strategy-compare
- Repo stars 142
- Author updated Live
- Author repo vectorbt-backtesting-skills
- Domain
- Data
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @marketcalls · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- External requests
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: strategy-compare
description: Compare multiple strategies or directions (long vs short vs both) on the same symbol. Generates…
category: data
runtime: no special runtime
---
# strategy-compare output preview
## PART A: Task fit
- Use case: Compare multiple strategies or directions (long vs short vs both) on the same symbol. Generates side-by-side stats table. Create a strategy comparison script. Parse $ARGUMENTS as: symbol followed by strategy names makes outbound network calls. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Arguments / Instructions / Example Usage” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Compare multiple strategies or directions (long vs short vs both) on the same symbol. Generates side-by-side stats table. Create a strategy comparison script. Parse $ARGUMENTS as: symbol followed by strategy names makes outbound network calls. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Arguments / Instructions / Example Usage” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; may access external network resources; usually needs no extra API key.
## Running Rules
- read files, write/modify files; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source mentions slash commands such as `/strategy-compare`; use them first when your agent supports command triggers.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Validate with a small run
Start with a small task and check whether the result follows “Arguments / Instructions / Example Usage”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: strategy-compare
description: Compare multiple strategies or directions (long vs short vs both) on the same symbol. Generates…
category: data
source: marketcalls/vectorbt-backtesting-skills
---
# strategy-compare
## When to use
- Compare multiple strategies or directions (long vs short vs both) on the same symbol. Generates side-by-side stats tab…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Arguments / Instructions / Example Usage” and keep inference separate from source facts.
- read files, write/modify files; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "strategy-compare" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Arguments / Instructions / Example Usage
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | may access external network resources
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Create a strategy comparison script.
Arguments
Parse $ARGUMENTS as: symbol followed by strategy names
$0= symbol (e.g., SBIN, RELIANCE, NIFTY)- Remaining args = strategies to compare (e.g., ema-crossover rsi donchian)
If only a symbol is given with no strategies, compare: ema-crossover, rsi, donchian, supertrend. If "long-vs-short" is one of the strategies, compare longonly vs shortonly vs both for the first real strategy.
Instructions
- Read the vectorbt-expert skill rules for reference patterns
- Create
backtesting/strategy_comparison/directory if it doesn't exist (on-demand) - Create a
.pyfile inbacktesting/strategy_comparison/named{symbol}_strategy_comparison.py - The script must:
- Fetch data once via OpenAlgo
- If user provides a DuckDB path, load data directly via
duckdb.connect(path, read_only=True). See vectorbt-expertrules/duckdb-data.md. - If
openalgo.tais not importable (standalone DuckDB), use inlineexrem()fallback. - Use TA-Lib for ALL indicators (never VectorBT built-in)
- Use OpenAlgo ta for specialty indicators (Supertrend, Donchian, etc.)
- Clean signals with
ta.exrem()(always.fillna(False)before exrem) - Run each strategy on the same data
- Indian delivery fees:
fees=0.00111, fixed_fees=20for delivery equity - Collect key metrics from each into a side-by-side DataFrame
- Include NIFTY benchmark in the comparison table (via OpenAlgo
NSE_INDEX) - Print Strategy vs Benchmark comparison table: Total Return, Sharpe, Sortino, Max DD, Win Rate, Trades, Profit Factor
- Explain results in plain language - which strategy performed best and why
- Plot overlaid equity curves for all strategies using Plotly (
template="plotly_dark") - Save comparison to CSV
- Never use icons/emojis in code or logger output
Example Usage
/strategy-compare RELIANCE ema-crossover rsi donchian
/strategy-compare SBIN long-vs-short ema-crossover
Decide Fit First
Design Intent
How To Use It
Boundaries And Review