distil-cli

distil-cli is a Fine-tuning & training data skill for AI agents, published by distil-labs in the distil-cli-skill repository on GitHub. Skillspace rates distil-cli F (15/100) and the safety scan rated it unsafe; the rating is based on static analysis only.

Unsafe. This skill has patterns associated with malicious or dangerous behaviour. We do not recommend running it.

Train task-specific small language models (SLMs) using the Distil Labs CLI and platform. Activate this skill when the user asks about: distil labs, distil CLI, the distil command, training small language models, knowledge distillation, creating SLMs from production traces, data preparation for model training, fine-tuning student models from teacher models, deploying trained SLMs, model evaluation metrics, task-specific model training, classification/QA/tool-calling model training, synthetic data generation for training, or any question about the distil platform, its configuration, or its workflows. Also activate when the user mentions: distil model, distil login, distil register, uploading training data, teacher evaluation, model retuning, model deployment with llama-cpp or vLLM, or when working with config.yaml / job_description.json / train.csv files for model training.

Grade

F

Quality

15 / 100

Safety

Unsafe

GitHub stars

177

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.