transformers

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

Quality

83%

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

Quality

Content

78%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.

Well-structured, actionable content that uses progressive disclosure effectively with real reference files and a credential validation checkpoint. Main gaps are minor redundancy between sections and placeholder identifiers in a couple of examples.

Suggestions

Replace placeholder 'model-id'/'task-name' strings in Pattern 1 and capability stubs with concrete examples to reach fully copy-paste-ready actionability.

Trim the redundant task-list repetition between Quick Start, Core Capabilities, and Common Patterns to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient with no over-explanation of concepts Claude already knows, but the Core Capabilities task list and Common Patterns repeat material already shown in Quick Start, leaving minor trim opportunities.	4 / 5
Actionability	Mostly executable, copy-paste-ready code in Quick Start and Patterns 2–3 (real model 'gpt2', AutoModel + Trainer examples), but Pattern 1 and some capability stubs use placeholder 'model-id'/'task-name' strings, a minor gap.	4 / 5
Workflow Clarity	There is a clear credential-validation checkpoint ('[ -n "$HF_TOKEN" ] && echo ... \|\| echo "NOT SET"' with remediation guidance) and a loose install→credentials→inference sequence, though the overall workflow is reference-style rather than a tightly sequenced multi-step process.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview with one-level-deep, well-signaled references to five real bundle files (pipelines.md, models.md, generation.md, training.md, tokenizers.md), each linked inline and summarized in a Reference Documentation section.	5 / 5
	Total	17 / 20 Passed

Description

88%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 description that clearly states what the skill does and when to use it, with comprehensive concrete action coverage across modalities. Minor improvements would add a few more natural synonyms and sharpen distinction from generic deep-learning skills.

Suggestions

Add a few common natural terms users say (e.g., 'chat', 'embeddings', 'inference') to broaden trigger_term_quality.

Tie the trigger more tightly to the Hugging Face ecosystem to reduce overlap with generic deep-learning/PyTorch skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across modalities — 'text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning' — giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' (pre-trained transformer models for NLP/CV/audio/multimodal tasks) and 'when' ('This skill should be used when working with pre-trained transformer models...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural task names users would say are well covered (classification, question answering, summarization, translation, object detection), but a few common synonyms/terms like 'chat', 'embeddings', or 'inference' are missing, so it stops short of fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	The 'pre-trained transformer models' niche is mostly distinct with clear triggers, but there is minor overlap risk with broader deep-learning or PyTorch-focused skills.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/llm-tools/transformers/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day 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.