Name: hugging-face-jobs
Rating: 46.400000000000006 (1 reviews)
Author: administrakt0r

hugging-face-jobs

Run any workload on fully managed Hugging Face infrastructure. No local setup required—jobs run on cloud CPUs, GPUs, or TPUs and can persist results to the Hugging Face Hub.

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/hugging-face-jobs/SKILL.md

The canonical home for this skill is hugging-face-jobs in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

46%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with broad code coverage, but it is severely verbose and fails at progressive disclosure: it inlines content that should live in separate reference files while pointing to those files, which do not actually exist in the bundle.

Suggestions

Move the full Token Usage Guide, Hardware Selection detail, and Troubleshooting sections into the referenced files (references/token_usage.md, hardware_guide.md, troubleshooting.md) and actually ship those files, leaving only concise pointers and a quick-start inline.

De-duplicate token guidance, which currently appears in three places (Prerequisites, Token Usage Guide, Saving Results), into a single canonical section.

Replace placeholder script paths in examples (e.g. "script": "inference.py") with inline script strings or the documented Path(...).read_text() pattern to match the skill's own stated best practice and close the actionability gap.

Dimension	Reasoning	Score
Conciseness	At 1038 lines the body is noticeably verbose, with token usage covered redundantly across 'Prerequisites', 'Token Usage Guide', and 'Critical: Saving Results', plus basic explanations ('What are HF Tokens?', 'Token Types') that pad rather than inform.	2 / 5
Actionability	Provides extensive concrete, executable code for MCP, CLI, and Python API across most operations, but several examples use placeholder script paths ('my_script.py', 'inference.py') that the skill itself warns will fail via the hf_jobs() MCP tool.	4 / 5
Workflow Clarity	Prerequisites and verification checklists provide some validation checkpoints, but the core submission flow reads as a feature catalog rather than a sequenced validate->fix->retry loop, and the batch-operation guideline caps this at 3.	3 / 5
Progressive Disclosure	The body signals references to references/token_usage.md, hardware_guide.md, hub_saving.md, troubleshooting.md and scripts/*.py, but none of those files exist on disk, and the same content (full token guide, hardware table, troubleshooting) is inlined anyway, defeating progressive disclosure.	2 / 5
	Total	11 / 20 Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly communicates what the skill does and is reasonably distinct, but it lacks an explicit trigger clause and omits the most natural keyword ('Jobs'), leaving it in the mid-range across dimensions.

Suggestions

Add an explicit 'Use when...' trigger clause naming concrete scenarios (e.g., 'Use when running cloud GPU/TPU jobs, batch inference, or scheduled workloads without local setup').

Include the natural term 'Jobs' / 'HF Jobs' and common synonyms like 'cloud compute', 'batch inference', and 'model training' so the description matches what users actually say.

Tighten 'Run any workload' to a few specific actions to lift specificity from 3 toward 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain ('fully managed Hugging Face infrastructure', 'cloud CPUs, GPUs, or TPUs') and two concrete actions ('Run any workload', 'persist results to the Hugging Face Hub'), but coverage is not comprehensive enough for a 4.	3 / 5
Completeness	Clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Relevant keywords like 'Hugging Face', 'GPUs', 'TPUs', and 'Hugging Face Hub' are present, but common variations users would actually say ('Jobs', 'cloud compute', 'training/inference/batch') are missing.	3 / 5
Distinctiveness Conflict Risk	The Hugging Face managed-infrastructure niche is clearly distinct with minimal conflict risk, though the broad 'Run any workload' phrasing creates minor overlap with the related model-trainer skill.	4 / 5
	Total	13 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1039 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 13 missing	Warning

	Total	13 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/hugging-face-jobs/SKILL.md
Commit: 57c135b

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.