icccccccccy GitHub avatar

investment-skills

icccccccccy

Investment Skills is a Codex-based project providing a next-day conditional trade plan skill for A-share stocks, combining forward-adjusted historical data, company and industry news, and user portfolio details to generate scenario-based, risk-controlled trading plans.

Stars

11

7-day growth

No data

Forks

2

Open issues

0

License

No data

Last updated

2026-07-25

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

This repository stands out for its rigorous, multi-step methodology that enforces forward-adjusted price calculations, verifies news with original sources, and structures plans around conditional scenarios (bullish, neutral, bearish) with explicit risk and position sizing rules, rather than offering simplistic buy/sell predictions.

Who it is for

  • A-share individual investors using Codex for pre-market analysis
  • Quantitative developers seeking a structured research pipeline
  • Risk-conscious traders who want systematic risk management
  • Portfolio managers needing daily consolidated briefings for multiple holdings

Use cases

  • Generate a next-day conditional trade plan for a single stock with user-provided cost and position
  • Receive a daily 8:30 AM portfolio briefing covering risk, concentration, and per-stock action cards
  • Analyze how company announcements and industry news affect the upcoming trading day's plan
  • Manage a local watchlist of stocks with cost and position data for automatic daily updates

Strengths

  • Forces use of forward-adjusted price data to avoid mechanical gaps from dividends/splits, with a cross-check against unadjusted latest-day OHLC
  • Requires news analysis to specify direction, transmission path, intensity, credibility, and price reflection level for each company and industry news item
  • Produces three mutually exclusive scenarios (strong, neutral, weak) with explicit trigger conditions, position size, stop-loss, and cancel conditions
  • Supports multiple holdings in one input, saves watchlist locally, and provides a unified 8:30 AM briefing that does not block on single-stock failures

Considerations

  • Designed only for A-shares; not applicable to Hong Kong, US, or other markets without adaptation
  • Not suitable for automated trading or millisecond execution; requires manual user initiation and cannot connect to broker APIs
  • Heavily relies on AkShare data availability and user-provided account/risk parameters; without cost or position info, plans only give percentage-based allocations

README quick start

安装

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482