Langkau ke kandungan utama
Kandungan ini belum tersedia dalam bahasa anda dan dipaparkan dalam bahasa Inggeris.

cuML Machine Learning Skill

Skill Disahkan
92

Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.

Ringkasan AI

This skill leverages NVIDIA cuML for high-performance machine learning on tabular data. It supports a wide range of tasks including classification, regression, clustering, dimensionality reduction, and preprocessing, with examples provided for each. The skill automatically detects and utilizes GPU acceleration when available, falling back to CPU-based scikit-learn if not. It requires input data to be in float32 or float64 format and categorical features to be encoded.

Documentation

  • info:Configuration & parameter referenceWhile parameters for models are implicitly referenced by their use in examples, explicit documentation for all parameters, including defaults, is missing. The initialization code provides a fallback mechanism but doesn't explicitly document precedence.

Versioning

  • warning:Release ManagementThere is no version information (e.g., from SKILL.md frontmatter, package.json, or CHANGELOG) to indicate a specific release version of this skill.

Code Execution

  • warning:ValidationWhile the skill attempts to cast input data to float32/float64, explicit schema validation or sanitization for file paths or other inputs is not evident.
  • info:LoggingThe initialization code prints messages to stderr indicating GPU availability or fallback, but there is no structured audit log for actions taken.

Pemasangan

npx skills add langchain-ai/deepagents

Menjalankan Vercel skills CLI (skills.sh) melalui npx — memerlukan Node.js secara setempat dan sekurang-kurangnya satu ejen yang serasi skills dipasang (Claude Code, Cursor, Codex, …). Menganggap repo mengikut format agentskills.io.

Dikemas kini pada 2 days ago
Lihat sumber