transformers

Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks. Use when working with AutoModel, pipelines, tokenizers, or TrainingArguments—not for general ML outside the Transformers library.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/transformers/SKILL.md

Quality

Content

65%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.

A well-structured, code-forward skill body with excellent progressive disclosure via real reference files. It loses points for time-sensitive inline dating, placeholder code in the patterns section, and the absence of explicit validation checkpoints in its workflows.

Suggestions

Move the 'June 2026' date and exact version pins into a dedicated compatibility/deprecated section so the time-sensitive info does not bloat the main install guidance.

Replace the 'task-name'/'model-id' placeholders in Common Patterns with concrete, runnable examples (e.g. a real model id) so every code block is copy-paste executable.

Add an explicit verify/check step after installation (e.g. checking transformers.__version__ and a one-line auth check) to give the install→auth→infer flow a validation checkpoint.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with code-forward sections, but the time-sensitive 'June 2026' date and inline version pins, plus mild padding (the Overview sentence and repeated 'When to use' lines Claude could infer), keep it at the mostly-efficient-but-could-be-tightened anchor rather than 4.	3 / 5
Actionability	Quick Start and Authentication give copy-paste-ready, executable code with concrete model IDs, but Common Patterns 1 and 2 lean on 'task-name'/'model-id' placeholders that are not runnable as written, the minor-gaps anchor at 4.	4 / 5
Workflow Clarity	A clear install→authenticate→infer sequence is present, but there are no explicit validation checkpoints or feedback loops; since the skill is not a destructive/batch workflow the cap does not apply, landing it on the steps-present-but-checkpoints-implicit anchor.	3 / 5
Progressive Disclosure	The body is a concise overview with well-signaled, one-level-deep references ('See references/pipelines.md for...') to five real files that exist in the bundle, matching the clear-overview-with-one-level-deep-references anchor.	5 / 5
	Total	15 / 20 Passed

Description

92%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.

A strong, specific description that names concrete capabilities, includes concrete trigger terms, and explicitly bounds when to use it (and when not to). The only minor gap is a few missing synonym trigger terms like Trainer and from_pretrained.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—'loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning'—across NLP, vision, audio, and multimodal tasks, matching the comprehensive-coverage anchor; no concrete action is missing for the library's core surface.	5 / 5
Completeness	Explicitly states both what it does (loading/inference/generation/fine-tuning) and when to use it ('Use when working with AutoModel, pipelines, tokenizers, or TrainingArguments'), plus a negative boundary, hitting the explicit what-and-when anchor.	5 / 5
Trigger Term Quality	Names natural API terms users actually say—'AutoModel, pipelines, tokenizers, or TrainingArguments'—but a few common variants (Trainer, from_pretrained) are absent, placing it just below the comprehensive-synonym anchor at 5.	4 / 5
Distinctiveness Conflict Risk	Scoped narrowly to the Transformers library and explicitly excludes 'general ML outside the Transformers library', giving it a clear niche with minimal overlap risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/transformers/SKILL.md
Commit: b2a92ba

Reviewed: 3 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.