strategy-compare
starsforks
How to install strategy-compare?
marketcalls/vectorbt-backtesting-skills/strategy-compare
$npx -y skills add marketcalls/vectorbt-backtesting-skills --skill strategy-compareCompare multiple strategies or directions (long vs short vs both) on the same symbol. Generates side-by-side stats table.
SKILL.md
| 1 | Create a strategy comparison script. |
| 2 | |
| 3 | ## Arguments |
| 4 | |
| 5 | Parse `$ARGUMENTS` as: symbol followed by strategy names |
| 6 | |
| 7 | - `$0` = symbol (e.g., SBIN, RELIANCE, NIFTY) |
| 8 | - Remaining args = strategies to compare (e.g., ema-crossover rsi donchian) |
| 9 | |
| 10 | If only a symbol is given with no strategies, compare: ema-crossover, rsi, donchian, supertrend. |
| 11 | If "long-vs-short" is one of the strategies, compare longonly vs shortonly vs both for the first real strategy. |
| 12 | |
| 13 | ## Instructions |
| 14 | |
| 15 | 1. Read the vectorbt-expert skill rules for reference patterns |
| 16 | 2. Create `backtesting/strategy_comparison/` directory if it doesn't exist (on-demand) |
| 17 | 3. Create a `.py` file in `backtesting/strategy_comparison/` named `{symbol}_strategy_comparison.py` |
| 18 | 3. The script must: |
| 19 | - Fetch data once via OpenAlgo |
| 20 | - If user provides a DuckDB path, load data directly via `duckdb.connect(path, read_only=True)`. See vectorbt-expert `rules/duckdb-data.md`. |
| 21 | - If `openalgo.ta` is not importable (standalone DuckDB), use inline `exrem()` fallback. |
| 22 | - **Use OpenAlgo ta for ALL indicators by default** (never VectorBT built-in). Only switch to TA-Lib if the user explicitly says "talib"/"TA-Lib" |
| 23 | - **Always use OpenAlgo ta** for specialty indicators (Supertrend, Donchian, etc.) - no TA-Lib equivalent exists |
| 24 | - Clean signals with `ta.exrem()` (always `.fillna(False)` before exrem) |
| 25 | - Run each strategy on the same data |
| 26 | - **Indian delivery fees**: `fees=0.00111, fixed_fees=20` for delivery equity |
| 27 | - Collect key metrics from each into a side-by-side DataFrame |
| 28 | - **Include NIFTY benchmark** in the comparison table (via OpenAlgo `NSE_INDEX`) |
| 29 | - **Print Strategy vs Benchmark comparison table**: Total Return, Sharpe, Sortino, Max DD, Win Rate, Trades, Profit Factor |
| 30 | - **Explain results** in plain language - which strategy performed best and why |
| 31 | - Plot overlaid equity curves for all strategies using Plotly (`template="plotly_dark"`) |
| 32 | - Save comparison to CSV |
| 33 | 4. Never use icons/emojis in code or logger output |
| 34 | |
| 35 | ## Example Usage |
| 36 | |
| 37 | `/strategy-compare RELIANCE ema-crossover rsi donchian` |
| 38 | `/strategy-compare SBIN long-vs-short ema-crossover` |
People who liked this also viewed
6 picksType
- azure-costAzure cost management: query costs, forecast spending, optimize to reduce waste. WHEN: \"Azure costs\", \"Azure bill\", \"cost breakdown\", \"how much am I spending\", \"forecast spending\", \"optimizSkillsJul 2026
- pricingWhen the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increaseSkillsJul 2026
- stripe-integrationMulti-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLISkillsJul 2026
- startup-financial-modelingMulti-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLISkillsJul 2026
- tushare-finance专为 Claude Code 设计的 Tushare Pro 金融数据技能包，支持 220+ 个接口，用自然语言获取 A 股行情、财务数据、宏观经济等金融数据。SkillsJul 2026
- azure-pricingFetches real-time Azure retail pricing using the Azure Retail Prices API (prices.azure.com) and estimates Copilot Studio agent credit consumption. Use when the user asks about the cost of any Azure seSkillsJul 2026
