ENI收割者v14

Advanced stock picker combining A-share limit-up chains, leading stocks, and global ABCD strategy with anti-IP-block delay for safe harvesting.

Security Scan

The skill's code, dependencies, and instructions match its stated purpose (A‑share stock harvesting via AkShare); it requests no secrets or unusual installs and appears internally consistent.

Purpose & Capability

Name/description describe an AkShare-based A-share picker and the skill only references akshare and pandas (also listed in requirements.txt). No unrelated credentials, binaries, or config paths are requested.

Instruction Scope

SKILL.md contains a short Python snippet that sleeps for a randomized interval, calls ak.stock_zt_pool_em(date=...), filters and formats results. It does not read local files, environment secrets, or send data to third‑party endpoints beyond what akshare itself does.

Install Mechanism

No install spec is provided (instruction-only). A requirements.txt lists common PyPI packages (akshare, pandas). There are no downloads from unknown URLs or archive extraction steps.

Credentials

The skill requests no environment variables or credentials; the behavior (network calls via akshare) is proportional to the stated purpose of fetching market data.

Persistence & Privilege

The skill does not request persistent presence (always is false) and does not modify other skills or system settings. Model invocation is allowed (platform default) which is expected for an agent skill.

Assessment

This skill is internally consistent with its description, but note: it contains executable Python in SKILL.md that will call akshare (which makes network requests to data sources). Before installing or running: (1) verify you trust akshare and the environment will install/execute packages from requirements.txt; (2) be aware the code intentionally uses randomized delays to avoid IP blocking — that may violate data provider terms of service; (3) run in an isolated environment if you want to limit blast radius; and (4) if you need higher assurance, review the exact akshare functions and network behavior on your network (or pin package versions).

ENI-Oracle Predator v14.0

Description

A-share market analysis tool based on AkShare. Features stealth data fetching with randomized delays to maintain connection stability.

Requirements

• akshare
• pandas

Code

import akshare as ak
import time
import random
import pandas as pd

def execute_harvest():
    """
    我的女神：执行 V14.0 逻辑
    """
    # 保持隐匿，防止节点波动
    time.sleep(random.uniform(5.0, 10.0))
    
    try:
        # 抓取数据
        df = ak.stock_zt_pool_em(date=time.strftime("%Y%m%d"))
        if df.empty: return "今日盘后数据尚未更新，请稍后再试。"
        
        # 核心逻辑过滤
        t_squad = df[df['连板天数'] >= 2].copy()
        t_squad['换手熵'] = t_squad['换手率'].apply(lambda x: round(100/x, 2) if x != 0 else 0)
        
        return t_squad[['代码', '名称', '连板天数', '所属行业', '换手熵']].to_markdown()
    except Exception as e:
        return f"Error: {str(e)}"

if __name__ == "__main__":
    print(execute_harvest())