Behavioral Finance Applications
Gives the agent behavioral-finance theory and quant signal rules for trading and bias checks
- Repository
- HKUDS/Vibe-Trading
- Stars
- 37,433
- Licence
- MIT
- Files
- 1 file
What it does
This skill gives an AI agent a reference of behavioral-finance ideas, such as investors reacting too slowly or too strongly to news, and turns them into trading signal rules, sentiment indicators, and checklists for common investor biases like loss aversion and herding. When asked about market momentum, reversals, or sentiment, the agent can use these frameworks to explain and structure its analysis, with a focus on China A-share examples. The file contains only text and code snippets; it does not itself fetch market data or run any trades.
Great for
- Quantitative researchers exploring momentum or reversal strategy ideas for China A-shares
- Investors or students who want a structured checklist of cognitive biases to review their own decisions
- Analysts building a market sentiment dashboard who want a starting set of indicators and weights
Skip it if
- Making live trading decisions: the thresholds and claimed excess returns (e.g. 3-5% over 20 days, 8% rebound after limit-downs) are stated without sources in the file and should be verified before relying on them, and past patterns may not persist.
- Users expecting real market data or automated trading: the skill only describes methods and does not connect to any data feed or broker.
- Investment advice for personal finance: the content is strategy-oriented and assumes familiarity with quant trading terms.
Try asking
- “Explain the difference between momentum and reversal effects and when each might apply to A-share stocks.”
- “Build a composite market sentiment score from turnover, margin growth, and limit-up counts using the suggested weights.”
- “Review my trading history for loss aversion or overconfidence signs and suggest debiasing rules.”
- “Compute a capital gain overhang indicator for a stock given its price and 60-day VWAP.”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
behavioral-finance.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip behavioral-finance.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip behavioral-finance.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 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 the agent to cite the source of any specific number (such as the excess return figures) and to flag which ones are unverified assumptions.
- Provide your own market data (turnover, margin balances, limit-up counts) in the conversation, since the skill does not supply it.
- Treat the sentiment score weights and thresholds as starting points to backtest on your own data rather than fixed rules.
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.