skills.rest
ruvnet
ruvnetCOMMUNITY
Explore all skills by this author →
Website𝕏@ruvGitHub

trader-cloud-backtest

Runs heavy neural-trader backtests and model training jobs on Anthropic Managed Agent cloud containers.

70.1k|8.4k|Updated Jun 2, 2025
Search Tags:#backtesting#Walk-Forward#Monte-Carlo#Cloud#ed25519#Managed Agents#neural-trader
One-click install
npx skills add https://github.com/ruvnet/claude-flow --skill trader-cloud-backtest
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: trader-cloud-backtest
Source: https://github.com/ruvnet/claude-flow/tree/main/plugins/ruflo-neural-trader/skills/trader-cloud-backtest
Command: npx skills add https://github.com/ruvnet/claude-flow --skill trader-cloud-backtest

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires neural-trader.

What problem does it solve?

Long-running trading strategy jobs like multi-year walk-forward backtests, large Monte-Carlo simulations, parameter sweeps, and neural model training are too heavy to run locally, and unmanaged cloud runs waste money on idle containers.

Core Features & Use Cases

  • Cloud Job Dispatch: Provisions an Anthropic Managed Agent container with the neural-trader CLI pre-installed, runs backtest, training, or sweep jobs, and terminates the environment immediately after results return.
  • Cost Controls: Enforces cost estimation before launch, cheap pre-flight smoke tests, environment reuse, and batched sweeps in a single container session.
  • Signed Result Ingestion: Signs backtest artifacts with Ed25519, verifies them against a pinned trusted public key before storage, and refuses promotion of invalid signatures to live strategies.
  • Use Case: Run a 2020-2024 walk-forward backtest of a multi-indicator strategy on SPY with 1000 Monte-Carlo paths in the cloud, then store the verified metrics and record the session cost.

Quick Start

Ask the agent to run a cloud backtest of the multi-indicator strategy on SPY from 2020 to 2024 with walk-forward validation and 1000 Monte-Carlo paths, then report Sharpe, max drawdown, and win rate.

Frequently Asked Questions about trader-cloud-backtest

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a neural-trader backtest in the cloud?▼

Create a Managed Agent container with the neural-trader npm package pre-installed, send a managed_agent_prompt with the backtest command and parameters, then retrieve the reported metrics and terminate the session. The skill handles provisioning, execution, and cleanup.

When should I use cloud backtesting instead of local backtesting?▼

Use the cloud runtime for multi-year walk-forward runs, large Monte-Carlo path counts, parameter sweeps, or model training jobs. Quick sanity checks and short backtests under about a minute should run locally with the trader-backtest skill.

What happens if the ANTHROPIC_API_KEY is missing for managed agents?▼

If the managed_agent tools report that an API key is needed, the skill falls back to the local trader-backtest skill instead of running in the cloud. Managed Agents beta access is a prerequisite for cloud execution.

How are cloud backtest results verified before use?▼

Results are signed locally as a SignedBacktestArtifact with Ed25519, then verified against a pinned trusted public key from project config before storage or promotion. If verification fails, the artifact is refused and never promoted to a live strategy.

How do I control costs for cloud backtest sessions?▼

Estimate cost before launching, install neural-trader once via initScript, reuse the environment, batch sweeps into one prompt, run a cheap smoke test first, and terminate the container immediately after results arrive. Idle containers keep billing until terminated.

Related Skills

Explore More Finance & Accounting Skills→
MoyuchiiiiMoyuchiiii

backtest-runner

Run backtests on specified stocks and time periods to output returns, drawdown, and Sharpe ratio.

Community
Intermediate
4tie4tie

profitable-strategy-discovery

Discover profitable crypto trading strategies via AutoQuant and Freqtrade backtesting.

Community
Advanced
duolaAmengweb3duolaAmengweb3
86

clawquant-trader

Executes batch and single Metamask wallet sweeps and transfers via CLI with JSON output.

Community
Advanced
Superior-TradeSuperior-Trade
226

superior-trade-api

Generates, backtests, and deploys automated trading strategies via Superior Trade API.

Official
Advanced