Global Macro Analysis
HKUDS/Vibe-Trading
Framework for central bank policy, exchange rate forecasting, geopolitical risk and capital flows that produces macro factor signals to guide cross-asset allocation.
查询 GDP、CPI、PPI、利率、汇率、社融等宏观经济指标,支持自然语言问句输入,返回相关宏观经济数据结果。当用户询问宏观经济数据、GDP、CPI、PPI、利率、汇率、社融、M2、PMI、工业增加值、消费、投资、进出口等宏观经济指标查询问题时,必须使用此技能。
$ npx skills add hiboys/ExploreFinance --skill hithink-macro-query -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hiboys/ExploreFinance hithink-macro-query --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/hiboys/ExploreFinance.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/hithink-macro-query .claude/skills/hithink-macro-query && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "hithink-macro-query" agent skill from https://github.com/hiboys/ExploreFinance/tree/main/.claude/skills/hithink-macro-query into .claude/skills/hithink-macro-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hithink-macro-query", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/hiboys/ExploreFinance/tree/main/.claude/skills/hithink-macro-queryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add hiboys/ExploreFinance --skill hithink-macro-query -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hiboys/ExploreFinance hithink-macro-query --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hiboys/ExploreFinance.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/hithink-macro-query .agents/skills/hithink-macro-query && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "hithink-macro-query" agent skill from https://github.com/hiboys/ExploreFinance/tree/main/.claude/skills/hithink-macro-query into .agents/skills/hithink-macro-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hithink-macro-query", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hiboys/ExploreFinance --skill hithink-macro-query -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hiboys/ExploreFinance hithink-macro-query --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hiboys/ExploreFinance.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/hithink-macro-query .cursor/skills/hithink-macro-query && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "hithink-macro-query" agent skill from https://github.com/hiboys/ExploreFinance/tree/main/.claude/skills/hithink-macro-query into .cursor/skills/hithink-macro-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hithink-macro-query", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/hiboys/ExploreFinance.git --path .claude/skills/hithink-macro-query--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add hiboys/ExploreFinance --skill hithink-macro-query -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hiboys/ExploreFinance hithink-macro-query --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hiboys/ExploreFinance.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/hithink-macro-query .gemini/skills/hithink-macro-query && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "hithink-macro-query" agent skill from https://github.com/hiboys/ExploreFinance/tree/main/.claude/skills/hithink-macro-query into .gemini/skills/hithink-macro-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hithink-macro-query", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install hiboys/ExploreFinance hithink-macro-queryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add hiboys/ExploreFinance --skill hithink-macro-query -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/hiboys/ExploreFinance.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/hithink-macro-query .github/skills/hithink-macro-query && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "hithink-macro-query" agent skill from https://github.com/hiboys/ExploreFinance/tree/main/.claude/skills/hithink-macro-query into .github/skills/hithink-macro-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hithink-macro-query", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hiboys/ExploreFinance --skill hithink-macro-query -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hiboys/ExploreFinance hithink-macro-query --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hiboys/ExploreFinance.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/hithink-macro-query .opencode/skills/hithink-macro-query && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "hithink-macro-query" agent skill from https://github.com/hiboys/ExploreFinance/tree/main/.claude/skills/hithink-macro-query into .opencode/skills/hithink-macro-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hithink-macro-query", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
hithink-macro-query查询 GDP、CPI、PPI、利率、汇率、社融等宏观经济指标,支持自然语言问句输入,返回相关宏观经济数据结果。当用户询问宏观经济数据、GDP、CPI、PPI、利率、汇率、社融、M2、PMI、工业增加值、消费、投资、进出口等宏观经济指标查询问题时,必须使用此技能。
Hithink Macro Query is an agent skill from hiboys/ExploreFinance. 查询 GDP、CPI、PPI、利率、汇率、社融等宏观经济指标,支持自然语言问句输入,返回相关宏观经济数据结果。当用户询问宏观经济数据、GDP、CPI、PPI、利率、汇率、社融、M2、PMI、工业增加值、消费、投资、进出口等宏观经济指标查询问题时,必须使用此技能。
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/cli.py`).
