quick-stats — Claude Code skill: what it does, how to install
Generates a short EMA crossover backtest for a symbol and prints core trading metrics. Use it when you want runnable code in a Jupyter cell or console.
npx skills add marketcalls/vectorbt-backtesting-skills --skill quick-stats -a claude-codeWhat quick-stats does
This skill produces one code block that can run in Jupyter or as a script, without creating files. It retrieves prices from OpenAlgo, uses DuckDB when you provide a database path, and falls back to yfinance when needed.
The default strategy uses an EMA 10/20 crossover through OpenAlgo ta. It cleans signals with ta.exrem() after .fillna(False). The output covers return, Sharpe Ratio, Sortino Ratio, maximum drawdown, win rate, Profit Factor, trade count, NIFTY benchmark return, and alpha. It also draws an equity curve with Plotly's dark template.
The calculation uses Indian delivery charges: fees=0.00111, fixed_fees=20. Check those costs against your own setup before comparing results. TA-Lib is used only when you explicitly request talib or TA-Lib.
What it helps with
- test an EMA crossover for a symbol
- retrieve market data from OpenAlgo or DuckDB
- compare strategy returns with NIFTY
- calculate drawdown and win rate
- plot an equity curve with Plotly
Example prompts for the agent
/quick-stats RELIANCE/quick-stats HDFCBANK NSE 1h/quick-stats SBIN NSE D
How to install quick-stats
1Skills CLI (Vercel)
npx skills add marketcalls/vectorbt-backtesting-skills --skill quick-stats -a claude-code2Manually: put the files in place
~/.claude/skills/quick-stats/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/quick-stats/
1Skills CLI (Vercel)
npx skills add marketcalls/vectorbt-backtesting-skills --skill quick-stats -a codex2Manually: put the files in place
.agents/skills/quick-stats/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add marketcalls/vectorbt-backtesting-skills --skill quick-stats -a cursor2Manually: put the files in place
.cursor/skills/quick-stats/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install marketcalls/vectorbt-backtesting-skills quick-stats2Manually: put the files in place
.github/skills/quick-stats/SKILL.md1Skills CLI (Vercel)
npx skills add marketcalls/vectorbt-backtesting-skills --skill quick-stats -a gemini-cli2Platform CLI
gemini skills install https://github.com/marketcalls/vectorbt-backtesting-skills --path .claude/skills/quick-statsManually: put the files in place
.devin/skills/quick-stats/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add marketcalls/vectorbt-backtesting-skills --skill quick-stats -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about quick-stats
How do I install quick-stats in Claude Code?
Run npx skills add marketcalls/vectorbt-backtesting-skills --skill quick-stats -a claude-code, then run npx skills add marketcalls/vectorbt-backtesting-skills --skill quick-stats -a claude-code again. The skill file is placed at ~/.claude/skills/quick-stats/SKILL.md.
What does quick-stats do?
It generates code for a short EMA 10/20 crossover backtest for a chosen symbol. The code prints trading metrics, compares the result with NIFTY, and plots an equity curve.
Where does quick-stats get market data?
It uses OpenAlgo first. When you provide a database path, it uses DuckDB; yfinance serves as a fallback source.
