Industry Research CN

v1.0.0

行业深度研究工具。当用户要求"研究XX行业"、"分析XX商品"、"行业研究报告"时触发。自动化搜集指定商品/行业的价格走势、成因分析、上下游产业链、重大新闻、A股上市公司列表及财务分析(营收/毛利润占比)、价格波动对各公司的影响(受益/受损)、投资机会与风险提示,并附重点公司换手率分析及技术面分析(K线形态+均线...

0· 43·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for whitertigerwilson/industry-research-cn.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Industry Research CN" (whitertigerwilson/industry-research-cn) from ClawHub.
Skill page: https://clawhub.ai/whitertigerwilson/industry-research-cn
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install industry-research-cn

ClawHub CLI

Package manager switcher

npx clawhub@latest install industry-research-cn
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (industry research, A-share/company analysis, K-line/turnover analysis) match the included scripts and SKILL.md: scripts perform K-line detection, turnover aggregation, company filtering and sample searches against public finance APIs (eastmoney, qt.gtimg). No unrelated credentials or tools are requested.
Instruction Scope
Instructions are scoped to web searches, fetching public news/data, and running the included Python scripts. One noteworthy instruction (Step 0.3) tells the agent to "immediately fix stock_filter.py" if data-source discrepancies or code errors are found — this grants the agent discretion to modify a bundled code file at runtime. That can be legitimate for data-correction but is a behavioral escalation compared with read-only analysis.
Install Mechanism
No install spec; this is instruction+script based. Scripts use the requests library and optionally akshare (noted in stock_filter.py). No downloads from untrusted URLs, no archive extraction, and all external endpoints are public finance/news APIs (eastmoney, qt.gtimg, push2 endpoints, AP/BBC/NPR referenced).
Credentials
The skill declares no environment variables or credentials and the scripts do not attempt to read secrets. Network access to public data providers is required and akshare is an optional dependency; no disproportionate or unrelated credentials/config paths are requested.
Persistence & Privilege
always:false (no forced always-on). The runtime instruction to edit stock_filter.py is the main persistence/privilege caveat: modifying its own bundled files is permitted in many workflows but increases risk of accidental or malicious logic changes if allowed without review. The skill does not request system-wide config changes or other skills' credentials.
Assessment
This skill appears to do what it says: it fetches news/price data from public sources and runs local Python scripts to produce structured industry research. Before enabling: 1) Understand it needs network access to public finance/news endpoints (eastmoney, qt.gtimg, AP/BBC/NPR) and may call them automatically. 2) The skill includes runnable scripts and will ask to run them; inspect the scripts yourself to ensure you accept their behavior (they only call public APIs and print results). 3) Decide whether you are comfortable allowing the agent to modify the bundled file stock_filter.py at runtime — this can be useful for correcting mappings but is a higher-risk action; consider requiring human approval before any file edits. 4) stock_filter.py mentions akshare (optional) and some scripts use a hardcoded end date (2026-04-15) which may produce stale results; expect to update dependencies or code for up-to-date data. 5) Do not treat outputs as investment advice; keep the provided disclaimer and verify critical data against primary filings. If you want lower risk, run the scripts manually in a sandbox and deny automatic file-write permissions to the agent.

Like a lobster shell, security has layers — review code before you run it.

latestvk97f1hwvep1sp8wpsd0xgwnhcd85n6pq
43downloads
0stars
1versions
Updated 1d ago
v1.0.0
MIT-0

Industry Research Skill

行业深度研究,10个维度结构化输出。

工作流程

Step 0: 预检——多源股价交叉核对

⚠️ 每次报告发布前必须执行,防止单一数据源错误(如代码错误)导致全报告失真。

核对流程:

  1. 搜索个股实时价格时,至少用两个不同数据源交叉验证:
    • 数据源A:腾讯行情 https://qt.gtimg.cn/q=sz{代码}
    • 数据源B:东方财富K线 https://push2his.eastmoney.com/api/qt/stock/kline/get?secid=0.{代码}
  2. 若两个数据源的价格差异超过5%,需排查代码是否正确
  3. 若发现代码错误,立即修正 stock_filter.py 中的预定义股票池

Step 1: 确认研究对象

用户输入行业/商品名称,确认为单一商品(如"硫酸"、"铜"、"原油"),非行业整体。

Step 2: 价格走势

使用 web_searchweb_fetch 搜集:

  • 近期价格走势(2025年至今)
  • 当前价格水平及同比/环比变化
  • 价格历史区间(近52周、5年、历史高点/低点)

优先数据源:AP News、BBC、NPR(英文主流媒体)→ 中文媒体(界面新闻、彭博中文、东方财富)作为辅助。

搜索关键词模板:{商品} price trend 2025 2026{商品} 价格上涨 原因

Step 3: 成因分析

从搜索结果中提取价格上涨/下跌的核心驱动因素,归类为:

