hugging-face-jobs

This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with tokens, secrets management, timeout configuration, and result persistence. Designed for general-purpose compute workloads including data processing, inference, experiments, batch jobs, and any Python-based tasks. Should be invoked for tasks involving cloud compute, GPU workloads, or when users mention running jobs on Hugging Face infrastructure without local setup.

1.31x

Quality

75%

Does it follow best practices?

Impact

88%

1.31x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/hugging-face-jobs/SKILL.md

Evaluation results

76%

20%

Batch Sentiment Analysis on Customer Reviews

UV job submission with inline script and Hub persistence

Criteria

Without context

With context

Uses hf_jobs MCP call

Inline script content

100%

PEP 723 dependency header

100%

Token via secrets parameter

100%

$HF_TOKEN placeholder used

Result persistence included

100%

GPU hardware selected

50%

100%

Non-default timeout set

Does NOT save script to local file first

100%

Token verification in script

100%

Notes.md explains decisions

100%

90%

35%

Automated Job Submission Integration for ML Platform

Python API token handling: get_token() vs $HF_TOKEN literal

Criteria

Without context

With context

Identifies $HF_TOKEN bug

50%

100%

Uses get_token() fix

100%

Does NOT use $HF_TOKEN in Python API

100%

Token via secrets not env

100%

Explains MCP vs Python API distinction

100%

Token not hardcoded

100%

Script comment explaining approach

100%

Script inner token verification

Explains 401 error root cause

75%

100%

99%

Automated Weekly Model Evaluation Pipeline

Scheduled jobs with hardware selection and timeout configuration

Criteria

Without context

With context

Uses scheduled job API

100%

Correct schedule format

100%

Appropriate GPU hardware

100%

Timeout with buffer above runtime

100%

Inline script content

100%

PEP 723 dependency header

100%

Token via secrets

100%

90%

Result persistence in script

100%

Timeout rationale documented

100%

Repository: huggingface/skills
Commit: 73246ad

Evaluated: 22 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Batch Sentiment Analysis on Customer Reviews Automated Job Submission Integration for ML Platform Automated Weekly Model Evaluation Pipeline

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.