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.
80
75%
Does it follow best practices?
Impact
88%
1.31xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/hugging-face-jobs/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly articulates both capabilities and trigger conditions. It provides comprehensive coverage of specific actions (hardware selection, secrets management, cost estimation) and includes natural trigger terms users would mention. The explicit 'Hugging Face Jobs infrastructure' focus makes it highly distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with tokens, secrets management, timeout configuration, and result persistence.' Also specifies use cases like 'data processing, inference, experiments, batch jobs, and any Python-based tasks.' | 3 / 3 |
Completeness | Explicitly answers both what ('UV scripts, Docker-based jobs, hardware selection, cost estimation...') and when ('Should be invoked for tasks involving cloud compute, GPU workloads, or when users mention running jobs on Hugging Face infrastructure'). Opens with 'This skill should be used when' providing clear trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'Hugging Face Jobs', 'cloud compute', 'GPU workloads', 'Docker', 'batch jobs', 'Python-based tasks', 'inference', 'data processing'. Good coverage of terms a user might naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on 'Hugging Face Jobs infrastructure' with distinct triggers like 'Hugging Face', 'Jobs', and specific features like 'UV scripts'. Unlikely to conflict with generic compute or other cloud provider skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly actionable with excellent executable examples and comprehensive coverage of HF Jobs functionality. However, it suffers from severe verbosity—the Token Usage section alone could be reduced by 80% by moving details to the referenced file. The skill repeats information extensively (token handling appears in 5+ places) and includes explanations Claude doesn't need (what tokens are, basic authentication concepts).
Suggestions
Move the detailed Token Usage Guide (~150 lines) to references/token_usage.md and keep only a 10-line summary with link in the main skill
Consolidate the repeated token handling examples—show the pattern once with MCP vs Python API difference, then reference it
Remove explanatory content Claude already knows: 'What are HF Tokens?', 'Token Types' definitions, basic authentication concepts
Add explicit error recovery workflows: 'If job fails with OOM → check logs → reduce batch size → resubmit' as a numbered sequence with validation steps
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~800+ lines, with extensive repetition of token usage information (dedicated section plus repeated throughout), multiple explanations of the same concepts (MCP vs CLI vs Python API shown repeatedly), and explanations of basic concepts Claude already knows (what tokens are, what authentication means). | 1 / 3 |
Actionability | The skill provides fully executable code examples throughout, with copy-paste ready MCP tool calls, Python API examples, and CLI commands. Examples include complete PEP 723 headers, proper secret handling, and real script patterns. | 3 / 3 |
Workflow Clarity | While there are checklists and step sequences, validation checkpoints are implicit rather than explicit. The 'Verification Checklist' before submitting is good, but there's no clear feedback loop for error recovery (e.g., what to do if job fails, how to debug, retry logic). | 2 / 3 |
Progressive Disclosure | References to external files exist (references/hardware_guide.md, references/troubleshooting.md) but the main skill contains massive inline content that should be in those reference files. The Token Usage section alone is ~150 lines that could be in references/token_usage.md with just a brief summary inline. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1043 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- huggingface/skills
- Commit
73246ad
- Reviewed
Table of Contents
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.