  • 供给侧(产能、进口、库存、检修)
  • 需求侧(下游行业景气度)
  • 政策/地缘政治因素
  • 成本端传导

Step 4: 上下游产业链

梳理上游原料及占比、下游用途及消费占比。使用表格输出。

Step 5: 重大新闻

提取最近3-6条重大新闻,每条附来源。关注:产能变化、政策动向、地缘事件、进出口限制。

Step 6: A股上市公司

使用 scripts/stock_filter.py 筛选主营业务涉及该商品的上市公司:

python scripts/stock_filter.py <商品关键词>

输出:公司名称、股票代码、主营收入占比(%)、毛利润占比(%)、该商品产能。

若脚本不可用,用 web_search 手动搜索"A股 {商品} 上市公司"。

Step 7: 受益/受损分析

基于Step 6数据,分析:

  • 受益:商品价格上涨 → 利润弹性大的公司(原料自给率高、产能大、营收占比高)
  • 受损:商品价格上涨 → 成本压力大的公司(外购原料、营收占比低)

使用弹性估算公式:

利润弹性 ≈ 价格变动幅度(%) × 产量 × 营收占比

Step 8: 投资机会与风险

综合以上分析,给出:

  • 明确受益标的(高弹性)
  • 稳健型标的(全产业链/资源自给)
  • 风险提示(价格高位、政策风险、地缘缓和)

Step 9: 换手率分析

针对Step 8中明确受益的前3名公司,补充最近30个交易日的换手率数据。

数据获取

python scripts/stock_turnover.py <股票代码> 30

输出指标

  • 最近30个交易日累计换手率(%)
  • 超过5%换手率的天数
  • 表格格式:公司 | 代码 | 30日累计换手率 | >5%换手天数 | 活跃度

判断标准

  • 累计换手率>100%:高度活跃 ⚠️
  • 累计换手率30-100%:正常活跃
  • 累计换手率<30%:相对冷清
  • 5%天数>10天:主力频繁活动

Step 10: K线形态 + 均线排列分析

针对Step 8中明确受益的前3名公司,补充技术面分析。

数据获取

python scripts/kline_pattern.py <股票代码> 15

K线形态检测

  • 锤子线/吊颈线、射击之星、吞没(阳包阴/阴包阳)、早晨/黄昏之星、乌云盖顶、大阳/大阴线(放量)
  • 每种形态标注:日期、类型、看多/看空信号、含义

均线多头/空头排列判断(基于5日、10日、20日均线):

  • 多头排列:5日均线>10日均线>20日均线,且价格站于5日均线上方 → 上升趋势
  • 空头排列:5日均线<10日均线<20日均线,且价格处于5日均线下方 → 下降趋势
  • 震荡/混合:均线纠缠、反复交叉 → 趋势不明

输出格式

### {公司名}({代码})
**均线排列**:{多头/空头/震荡} | MA5={价格} MA10={价格} MA20={价格}
**K线形态**:共检测到N个信号
- {日期} [{WE/BE}] {形态名称} — {含义}
**综合判断**:{基于技术面的短期趋势描述}

输出格式

# {商品} 行业深度研究报告
> 数据来源:xxx | 报告日期:2026年x月x日

## 一、价格走势
## 二、成因分析
## 三、上下游产业链
## 四、重大新闻
## 五、A股相关上市公司
## 六、受益/受损分析
## 七、投资机会与风险
## 八、重点公司换手率分析(近30交易日)
## 九、技术面分析(前3重点公司)
⚠️ 免责声明

免责声明模板

⚠️ 以上内容仅供参考,不构成投资建议。数据来源于公开资料,部分为公司历史披露数据,请以公司公告为准。投资有风险,入市需谨慎。

已知商品研究案例

  • 硫酸(2026年4月):硫磺酸、冶炼酸工艺;铜陵有色/江西铜业/华尔泰受益;钛白粉企业受损
  • 镍(2026年4月):不锈钢+电池双赛道;华友钴业/格林美/容百科技受益;不锈钢厂受损
  • 宠物食品(2026年4月):A股纯度最高标的乖宝宠物(301498);消费升级+品牌溢价逻辑;换手率正常无异动
  • 铜(2026年4月):紫金矿业/洛阳钼业/铜陵有色受益;铜加工企业受损

升级方向(预留)

  • ✅ 第九模块已添加:换手率分析
  • ✅ 第十模块已添加:K线形态+均线排列分析
  • 添加 akshare 实时价格API支持(当前网络数据源不稳定)
  • 添加财报数据自动抓取(营收/毛利占比精确计算)
  • 添加期货/现货升贴水分析
  • 支持多商品对比研究

Comments

Loading comments...