The repository describes itself as: 金融知识学习整理,知识来源包括行业书籍、财新周刊、前沿论文、法律法规等. The licence is MIT.
Read from SKILL.md and the folder at commit 28bc9ee. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3curlopensslFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
openapi.iwencai.comAlso links to:
iwencai.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
IWENCAI_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Hithink Macro Query loads about 1.9k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 318 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from hiboys/ExploreFinance at commit 28bc9ee, republished under its MIT licence (© hiboys). 318 words, ~1,930 tokens.
.claude/skills/hithink-macro-query/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.1.0.0(与 X-Claw-Skill-Version 保持一致)
本技能提供宏观数据查询能力,支持:
数据来源:同花顺问财(https://www.iwencai.com/unifiedwap/chat)
首次使用 - 获取 API Key 所有技能都需要 IWENCAI_API_KEY 环境变量才能使用。 如果用户尚未配置,按以下步骤引导:
步骤 1:获取 API Key 在浏览器内打开同花顺i问财SkillHub页面:https://www.iwencai.com/skillhub
步骤 2:登录
步骤 3:点击具体的Skill,打开弹窗查看详情,在安装方式-Agent用户-找到您的IWENCAI_API_KEY这一段,复制
步骤 4:配置环境变量 获取到 API Key 后,直接复制指引文字发送给AI助手,或手动设置环境变量:
macOS / Linux (bash / zsh):
export IWENCAI_API_KEY="your-api-key"Windows (PowerShell):
$env:IWENCAI_API_KEY="your-api-key"Windows (CMD):
set IWENCAI_API_KEY=your-api-key接收用户的自然语言查询请求,分析用户意图,识别宏观数据相关查询类型:
将用户问句适当改写为标准的金融查询问句,保持原意不变:
改写规则:
常用查询改写示例:
| 用户原始问句 | 改写后查询 |
|---|---|
| 今年GDP多少 | 2024年中国GDP |
| 最近CPI怎么样 | 最近一期CPI |
| LPR利率是多少 | LPR利率 |
| M2增速如何 | M2增速 |
调用问财 OpenAPI 网关获取数据,使用 scripts/cli.py CLI 或直接在 skill 逻辑中构造 HTTP 请求。所有发往网关的请求必须严格携带以下 Header:
| Header | 取值说明 |
|---|---|
Authorization | Bearer <API Key>,API Key 仅从环境变量 IWENCAI_API_KEY 读取 |
Content-Type | application/json |
X-Claw-Call-Type | normal(正常请求)或 retry(失败后的重试) |
X-Claw-Skill-Id | hithink-macro-query(与 skill name 一致) |
X-Claw-Skill-Version | 1.0.0(与本文档版本一致) |
X-Claw-Plugin-Id | none |
X-Claw-Plugin-Version | none |
X-Claw-Trace-Id | 每次请求必须新生成的 64 字符全局唯一追踪 ID(推荐 secrets.token_hex(32)) |
请求体示例:
{
"query": "改写后的查询语句",
"page": "1",
"limit": "10",
"is_cache": "1",
"expand_index": "true"
}Python 调用示例(含 Claw Headers):
import os
import json
import secrets
import urllib.request
url = "https://openapi.iwencai.com/v1/query2data"
api_key = os.environ["IWENCAI_API_KEY"]
trace_id = secrets.token_hex(32) # 64 字符唯一 ID
payload = {
"query": "2024年中国GDP",
"page": "1",
"limit": "10",
"is_cache": "1",
"expand_index": "true"
}
headers = {
"Authorization": f"Bearer {api_key}",
"Content-Type": "application/json",
"X-Claw-Call-Type": "normal",
"X-Claw-Skill-Id": "hithink-macro-query",
