pytorch-lightning

Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.

Quality

70%

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 ./bundled/skills/pytorch-lightning/SKILL.md

Quality

Content

72%Weight 40%Scale 1-3

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

The body is well-structured with executable code and excellent progressive disclosure to verified reference/script files, but it restates some known concepts and lacks explicit validation checkpoints in its main workflow.

Suggestions

Trim the Overview paragraph to avoid restating the framework's purpose and the frontmatter description; assume Claude knows what PyTorch Lightning is.

Add an explicit validation/checkpoint step to the Quick Workflow, e.g. run `Trainer(fast_dev_run=True)` or a sanity check before `trainer.fit(...)` to catch errors early.

Move any further concept-level explanation out of SKILL.md into the relevant references/ files to keep the overview lean.

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient with lean lists per capability, but the Overview paragraph restates the description and explains known framework concepts ('organizes PyTorch code to eliminate boilerplate'), so it could be tightened — matching the score-2 anchor rather than the fully lean score-3 anchor.	2 / 3
Actionability	It provides fully executable, copy-paste-ready code (a complete LightningModule, Trainer config, DataLoader usage) plus concrete method signatures and real template/reference files, matching the score-3 anchor.	3 / 3
Workflow Clarity	The 'Quick Workflow' gives a clear three-step sequence but includes no explicit validation/verification checkpoints (e.g. sanity-check or fast_dev_run before fit), so per the rubric's destructive/batch-operation cap it sits at the score-2 anchor rather than score 3.	2 / 3
Progressive Disclosure	The body is a concise overview with well-signaled one-level-deep references to real bundle files (verified: all three scripts/ and all seven references/ files exist) and a Resources index, matching the clear-overview anchor.	3 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 is specific and distinctive, listing concrete Lightning capabilities, but it lacks an explicit 'Use when...' trigger clause and leans on component jargon over natural user phrasings.

Suggestions

Add an explicit 'Use when...' clause listing natural user triggers, e.g. 'Use when training or scaling neural networks with PyTorch Lightning, configuring multi-GPU/TPU training, or setting up DDP/FSDP/DeepSpeed.'

Include common natural phrasings a user would actually say ('train a model', 'scale training across GPUs', 'set up distributed training') alongside the component names.

Lead with the highest-intent trigger terms before the detailed capability list so the skill surfaces on natural requests.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging ... distributed training (DDP, FSDP, DeepSpeed)'), matching the comprehensive-action anchor rather than the partial score-2 anchor.	3 / 3
Completeness	It clearly answers 'what' but has no 'Use when...' clause or equivalent explicit trigger guidance; per the rubric guideline a missing 'Use when' clause caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant domain terms are present ('PyTorch Lightning', 'LightningModules', 'Trainers', 'DDP, FSDP, DeepSpeed') but they lean toward component jargon and miss common natural user phrasings ('train a model', 'neural network training'), fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	It names a clear niche ('Deep learning framework (PyTorch Lightning)' with LightningModules, DDP, FSDP, DeepSpeed) making it unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 12 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/pytorch-lightning/SKILL.md
Commit: f627ab5

Reviewed: 10 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.