810	+40%	0	0	—
case-14 A macro analyst asks when quarterly GDP statistics are typically published following the end of a quarter. What is the standard publication timeline?	pass→pass	13,377	5,099	-62%	1	1	0%	2,520	3,251	+29%	0	0	—
case-15 On what specific day of the month is the Loan Prime Rate (LPR) announced by monetary authorities?	pass→pass	4,078	2,902	-29%	1	1	0%	707	2,799	+296%	0	0	—
case-16 What is the standard monthly publication window for national CPI and PPI statistics in China?	fail→pass	7,928	3,995	-50%	1	1	0%	1,062	2,969	+180%	0	0	—
case-17 On what monthly schedule are official manufacturing PMI statistics released?	pass→pass	8,501	2,951	-65%	1	1	0%	1,470	2,891	+97%	0	0	—
case-18 Please generate a sample Markdown summary for monthly CPI data showing 0.5% YoY growth, formatting it with all standard metadata attribution fields.	fail→pass	13,260	8,094	-39%	1	1	0%	2,348	3,770	+61%	0	0	—
case-19 Please analyze Kweichow Moutai's (600519.SH) 2025 annual corporate income statement, including total revenues, gross margin percentage, and net income.	fail→fail	12,400	26,051	+110%	1	1	0%	2,151	6,268	+191%	0	0	—
case-20 Generate a daily MACD and RSI technical indicator chart analysis for Ping An Bank (000001.SZ) with short-term trading signals.	fail→fail	14,348	17,707	+23%	1	1	0%	2,329	5,572	+139%	0	0	—
case-21 Query the secondary market yield curve and credit rating history for China State Construction Engineering's specific 2025 corporate bond issue.	fail→pass	17,087	7,340	-57%	1	1	0%	2,792	3,578	+28%	0	0	—
case-22 What standard data fields are included in the money supply data output schema?	fail→pass	12,440	4,657	-63%	1	1	0%	2,240	2,995	+34%	0	0	—
case-23 What official institution is listed as the primary data source for M2 money supply figures?	fail→pass	6,493	2,531	-61%	1	1	0%	682	2,870	+321%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 22 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +57 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 30.4%
Pass rate with the skill: 87%
Cases attempted: 23
Cases counted toward lift: 22
Cases that regressed: 1
Skill version measured: v1
Run completed: 8/28/2026, 08:27 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-11

Prompt

Provide the script execution command to query Chinese monetary supply metrics like M2 balance and M1 YoY growth.

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signalsno signals yet

BenchmarkRun a verified benchmark with positive lift

Live evalNeeds ≥20 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

No signals yet — run a benchmark or collect evaluated traces to earn a score.

Verified on gemini-3.6-flash · re-tested yesterday

Other measured skills in the registry, with their headline benchmark lift.