"X-Claw-Skill-Version": "1.0.0",
"X-Claw-Plugin-Id": "none",
"X-Claw-Plugin-Version": "none",
"X-Claw-Trace-Id": trace_id,
}
data = json.dumps(payload).encode("utf-8")
request = urllib.request.Request(url, data=data, headers=headers, method="POST")
response = urllib.request.urlopen(request, timeout=30)
result = json.loads(response.read().decode("utf-8"))
# 解析返回数据
datas = result.get("datas", []) # 当前页数据列表
code_count = result.get("code_count", 0) # 符合条件的总记录数
chunks_info = result.get("chunks_info", {}) # 查询字句信息
# 分页提示:如果 code_count > len(datas),通过增加 page 参数翻页注意: 默认返回 10 条数据,但符合条件的总数可能更多,需关注 code_count 字段并通过分页获取全部数据。
如果 datas 为空或无数据,适当放宽或简化查询条件后重新请求(最多尝试 2 次):
每次重试都算作一次改写,最终返回时需说明最终使用的查询问句。
解析返回的 datas 数组,提取相关指标:
for item in datas:
# 根据查询类型提取相应宏观经济数据字段
# 如:指标名称、数值、时间等
# 返回数据通常以表格形式呈现,包含多个字段列skill 需要自行决策当前数据是否足够回答用户问题:
组织语言回答用户问题,确保:
| 参数名 | 类型 | 必填 | 说明 |
|---|---|---|---|
| query | STRING | 是 | 用户问句 |
| page | STRING | 否 | 分页参数,默认值:1 |
| limit | STRING | 否 | 分页参数,默认值:10 |
| is_cache | STRING | 否 | 缓存参数,默认值:1 |
| expand_index | STRING | 否 | 是否展开指数,默认值:true |
| 参数名 | 类型 | 说明 |
|---|---|---|
| datas | ARRAY | 金融数据列表,对象数组,每个对象包含指标名称、数值、时间等字段 |
| code_count | INT | 符合查询条件的总记录数量(注意:可能大于当前返回的 datas 条数) |
| chunks_info | OBJECT | 用户问句查询返回的字句信息,包含查询条件的解析结果 |
响应示例:
{
"datas": [
{
"指标名称": "GDP",
"数值": "126.06万亿",
"时间": "2024年"
}
],
"code_count": 50,
"chunks_info": {
"query": "2024年中国GDP",
"parsed_conditions": ["2024年", "中国", "GDP"]
}
}重要提示:
datas 默认只返回 10 条数据(可通过 limit 参数调整)code_count 表示符合条件的总记录数,可能远大于 datas 的长度code_count > len(datas) 时,需要通过 page 参数翻页获取更多数据datas 数组中的对象字段本 skill 提供跨平台 CLI 脚本 scripts/cli.py,基于 Python 3 标准库实现,无第三方依赖。
| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
--query | STRING | 是 | 直接传入查询字符串 |
--page | STRING | 否 | 分页参数,值必须为正整数,默认值:1 |
--limit | STRING | 否 | 每页条数,值必须为正整数,默认值:10 |
--api-key | STRING | 否 | API 密钥(默认从环境变量读取) |
--call-type | STRING | 否 | 调用类型:normal(正常请求)或 retry(重试请求),默认值:normal |
--timeout | INT | 否 | 请求超时时间(秒),默认值:30 |
# 查询2024年中国GDP
python3 scripts/cli.py --query "2024年中国GDP"
# 查询最近一期CPI
python3 scripts/cli.py --query "最近一期CPI"
# 查询LPR利率
python3 scripts/cli.py --query "LPR利率"
# 翻页查询
python3 scripts/cli.py --query "GDP数据" --page 2 --limit 20
# 重试请求(放宽条件后使用 retry 标记)
python3 scripts/cli.py --query "2024年中国GDP" --call-type "retry"
# 指定超时时间(复杂查询可适当增加)
python3 scripts/cli.py --query "2024年中国GDP" --timeout 60curl -X POST "https://openapi.iwencai.com/v1/query2data" \
-H "Authorization: Bearer $IWENCAI_API_KEY" \
-H "Content-Type: application/json" \
-H "X-Claw-Call-Type: normal" \
-H "X-Claw-Skill-Id: hithink-macro-query" \
