AKShare Stock Selection Integration for Openclaw

An intelligent stock selection skill leveraging real-time AKShare data with dynamic weighting and multi-dimensional scoring systems.

haosongyi-star
v1.0.0
Mar 14, 2026
0
1.1k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install akshare-integrated

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install akshare-integrated using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is AKShare Stock Selection Integration?

The AKShare Stock Selection Integration is a sophisticated tool designed for the Openclaw Skills ecosystem to provide professional-grade market analysis. It utilizes the AKShare library to pull real-time pricing and financial data, applying a three-layer, nine-dimensional scoring system to evaluate stocks across A-share, HK, and US markets.

By integrating dynamic weighting and industry-specific scoring standards, this skill moves beyond simple price tracking. it offers a comprehensive risk management framework, position sizing suggestions, and tiered evidence reliability (A/B/C/D), making it an essential asset for developers building automated trading agents or financial research bots.

AKShare Stock Selection Integration Use Cases

  • Real-time stock analysis and scoring across global markets (A-shares, Hong Kong, and US stocks).
  • Automated portfolio rebalancing based on dynamic value, transaction, and risk scores.
  • Quantitative screening for specific stock symbols to identify BUY, HOLD, or SELL signals.
  • Building automated financial research reports with high-reliability data evidence.

How AKShare Stock Selection Integration Works

  1. Data Acquisition: Fetches real-time market data through the AKShare interface with a multi-source backup mechanism.
  2. Multi-Dimensional Scoring: Evaluates the stock across three layers: Value (40%), Transactional (35%), and Risk (25%).
  3. Decision Logic: Processes the aggregate score to output specific actions like BUY, HOLD, REDUCE, or SELL.
  4. Risk Control Application: Applies stop-loss/take-profit boundaries and position limits to the final recommendation.
  5. Result Output: Generates structured JSON or CLI reports containing the recommendation, score, and evidence level.

AKShare Stock Selection Integration Setup

To get started with this skill in the Openclaw Skills environment, install the necessary dependencies:

# Upgrade AKShare to the latest version
pip install akshare --upgrade

# Install required data processing libraries
pip install pandas numpy

AKShare Stock Selection Integration Data Schema & Taxonomy

The skill organizes data into a structured hierarchy to ensure clarity and reliability:

Layer Components Weight
Value Layer Financial health, industry status, valuation metrics 40%
Transaction Layer Capital flow, K-line patterns, volume-price correlation 35%
Risk Layer Volatility, event-based risks, liquidity risk 25%

Evidence Taxonomy:

  • A/B Level: High reliability, based on verified real-time data.
  • C/D Level: Lower reliability, potentially using delayed or incomplete data sources.

AKShare Stock Selection Integration Advanced Features

  • Dynamic Weighting: Automatically adjusts scoring criteria based on prevailing market trends.
  • Industry Differentiation: Applies unique scoring standards tailored to specific sectors.
  • Position Sizing Engine: Provides specific percentage suggestions (e.g., 5% to 15%) based on the certainty of the score.
  • Asynchronous Batch Processing: High-performance multi-market queries using concurrent requests.
  • Local Caching: Optimized 5-minute local cache to reduce API overhead and bypass frequency limits.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*