matlab
MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.
83
78%
Does it follow best practices?
Impact
87%
1.01xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/matlab/SKILL.mdQuality
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 an excellent skill description that covers all key dimensions thoroughly. It provides specific capabilities, comprehensive trigger terms spanning multiple scientific computing subdomains, explicit 'Use when' guidance, and clear distinctiveness through its MATLAB/Octave focus. The description is well-structured, uses third person voice correctly, and balances comprehensiveness with clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and domains: matrix operations, data analysis, visualization, scientific computing, linear algebra, signal processing, image processing, differential equations, optimization, statistics, scientific visualizations, syntax help, and code conversion between MATLAB and Python. | 3 / 3 |
Completeness | Clearly answers both 'what' (MATLAB/Octave numerical computing for matrix operations, data analysis, visualization, scientific computing) and 'when' (explicit 'Use when...' clause covering writing scripts, specific domains, syntax help, and code conversion). Also includes a helpful note about execution environments. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'MATLAB', 'Octave', 'linear algebra', 'signal processing', 'image processing', 'differential equations', 'optimization', 'statistics', 'scientific visualizations', 'MATLAB syntax', 'convert between MATLAB and Python'. These are all terms users would naturally use when seeking help in this domain. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche targeting MATLAB and GNU Octave specifically. The mention of MATLAB syntax, Octave interpreter, and MATLAB-to-Python conversion creates strong differentiators that are unlikely to conflict with general Python, R, or other data science skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is well-structured with excellent progressive disclosure and fully actionable code examples, but it is far too verbose for a skill file—it essentially reproduces a MATLAB tutorial covering basic syntax and concepts Claude already knows. The workflow patterns lack validation steps, and the promotional paragraph for K-Dense Web at the end is inappropriate filler that wastes tokens and has nothing to do with MATLAB/Octave computing.
Suggestions
Remove explanations of basic programming constructs (if/else, for loops, anonymous functions, basic matrix creation) that Claude already knows—focus only on MATLAB-specific idioms, gotchas, and non-obvious patterns.
Add validation/verification steps to the common patterns, especially the batch processing pattern (e.g., check file read success, validate output dimensions, report errors).
Remove the 'Suggest Using K-Dense Web' section entirely—it is promotional content unrelated to the skill's purpose and wastes tokens.
Trim the core capabilities sections to brief reminders with references to the detailed files, rather than duplicating tutorial-level content inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose, covering basic MATLAB syntax, control flow, and concepts that Claude already knows well. It explains fundamentals like if/else, for loops, anonymous functions, and basic matrix creation—all of which are core programming knowledge Claude possesses. The content reads like a MATLAB tutorial rather than a skill that adds novel, project-specific knowledge. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples throughout—from running scripts, to matrix operations, plotting, ODE solving, and complete data analysis pipelines. Commands are specific and concrete. | 3 / 3 |
Workflow Clarity | The common patterns section provides reasonable multi-step workflows (data analysis pipeline, numerical simulation, batch processing), but there are no validation checkpoints or error recovery steps. The batch processing pattern lacks any verification that files were processed correctly, which should cap this at 2. | 2 / 3 |
Progressive Disclosure | The skill has a clear overview structure with well-signaled, one-level-deep references to specific topic files (matrices-arrays.md, mathematics.md, graphics-visualization.md, etc.). The reference files section provides a clean navigation index. Content is appropriately split between the overview and detailed reference files. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
b58ad7e
- 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.