-H "X-Claw-Skill-Version: 1.0.0" \
-H "X-Claw-Plugin-Id: none" \
-H "X-Claw-Plugin-Version: none" \
-H "X-Claw-Trace-Id: $(openssl rand -hex 32)" \
-d '{
"query": "2024年中国GDP",
"page": "1",
"limit": "10",
"is_cache": "1",
"expand_index": "true"
}'Windows (PowerShell) 等价示例:
$bytes = New-Object byte[] 32; [System.Security.Cryptography.RandomNumberGenerator]::Create().GetBytes($bytes); $traceId = -join ($bytes | ForEach-Object { $_.ToString("x2") })
Invoke-RestMethod -Uri "https://openapi.iwencai.com/v1/query2data" -Method POST -Headers @{
"Authorization" = "Bearer $env:IWENCAI_API_KEY"
"Content-Type" = "application/json"
"X-Claw-Call-Type" = "normal"
"X-Claw-Skill-Id" = "hithink-macro-query"
"X-Claw-Skill-Version" = "1.0.0"
"X-Claw-Plugin-Id" = "none"
"X-Claw-Plugin-Version" = "none"
"X-Claw-Trace-Id" = $traceId
} -Body '{"query":"2024年中国GDP","page":"1","limit":"10","is_cache":"1","expand_index":"true"}'重要提示:
密钥缺失(环境变量未设置且未传 --api-key):
代理必须口头提示用户「使用前」中的完整 API Key 获取指引文案,即:
首次使用 - 获取 API Key 所有技能都需要 IWENCAI_API_KEY 环境变量才能使用。 如果用户尚未配置,按以下步骤引导:
步骤 1:获取 API Key 在浏览器内打开同花顺i问财SkillHub页面:https://www.iwencai.com/skillhub
步骤 2:登录
步骤 3:点击具体的Skill,打开弹窗查看详情,在安装方式-Agent用户-找到您的IWENCAI_API_KEY这一段,复制
步骤 4:配置环境变量 获取到 API Key 后,直接复制指引文字发送给AI助手,或手动设置环境变量:
无数据返回:引导用户访问同花顺问财(https://www.iwencai.com/unifiedwap/chat)。
最多重试 2 次逐步放宽条件(重试时 X-Claw-Call-Type 改为 retry)。
hithink-macro-query/
├── SKILL.md # Skill 配置文件
├── LICENSE.txt # 许可证文件
└── scripts/
└── cli.py # CLI 入口(单一脚本,内含 API 调用和数据处理)© hiboys, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 2 other files (scripts) in .claude/skills/hithink-macro-query of hiboys/ExploreFinance.
Open the folder on GitHubat commit 28bc9ee
Hithink Macro Query next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Hithink Macro Query this skillhiboys/ExploreFinance | 365 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Global Macro AnalysisHKUDS/Vibe-Trading | 35k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Macro Cycle and Policy AnalysisHKUDS/Vibe-Trading | 35k | — | ~2.1k | Automated safety check: Pass | MIT | |
| Kotler Macro Analyzersickn33/agentic-awesome-skills | 47k | 1 repos | ~635 | Automated safety check: Pass | MIT | |
| Support Macromohitagw15856/pm-claude-skills | 1.4k | — | ~856 | Automated safety check: Pass | MIT | |
| Macro Briefingbrycewang-stanford/Auto-Empirical-Research-Skills | 4.6k | — | ~4.8k | Automated safety check: Notes | Custom licence |
HKUDS/Vibe-Trading
Framework for central bank policy, exchange rate forecasting, geopolitical risk and capital flows that produces macro factor signals to guide cross-asset allocation.
