Skip to content
Get packs

Asset Allocation and Optimizers

Explains portfolio allocation theory and how to configure four built-in portfolio optimizers.

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

What it does

Once installed, the agent can explain classic portfolio construction methods such as Modern Portfolio Theory, Black-Litterman, risk budgeting and the all-weather approach, and help you choose and configure one of five optimizers in a config.json file. It is mainly a reference guide covering theory, parameters and default settings, with the output meant to be written into a configuration file. The SKILL.md itself contains no executable code.

Great for

  • Students or analysts learning how different asset allocation frameworks differ
  • Developers configuring the optimizer settings in the Vibe-Trading system
  • Investors who want a plain-language explanation of risk parity versus mean-variance before deciding

Skip it if

  • Personal financial advice: the file gives general theory and example allocations, not tailored recommendations, and it does not account for individual circumstances or risk tolerance
  • Live trading decisions without independent testing: the guidance warns that mean-variance is often poor out of sample and sensitive to inputs, so results need backtesting

Try asking

  • “Explain the difference between risk parity and mean-variance optimization in simple terms”
  • “Help me set up a config.json using the risk_parity optimizer with a 90-day lookback”
  • “How does the Black-Litterman model combine market equilibrium with my own views?”
  • “What turnover_penalty value should I use for daily versus monthly rebalancing?”
Step-by-step guide: how to use Asset Allocation and OptimizersInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    asset-allocation.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

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

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip asset-allocation.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

  • Ask for a plain-language explanation first, then request a config snippet once you understand the trade-offs.
  • Treat example allocations (such as the China-focused all-weather mix) as illustrations and validate them with your own data.
  • Check the lookback and penalty parameters against your data frequency before running any optimizer.

What's inside

  • 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.