CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

matlab

Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

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

A well-engineered skill body: executable commands and concrete APIs throughout, a gated default workflow, and an exemplary one-level-deep reference structure with all cited paths verified to exist. The main costs are moderate token weight from version/date pinning and ancillary sections, and the lack of explicit error-recovery loops in the workflow.

Suggestions

Consolidate version and date pinning (R2026a/R2026b, Octave 11.3.0, review dates) into the existing 'Review scope' section and trim repeated baseline mentions elsewhere to tighten conciseness.

Add a short fix-and-retry guidance note for the workflow's validation gates (e.g., what to do when static inventory or manifest validation flags a risk) to reach top-tier workflow clarity.

Move the citation instructions to a reference file and keep a one-line pointer, reducing the main body's token budget.

DimensionReasoningScore

Conciseness

Dense, expert-level bullets assume MATLAB competence with no introductory padding, but trimmable material remains: the citation section, the 'no templates/ directory' contract note, and version/date pinning (R2026a/R2026b/Octave 11.3.0, reviewed 2026-10-01) scattered across sections rather than consolidated — efficient overall, just short of every-token-earns-its-place.

4 / 5

Actionability

Copy-paste-ready bash invocations for all seven bundled helpers with realistic arguments, a complete executable arguments-block MATLAB example, and specific API names (exportgraphics, lsqminnorm, codeIssues, matlab.codetools.requiredFilesAndProducts) covering the common cases.

5 / 5

Workflow Clarity

The seven-step Default workflow has a clear sequence and real validation gates (static inventory before any runtime load, dry-run scaffold default with --write refusing collisions, launch only after explicit approval), satisfying the destructive/batch validation requirement; however explicit fix-and-retry feedback loops are absent, so it sits below the top anchor.

4 / 5

Progressive Disclosure

An overview body where every section ends in a clearly signaled one-level-deep pointer ("Read [programming](references/programming.md)"), all eight referenced files plus three JSON assets and all helper scripts exist, and references contain no further nested links — easy navigation with appropriate content split.

5 / 5

Total

18

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with an explicit what-plus-when structure and natural trigger terms anchored by the distinctive MATLAB/Octave niche. The only gaps are missing file extensions and synonyms in the trigger list, which keep specificity and trigger coverage a step below comprehensive.

DimensionReasoningScore

Specificity

"Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows" names the domain and several actions with concrete artifacts ("tabular/time data", "MAT files", "graphics"), but the verbs remain broad and file extensions like .m/.mlx are not enumerated — several specific actions with minor coverage gaps.

4 / 5

Completeness

Explicitly answers both: what ("Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows") and when ("Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability") with concrete trigger phrases — an explicit 'Use for' clause is present, matching the top anchor.

5 / 5

Trigger Term Quality

Natural terms users would say are present (MATLAB, GNU Octave, arrays, MAT files, tests, projects, graphics, Python interoperability), but common synonyms and extensions (.m, .mlx, toolboxes) are missing, placing it just below the comprehensive-coverage-with-extensions anchor.

4 / 5

Distinctiveness Conflict Risk

"MATLAB or GNU Octave" pins a clear niche with minimal broad conflict, but generic tokens ("arrays", "tests", "projects") plus the Python-interop mention create minor overlap with general data-analysis or Python skills.

4 / 5

Total

17

/

20

Passed

Validation

100%

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

K-Dense-AI/scientific-agent-skills

Path

skills/matlab/SKILL.md

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.