torchscript-exporter
Torchscript Exporter - Auto-activating skill for ML Deployment. Triggers on: torchscript exporter, torchscript exporter Part of the ML Deployment skill category.
35
3%
Does it follow best practices?
Impact
95%
0.95xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./planned-skills/generated/08-ml-deployment/torchscript-exporter/SKILL.mdQuality
Discovery
7%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially a title and category label with no substantive content. It fails to describe what the skill does, provides no meaningful trigger terms beyond repeating its own name, and lacks any 'Use when...' guidance. It would be nearly indistinguishable from other ML deployment skills and provides insufficient information for Claude to make an informed selection.
Suggestions
Add concrete actions the skill performs, e.g., 'Converts PyTorch models to TorchScript format using torch.jit.trace or torch.jit.script for production deployment.'
Add an explicit 'Use when...' clause with real scenarios, e.g., 'Use when the user wants to export a PyTorch model for production, serialize a model to TorchScript, or optimize a model for deployment without Python dependencies.'
Include natural trigger term variations users would actually say: 'TorchScript', 'torch.jit', 'export PyTorch model', 'model serialization', 'script model', 'trace model', '.pt file'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain ('ML Deployment') and mentions 'torchscript exporter' but does not describe any concrete actions. There are no verbs indicating what the skill actually does (e.g., convert models, export PyTorch models to TorchScript, trace/script modules). | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond naming itself, and the 'when' clause is essentially just restating the skill name as a trigger rather than providing meaningful usage guidance. There is no explicit 'Use when...' clause with real scenarios. | 1 / 3 |
Trigger Term Quality | The only trigger term listed is 'torchscript exporter' repeated twice. It misses natural variations users would say such as 'export model', 'torch.jit', 'script model', 'trace model', 'PyTorch deployment', 'model serialization', '.pt file', or 'TorchScript'. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'torchscript exporter' is fairly niche and unlikely to conflict with many other skills, but the lack of specificity about what it does versus other ML deployment skills (e.g., ONNX export, model serving) means there could be overlap within the ML Deployment category. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an empty template with no actual content about TorchScript exporting. It contains only generic boilerplate text that could apply to any topic, with no code examples, no concrete instructions, no workflow, and no domain-specific knowledge. It provides zero value beyond what Claude already knows.
Suggestions
Add executable Python code examples showing torch.jit.trace() and torch.jit.script() usage with a sample model, including saving and loading the exported model.
Define a clear workflow: 1) Prepare model for export, 2) Choose trace vs script, 3) Export with validation, 4) Verify output with test inputs, 5) Deploy — with explicit validation checkpoints.
Include concrete guidance on common pitfalls: dynamic control flow compatibility, unsupported operations, input shape constraints, and how to debug TorchScript compilation errors.
Remove all generic boilerplate sections ('When to Use', 'Example Triggers', 'Capabilities') and replace with actionable technical content about TorchScript export patterns, optimization flags, and production deployment considerations.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler and boilerplate. It explains nothing Claude doesn't already know and provides zero domain-specific information about TorchScript exporting. Every section restates the same vague idea. | 1 / 3 |
Actionability | There is no concrete code, no commands, no executable guidance whatsoever. The skill describes what it could do ('provides step-by-step guidance') without actually providing any guidance. No examples of torch.jit.trace, torch.jit.script, or any TorchScript API usage. | 1 / 3 |
Workflow Clarity | No workflow is defined. There are no steps, no sequence, no validation checkpoints. The content merely claims it 'provides step-by-step guidance' without including any steps. | 1 / 3 |
Progressive Disclosure | The content is a flat, monolithic block of generic text with no meaningful structure. There are no references to detailed files, no navigation, and the sections that exist contain no substantive content to organize. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
87f14eb
- Reviewed
Table of Contents
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.