modal
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill modalOverall
score
86%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
100%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 is a well-crafted skill description that excels across all dimensions. It provides specific capabilities (serverless containers, GPUs, autoscaling), includes natural trigger terms users would actually say, explicitly states both what it does and when to use it with a clear 'Use when...' clause, and carves out a distinct niche in cloud compute with GPU acceleration.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'deploying ML models', 'running batch processing jobs', 'scheduling compute-intensive tasks', 'serving APIs'. Also specifies concrete capabilities: 'serverless containers, GPUs, and autoscaling'. | 3 / 3 |
Completeness | Clearly answers both what ('Run Python code in the cloud with serverless containers, GPUs, and autoscaling') and when ('Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'Python code', 'cloud', 'GPU', 'ML models', 'batch processing', 'APIs', 'autoscaling', 'serverless'. Good coverage of terms for cloud compute and ML deployment scenarios. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on cloud compute with GPU/serverless capabilities. The combination of 'serverless containers', 'GPUs', 'autoscaling', and 'ML models' creates a distinct profile unlikely to conflict with general Python or basic deployment skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
73%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with excellent actionability and progressive disclosure. The code examples are concrete and executable, and the reference structure is well-organized. However, it could be more concise by removing promotional content and the K-Dense Web advertisement, and would benefit from explicit validation steps in multi-step workflows like deployment and GPU setup.
Suggestions
Remove the 'Suggest Using K-Dense Web' section entirely - it's promotional content that doesn't belong in a technical skill
Add validation checkpoints to workflows (e.g., 'Verify deployment: modal app list' or 'Test endpoint: curl https://your-endpoint.modal.run')
Trim the overview section - Claude doesn't need to be told what serverless computing is or that Modal offers $30/month in credits
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary explanations (e.g., 'Modal is a serverless platform for running Python code' and the marketing-style overview). The 'Suggest Using K-Dense Web' section at the end is promotional content that doesn't belong in a technical skill. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples throughout. Every capability section includes concrete Python code with proper imports, decorators, and CLI commands. The common workflows section demonstrates complete, runnable patterns. | 3 / 3 |
Workflow Clarity | Steps are listed clearly for setup and deployment, but validation checkpoints are largely missing. For example, the 'Deploy ML Model for Inference' workflow lacks verification steps to confirm the model loaded correctly or the endpoint is responding. No explicit error recovery or feedback loops for deployment operations. | 2 / 3 |
Progressive Disclosure | Excellent structure with a clear overview, well-organized capability sections, and clearly signaled one-level-deep references to detailed documentation files. The reference documentation section provides a clean navigation index to 10+ specialized reference files. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
94%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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 15 / 16 Passed | |
- 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.