ML

ml-backtest-dataset

Local bundle for ML inference, dataset scripting, and backtesting. Ensures advisory-only boundaries for model output.

Install

mkdir -p .claude/skills/ml-backtest-dataset && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13573" && unzip -o skill.zip -d .claude/skills/ml-backtest-dataset && rm skill.zip

Installs to .claude/skills/ml-backtest-dataset

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Codex-local skill bundle for ML inference, dataset scripts, backtests, and advisory-only model boundaries.
106 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Map model inference code, dataset builders, and feature generation.
  • Identify backtest scripts and stored artifacts.
  • Preserve risk-policy and paper-trading guardrails around predictions.
  • Document any temporal split assumptions.
  • Identify inference/backtest entrypoints.

How it works

This skill scouts and maps ML components, ensuring risk policies are preserved and documenting assumptions, to prepare for or run backtests.

Inputs & outputs

You give it
ML inference code, dataset builders, feature generation scripts, backtest scripts, and stored artifacts.
You get back
Identified dataset and feature paths, inference/backtest entrypoints, and a proposed or run validation/backtest command.

When to use ml-backtest-dataset

  • Backtest ML model predictions
  • Inspect feature generation scripts
  • Validate dataset temporal splits

About this skill

ML Backtest Dataset

This is a Codex-local skill bundle, not a guaranteed auto-discovered official Codex skill.

Rules

  • Scout first: map model inference code, dataset builders, feature generation, backtest scripts, stored artifacts, and tests.
  • Keep ML output advisory unless a future explicitly approved task changes that product boundary.
  • Avoid training/validation leakage and document any temporal split assumptions.
  • Do not mutate production data or overwrite model artifacts without explicit user approval.
  • Backtest evidence must include data range, assumptions, and limitations.
  • Preserve risk-policy and paper-trading guardrails around predictions.

Evidence

  • Dataset and feature paths inspected.
  • Inference/backtest entrypoints identified.
  • Advisory-only boundary preserved.
  • Validation or backtest command proposed or run.

When not to use it

  • When the task involves mutating production data.
  • When the task involves overwriting model artifacts without explicit user approval.

Limitations

  • ML output remains advisory unless a future approved task changes the product boundary.
  • The skill avoids training/validation leakage.
  • The skill does not mutate production data or overwrite model artifacts without explicit user approval.

How it compares

This skill bundles ML utilities with explicit rules for risk-policy preservation and documentation of assumptions, unlike general ML script execution.

Compared to similar skills

ml-backtest-dataset side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
ml-backtest-dataset (this skill)02moNo flagsIntermediate
llava78moReviewAdvanced
cocoindex69moReviewIntermediate
ai-multimodal96moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

llava

zechenzhangAGI

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

7117

cocoindex

cocoindex-io

Comprehensive toolkit for developing with the CocoIndex library. Use when users need to create data transformation pipelines (flows), write custom functions, or operate flows via CLI or API. Covers building ETL workflows for AI data processing, including embedding documents into vector databases, building knowledge graphs, creating search indexes, or processing data streams with incremental updates.

6116

ai-multimodal

mrgoonie

Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.

9108

rag-implementation

wshobson

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

10101

rdkit

K-Dense-AI

Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.

856

pyhealth

davila7

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).

351

Search skills

Search the agent skills registry