metamorphic-test-generator

Generate test cases using metamorphic testing by applying transformations based on metamorphic properties. Use when you need to expand test suites, test programs without oracles, validate mathematical or algorithmic properties, or detect subtle bugs through input-output relationships. The skill takes a program, original test cases, and metamorphic properties as input, generates new test cases by applying transformations, executes tests, verifies outputs satisfy properties, reports violations and anomalies, and outputs an expanded test suite with property coverage summary. Supports multiple programming languages and property types.

1.57x

Quality

78%

Does it follow best practices?

Impact

88%

1.57x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/metamorphic-test-generator/SKILL.md

Quality

Content

65%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.

The body is reasonably actionable and concise with executable commands, but it lacks an explicit workflow with validation checkpoints for batch generation and fails to link to the bundled references and templates that exist alongside it.

Suggestions

Add a numbered workflow with a validation checkpoint, e.g. run generate.py -> execute generated tests -> verify property_coverage and review violations -> iterate on properties, so the batch process has an explicit feedback loop.

Link the existing bundle files from the body: point the 'Common Metamorphic Properties' section to references/properties.md and reference assets/properties-template.json and assets/test-cases-template.json for getting started.

Trim redundancy by collapsing the duplicated command shape across Quick Start and Usage, and remove the Overview restatement of the frontmatter description.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands and no concept-explaining fluff, but the Overview restates the description and the 'What Gets Generated'/'Quick Start'/'Usage' sections repeat the same command shape, leaving minor padding to trim.	4 / 5
Actionability	Provides executable CLI commands, a usage signature, and a concrete JSON report example, but stops short of fully copy-paste-ready coverage showing actual generated test output or wiring the bundled example program into a worked example.	4 / 5
Workflow Clarity	Lists generated outputs and quick-start commands but offers no sequenced multi-step workflow with validation/verification checkpoints for the batch generation operation; the missing run-then-verify-then-iterate feedback loop caps this at 3.	3 / 5
Progressive Disclosure	Sections are organized and references the real scripts/generate.py, but it never signals the existing references/properties.md or asset templates and inlines a property list that duplicates what belongs in those files.	3 / 5
	Total	14 / 20 Passed

Description

92%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 that explicitly covers both what the skill does and when to use it, with concrete pipeline actions and a well-scoped niche. Minor gap is the absence of common synonyms and file extensions in the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full pipeline (generate, execute, verify, report, output expanded suite) with comprehensive coverage, matching the anchor for several specific concrete actions.	5 / 5
Completeness	Clearly states what the skill does and provides an explicit 'Use when...' trigger clause with concrete scenarios, satisfying both the what and when requirements.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('expand test suites', 'test programs without oracles', 'detect subtle bugs') but lacks common synonyms such as 'property-based testing' or 'mutation testing' and any file extensions.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche ('metamorphic testing', 'programs without oracles', 'input-output relationships') with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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: ArabelaTso/Skills-4-SE
Path: skills/metamorphic-test-generator/SKILL.md
Commit: 4f38503

Reviewed: 19 days ago

Table of Contents

Discovery Implementation Validation

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.