Torchscript Exporter - Auto-activating skill for ML Deployment. Triggers on: torchscript exporter, torchscript exporter Part of the ML Deployment skill category.
Install with Tessl CLI
npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill torchscript-exporterOverall
score
19%
Does it follow best practices?
Validation for skill structure
Activation
7%This description is severely underdeveloped, essentially just restating the skill name without explaining capabilities or usage triggers. It provides no actionable information for Claude to determine when to select this skill over others. The description reads as auto-generated boilerplate rather than a useful skill selector.
Suggestions
Add specific actions the skill performs, e.g., 'Converts PyTorch models to TorchScript format via tracing or scripting, optimizes for production inference, validates exported models'
Include a 'Use when...' clause with natural trigger terms like 'export pytorch model', 'torchscript', 'jit compile', 'deploy model', 'model serialization', '.pt file'
Remove the duplicate trigger term and expand with variations users would naturally say when needing this functionality
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only names the tool ('Torchscript Exporter') and category ('ML Deployment') without describing any concrete actions. No verbs or specific capabilities are listed. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond the name, and has no explicit 'Use when...' clause or equivalent guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | The trigger terms are just 'torchscript exporter' repeated twice - no natural variations users might say like 'export model', 'convert to torchscript', 'deploy pytorch model', or 'jit compile'. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'torchscript' is fairly specific to PyTorch model serialization, which provides some distinctiveness, but the lack of detail about what operations it performs could cause confusion with other ML deployment or model conversion skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
0%This skill content is a placeholder template with no actual technical substance. It contains zero actionable information about TorchScript exporting - no code examples, no API usage, no workflow steps, and no best practices. The entire content describes what the skill should do rather than actually doing it.
Suggestions
Add executable Python code showing torch.jit.trace() and torch.jit.script() usage with a concrete model example
Include a clear workflow: 1) Prepare model, 2) Choose trace vs script, 3) Export, 4) Validate exported model, 5) Test inference
Add specific guidance on common pitfalls (dynamic control flow, unsupported operations) and how to handle them
Replace meta-descriptions ('Provides step-by-step guidance') with actual technical content about TorchScript export patterns
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely boilerplate with no actual technical information about TorchScript exporting. It explains what the skill does in abstract terms without providing any concrete guidance, wasting tokens on meta-description. | 1 / 3 |
Actionability | No executable code, commands, or specific instructions are provided. The content only describes what the skill claims to do ('provides step-by-step guidance') without actually providing any guidance, code examples, or concrete steps for TorchScript export. | 1 / 3 |
Workflow Clarity | No workflow is defined. There are no steps, no sequence, and no validation checkpoints for exporting models to TorchScript format. The skill promises 'step-by-step guidance' but delivers none. | 1 / 3 |
Progressive Disclosure | The content is a flat, uninformative structure with no references to detailed documentation, examples, or related resources. It mentions 'Related Skills' but provides no actual links or navigation to useful content. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
69%Validation — 11 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 11 / 16 Passed | |
Reviewed
Table of Contents
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.