Name: pytorch-patterns
Rating: 59.2 (1 reviews)
Author: affaan-m

pytorch-patterns

PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.

Quality

69%

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 ./.kiro/skills/pytorch-patterns/SKILL.md

The canonical home for this skill is pytorch-patterns in affaan-m/ECC

Quality

Content

72%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 body is highly actionable with comprehensive executable code and clean organization, but it is a monolithic reference catalog with no progressive disclosure to separate files and no sequenced workflow with validation checkpoints. Splitting detailed sections into reference files would improve navigation.

Suggestions

Move detailed code-pattern sections (e.g., training-loop variants, full architecture examples) into one-level-deep reference files with clear links from SKILL.md to improve progressive disclosure.

Add a brief sequenced workflow with validation checkpoints for at least one common flow (e.g., build model -> train -> checkpoint -> evaluate) to raise workflow clarity.

Trim the paired Good/Bad commentary and closing 'Remember' summary where the code alone conveys the point, to tighten conciseness toward a 5.

Dimension	Reasoning	Score
Conciseness	Largely code-driven with terse intros and minimal re-explanation of concepts Claude already knows, though the paired Good/Bad examples and closing 'Remember' summary add some length that could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready code covers the common PyTorch cases (device setup, seeding, training/validation loops, DataLoader config, checkpointing, AMP, torch.compile) plus a concise idioms table.	5 / 5
Workflow Clarity	Content is a well-organized patterns catalog rather than a sequenced multi-step workflow, so there are no explicit validation checkpoints or feedback loops; organization is clear but no sequenced process is present.	3 / 5
Progressive Disclosure	The body has clear section structure but is a single ~390-line monolithic SKILL.md with no bundle files and no one-level-deep references, so content that could be split remains inline.	3 / 5
	Total	15 / 20 Passed

Description

66%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 conveys the skill's PyTorch/deep-learning focus and concrete capability areas, but it omits any explicit 'when to use' trigger guidance. Adding a 'Use when...' clause with natural trigger phrases would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases (e.g., 'Use when writing PyTorch training scripts, building nn.Module architectures, or debugging data loading pipelines').

Include natural synonyms and extensions users might say, such as 'neural networks', 'GPU/CUDA', 'tensors', or '.pt checkpoints', to broaden trigger-term coverage.

Replace generic verbs like 'building' with more distinct concrete actions to push specificity toward a 5.

Dimension	Reasoning	Score
Specificity	Names the PyTorch/deep-learning domain plus several concrete capability areas (training pipelines, model architectures, data loading), though the action verbs remain generic ('building', 'patterns and best practices') rather than distinct concrete actions.	4 / 5
Completeness	The 'what' is clearly answered, but there is no 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('PyTorch', 'deep learning', 'training pipelines', 'model architectures', 'data loading') but misses common synonyms and extensions like 'neural network', 'GPU', 'CUDA', or '.pt' files.	4 / 5
Distinctiveness Conflict Risk	The PyTorch-specific deep-learning niche is clearly distinguishable with minimal conflict risk, though 'training pipelines' could overlap slightly with general ML tooling skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: .kiro/skills/pytorch-patterns/SKILL.md
Commit: d8409a4

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.