metamorphic-test-generator

Generates metamorphic tests — tests that check relationships between multiple runs instead of checking exact outputs, useful when the correct output is unknown or expensive to compute. Use when there's no oracle, when testing ML/numerical/search code, or when the spec describes properties rather than values.

Quality

92%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

100%

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

This is an excellent skill that efficiently teaches a sophisticated testing technique. It combines conceptual clarity (the ASCII diagram), practical reference material (the relation catalog), actionable heuristics (the 7 questions), and executable examples. The 'Do not' section adds important guardrails without being verbose.

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient, assuming Claude's competence. It jumps directly into the core concept with a clear diagram, provides a dense reference table, and avoids explaining basic concepts like what testing is or how property-based testing frameworks work.	3 / 3
Actionability	Provides fully executable Python code examples using Hypothesis, concrete worked examples for search engines and numerical code, and a comprehensive catalog of metamorphic relations with specific transforms. The code is copy-paste ready.	3 / 3
Workflow Clarity	The skill clearly sequences the process: understand the concept → identify relations using the 7-question checklist → implement tests → validate relation correctness. The 'Do not' section provides explicit validation guidance, and the output format ensures structured deliverables.	3 / 3
Progressive Disclosure	Content is well-organized with clear sections: core idea, relation catalog, discovery heuristics, worked examples, anti-patterns, and output format. For a skill of this scope (~100 lines), the single-file structure is appropriate with no need for external references.	3 / 3
	Total	12 / 12 Passed

Description

85%

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 strong skill description that clearly explains a specialized testing technique and provides explicit guidance on when to use it. The description excels at specificity and completeness with a clear 'Use when...' clause. Minor improvement could be made by adding more natural trigger terms users might use when they need this type of testing.

Suggestions

Add common alternative terms users might say, such as 'property-based testing', 'invariant testing', 'non-deterministic testing', or 'testing without expected outputs'

Dimension	Reasoning	Score
Specificity	Lists specific concrete actions: 'Generates metamorphic tests', 'tests that check relationships between multiple runs', and explains the technique clearly with 'instead of checking exact outputs'. Uses proper third person voice.	3 / 3
Completeness	Clearly answers both what ('Generates metamorphic tests — tests that check relationships between multiple runs') AND when ('Use when there's no oracle, when testing ML/numerical/search code, or when the spec describes properties rather than values') with explicit trigger guidance.	3 / 3
Trigger Term Quality	Includes some relevant terms like 'metamorphic tests', 'ML', 'numerical', 'search code', 'no oracle', and 'properties'. However, missing common variations users might say like 'property-based testing', 'invariant testing', or 'non-deterministic output testing'.	2 / 3
Distinctiveness Conflict Risk	Highly distinctive niche focusing specifically on metamorphic testing with clear differentiators: 'no oracle', 'relationships between multiple runs', 'properties rather than values'. Unlikely to conflict with general unit testing or other testing skills.	3 / 3
	Total	11 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: santosomar/general-secure-coding-agent-skills
Commit: 47d56bb

Reviewed: 4 months 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.