Skip to content
Get packs

Seasonal Calendar Trading Signals

Generates long/short/flat trading signals from month-of-year and weekday patterns in price data

Source Download skill
Repository
HKUDS/Vibe-Trading
Stars
37,433
Licence
MIT
Files
2 files

What it does

This skill teaches an AI agent to build a simple trading strategy based on calendar effects, such as certain months or weekdays historically performing better or worse. Once installed, when asked, the agent can label each period as long (1), short (-1), or stay out (0) using pandas, and can set which months and weekdays count as bullish or bearish. The skill describes the logic and includes a Python example engine, but it is a statistical pattern, not a guaranteed prediction, and its usefulness depends on backtesting.

Great for

  • Quant researchers testing whether calendar effects hold in a given market
  • Developers prototyping a simple rules-based strategy on OHLCV price data
  • Students learning how time-based market anomalies are coded and tested

Skip it if

  • Investors expecting reliable profits: seasonal patterns are statistical regularities that can fail or vanish, and the skill itself warns about sample size
  • Live trading without independent backtesting and risk controls, since the skill provides no risk management, position sizing, or transaction cost modelling

Try asking

  • “Create a seasonal signal for daily prices that is long in January to March and November to December and flat otherwise”
  • “Add a Friday weekday overlay to my sell-in-May strategy and only trade when both month and weekday agree”
  • “Backtest the sell-in-May effect on my OHLCV CSV and explain the sample size limits”
Step-by-step guide: how to use Seasonal Calendar Trading SignalsInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    seasonal.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip seasonal.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip seasonal.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Check the example engine's use of 'or' defaults: passing an empty list falls back to the default months, so pass explicit lists when you intend to change them
  • Run out-of-sample tests and check statistical significance before relying on any calendar pattern
  • Review the generated code before executing it, since the skill includes a script the agent will run

What's inside

  • example_signal_engine.py
  • SKILL.md

Redistributed unmodified from HKUDS/Vibe-Trading under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.