context-course
github.com/huggingface/context-course
Skill | Added | Review |
|---|---|---|
autolab-reporter Operate the local Trackio reporter for Autolab HF Jobs. Use when a reporter or planner needs to inspect scores, active jobs, worker anomalies, duplicate launches, or the overall experiment board. | 70 70 Impact — No eval scenarios have been run Securityby  Advisory Suggest reviewing before use Reviewed: Version: 0448a7c | |
autolab-managed-experiment Run one Autolab benchmark experiment safely on Hugging Face Jobs. Use when a planner, reviewer, or experiment worker is preparing, auditing, launching, or reviewing a single train.py hypothesis against the current local promoted master. | 87 87 1.94x Agent success vs baseline Impact 99% 1.94xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0448a7c | |
hf-cli Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing repositories, models, datasets, and Spaces on the Hugging Face Hub. Replaces now deprecated `huggingface-cli` command. | 76 76 2.27x Agent success vs baseline Impact 100% 2.27xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0448a7c | |
huggingface-local-models Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving. | 90 90 1.25x Agent success vs baseline Impact 73% 1.25xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0448a7c | |
autolab-hermes-delegation Use Hermes delegate_task cleanly in this repo for planner, reviewer, researcher, reporter, experiment-worker, and memory-keeper roles. | 69 69 5.00x Agent success vs baseline Impact 100% 5.00xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0448a7c |