agent-trading-predictor

Agent skill for trading-predictor - invoke with $agent-trading-predictor

Install with Tessl CLI

npx tessl i github:ruvnet/claude-flow --skill agent-trading-predictor

What are skills?

3.27x

Review — 13%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Evaluation — 95%

↑ 3.27x

Agent success when using this skill

Validation — 11 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

77%

Satellite-to-Ground Latency Arbitrage Strategy

Satellite arbitrage temporal lead analysis

Criteria

Without context

With context

Temporal lead tool

100%

Satellite scenario param

100%

Geostationary distance

30%

100%

Advantage threshold

75%

100%

Predictive trade tool

100%

Light travel tool

100%

distanceKm param

100%

matrixSize param

100%

Trade prediction params

22%

100%

Conditional guard

100%

Without context: $0.2870 · 1m 38s · 11 turns · 16 in / 5,921 out tokens

With context: $0.5670 · 2m 40s · 23 turns · 387 in / 8,159 out tokens

100%

40%

Time Series Price Prediction Model for a Trading Desk

Neural network price prediction configuration

Criteria

Without context

With context

Neural train tool

100%

LSTM architecture type

100%

First LSTM layer units

100%

First LSTM return_sequences

100%

Dropout rate

100%

Second LSTM units

100%

Dense output layer

100%

Adam optimizer

100%

Learning rate

100%

Batch size and epochs

100%

Compute tier

100%

Without context: $0.3817 · 1m 55s · 19 turns · 74 in / 6,163 out tokens

With context: $0.4627 · 1m 56s · 21 turns · 26 in / 6,197 out tokens

87%

81%

Real-Time Portfolio Optimization System for a Proprietary Trading Firm

Portfolio optimization with sublinear solver and daily trading cycle

Criteria

Without context

With context

Sandbox create tool

100%

Sandbox template

100%

Sandbox name

Sandbox env vars

100%

Sandbox timeout

100%

Sandbox execute tool

100%

1ms execution cycle

100%

Sublinear solver tool

100%

Neumann method

100%

Solver epsilon

100%

Solver maxIterations

62%

100%

Dense matrix format

100%

Daily cycle stages

14%

Without context: $0.4793 · 2m 14s · 26 turns · 166 in / 7,310 out tokens

With context: $0.5970 · 2m 41s · 24 turns · 279 in / 9,074 out tokens

Evaluated: 3 days ago
Agent: Claude Code
Model: Unknown

Table of Contents

Satellite-to-Ground Latency Arbitrage Strategy Time Series Price Prediction Model for a Trading Desk Real-Time Portfolio Optimization System for a Proprietary Trading Firm

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.