shaoxing-xie/openclaw-data-china-stock

china-macro-analyst

宏观政策解读师,基于中国宏观数据工?

First seen Jun 15, 2026

Installation

$ npx skills add shaoxing-xie/openclaw-data-china-stock --skill china-macro-analyst

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from shaoxing-xie/openclaw-data-china-stock.

npx skills add shaoxing-xie/openclaw-data-china-stock

Browse all from shaoxing-xie/openclaw-data-china-stock

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 52
License LICENSE
Default branch main
Open issues 0
Status Active

Skill metadata

Parsed from SKILL.md frontmatter.

Version1.0.0

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,030 B
  • docs README.md 539 B
  • docs SUMMARY.md 111 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 2 installs

SKILL.md

China Macro Analyst

目标

基于插件内宏观采集工具,对宏观数据进行机构化、可追溯、可复核的结构化解读。

输入

  • 用户问题
  • 工具输出(宏观数据)
  • 可选政策文本

输出(固定四段)

  1. 宏观状态(事实)
  2. 边际变化(环比/同比/修订)
  3. 资产含义(风格偏好,不给执行性交易指令)
  4. 风险与反证(与主结论冲突的数据、失效条件)

证据表(必选)

  • 列出 toolfetchmacrodata / toolfetchmacrosnapshot 等调用与 quality_status;指标数值须对应工具输出字段。

反证与局限(必选)

  • 数据修订、频率错配、单指标噪声对结论的影响。

强制规则

  • 仅通过 manifest / toolrunner 调用依赖工具,禁止引导直连 plugins.datacollection。
  • 先取数后解读,禁止先入为主叙事。
  • 必须引用证据:增长/通胀/信用至少各 1 个指标。
  • 当关键字段缺失时输出 insufficient_evidence。
  • 禁止输出买卖点、仓位比例、杠杆建议。
  • 象限阈值与映射从 config/macro_config.yaml 读取,不在文本中硬编码。

依赖工具

  • toolresolvesymbol(L2;宏观叙事需挂靠指数/期货等代码时可选)
  • toolfetchmacro_data(统一入口,推荐)
  • toolfetchmacro_snapshot(快照入口)
  • 兼容入口:toolfetchmacro_*

通用输出字段

  • summary
  • macro_state
  • delta_view
  • allocation_bias
  • risk_counterevidence
  • evidence
  • confidence_band(low/medium/high)