HKUDS/Vibe-Trading
Reads GDP, inflation, PMI, rates and FX data plus central bank policy to place the economy in a cycle stage and derive major asset allocation tilts for China, the US and Europe.
sickn33/agentic-awesome-skills
Professional PESTEL/SWOT analysis agent based on Kotler's methodology for strategic market audits.
mohitagw15856/pm-claude-skills
Write reusable support macros / canned responses that sound human, not robotic.
brycewang-stanford/Auto-Empirical-Research-Skills
Macroeconomic monitor. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.
tradermonty/claude-trading-skills
Detect structural macro regime transitions (1-2 year horizon) using cross-asset ratio analysis.
hiboys/ExploreFinance
支持A股、港股、基金、ETF等金融标的公告的查询,同时公告类型包括不限于定期财务报告、分红派息、回购增持、资产重组等等。
hiboys/ExploreFinance
将 SDD-RIPER 方法论落地为严格可执行流程的技能。用于代码/架构任务中的“功能级与项目级 CodeMap 生成、全模态需求上下文打包、Spec 驱动研发、RIPER 阶段门禁推进”,适用于 Claude/Codex/其他 CLI Agent 的多轮协作开发。
hiboys/ExploreFinance
金融领域的可比公司分析工具,通过行业分析法对目标公司与可比公司整合经营指标、估值倍数和统计基准比较。目前仅支持A股上市公司分析。输入单一公司问句后,调用可比公司接口并生成主题化Excel报告。适用于快速对比目标公司与同业在经营、财务、估值维度的差异。
hiboys/ExploreFinance
ETF 资金流深度分析工作流。基于东方财富妙想数据,对宽基/行业 ETF 的净流入、主力流向、申购赎回分歧进行量化分析, 识别拥挤度风险与资金真实意图。适用于 ETF 择时、板块轮动验证、卖方研报交叉核验。
hiboys/ExploreFinance
面向公募基金的单基金综合诊断能力。适用于用户提出“这只基金怎么样”“适不适合继续持有”“风险和收益特征如何”等泛化问题时,返回结构化的Markdown诊断报告。每次仅分析一只基金,不处理多基金对比与量化建模。触发核心条件:用户问法为概括性诊断,未要求具体指标公式计算或回测建模。
hiboys/ExploreFinance
查询行业估值、财务、盈利、行情、板块排名等数据,支持自然语言问句输入,返回相关行业数据结果。当用户询问行业数据、行业估值、行业排名、行业财务、行业盈利、行业行情、板块排名等行业相关问题时,必须使用此技能。
查询 GDP、CPI、PPI、利率、汇率、社融等宏观经济指标,支持自然语言问句输入,返回相关宏观经济数据结果。当用户询问宏观经济数据、GDP、CPI、PPI、利率、汇率、社融、M2、PMI、工业增加值、消费、投资、进出口等宏观经济指标查询问题时,必须使用此技能。. Hithink Macro Query is an agent skill from hiboys/ExploreFinance.
Run `npx skills add hiboys/ExploreFinance --skill hithink-macro-query -a claude-code`. Or copy the skill folder (.claude/skills/hithink-macro-query in hiboys/ExploreFinance) into .claude/skills/hithink-macro-query in your project. Claude Code loads it when a task matches its description.
Run `npx skills add hiboys/ExploreFinance --skill hithink-macro-query -a codex`. Or copy the skill folder (.claude/skills/hithink-macro-query in hiboys/ExploreFinance) into .agents/skills/hithink-macro-query in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hiboys/ExploreFinance --skill hithink-macro-query -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hithink-macro-query, .gemini/skills/hithink-macro-query, .github/skills/hithink-macro-query and .opencode/skills/hithink-macro-query in your project.
Going by SKILL.md and its folder, Hithink Macro Query needs Python for the scripts in its folder, the command-line tools its instructions call (python3, curl and openssl) and credentials named IWENCAI_API_KEY. Our summary lists: Python 3; A credential in IWENCAI_API_KEY.
SKILL.md names 2 domains. In commands or code: openapi.iwencai.com; the agent is likely to contact it when it follows the instructions. As links in the text: iwencai.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Hithink Macro Query is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Hithink Macro Query: Global Macro Analysis (HKUDS/Vibe-Trading, 35k stars), Macro Cycle and Policy Analysis (HKUDS/Vibe-Trading, 35k stars), Kotler Macro Analyzer (sickn33/agentic-awesome-skills, 47k stars) and Support Macro (mohitagw15856/pm-claude-skills, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
hiboys (a GitHub user) maintains it in hiboys/ExploreFinance, which has 365 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on June 17, 2026.
Source: hiboys/ExploreFinance on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.