edge-case-generator

Automatically identify potential boundary and exception cases from requirements, specifications, or existing code, and generate comprehensive test cases targeting boundary conditions, edge cases, and uncommon scenarios. Use this skill when analyzing programs, code repositories, functions, or APIs to discover and test corner cases, null handling, overflow conditions, empty inputs, concurrent access patterns, and other exceptional scenarios that are often missed in standard testing.

1.03x

Quality

72%

Does it follow best practices?

Impact

96%

1.03x

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/edge-case-generator/SKILL.md

Quality

Content

53%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 rich with concrete, multi-language test examples and a clear generation workflow, but it pays for it in verbosity — re-explaining basic edge-case concepts and triplicating the same enumeration across three sections. Workflow also lacks an explicit verification step.

Suggestions

Consolidate the redundant enumerations: the 'Core Capabilities', 'Edge Case Analysis Workflow', and 'Common Edge Case Checklist' sections repeat the same boundary/null/overflow/collection categories — keep one canonical list and drop the others.

Trim re-explanation of basic programming concepts (what boundary values, null, overflow, and empty collections are) that Claude already knows; retain the concrete test-code patterns which are the real value.

Add an explicit verification checkpoint to the workflow, e.g. a final step 'Run the generated tests; confirm they compile and that expected-failure cases fail for the stated reason.'

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: it re-explains basic concepts Claude already knows (boundary values, null, overflow, empty collections), and the 'Core Capabilities', 'Edge Case Analysis Workflow', and 'Common Edge Case Checklist' are three overlapping enumerations of the same ideas. Not a 1 because the concrete code examples do carry value.	2 / 5
Actionability	Concrete, executable test patterns across pytest, Jest, JUnit, C, and Go with real assertions covering common cases; not a 5 because the system-under-test functions (factorial, processArray, safe_strlen, binary_search) are undefined, so examples are not literally copy-paste runnable end-to-end.	4 / 5
Workflow Clarity	A clear 5-step sequence (input domains -> state -> outputs -> interactions -> generate tests) is present, but there is no verification checkpoint (e.g., 'run generated tests and confirm failure-mode tests fail for the expected reason'), leaving checkpoints implicit.	3 / 5
Progressive Disclosure	Four reference files (python/javascript/java/c_cpp_edge_cases.md) exist and are clearly signaled one level deep in the 'Language-Specific Patterns' section; not a 5 because the ~666-line body inlines a large volume of general methodology that could be trimmed or further externalized.	4 / 5
	Total	13 / 20 Passed

Description

91%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, well-constructed description that explicitly covers what the skill does and when to invoke it, with rich natural trigger terms and multiple synonyms for edge-case concepts. Minor overlap risk with general testing skills and a slightly compressed action list keep it just short of perfect.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('identify potential boundary and exception cases', 'generate comprehensive test cases targeting boundary conditions, edge cases, and uncommon scenarios') with enumerated sub-categories; not a 5 because the core 'what' reduces to two main actions (identify + generate) rather than an exhaustive set.	4 / 5
Completeness	Explicitly answers both 'what' (identify and generate test cases for boundary/edge/exception scenarios) and 'when' via a clear 'Use this skill when analyzing programs, code repositories, functions, or APIs...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage with synonyms a user would actually say: 'edge cases', 'boundary conditions', 'corner cases', 'uncommon/exceptional scenarios', plus concrete exception terms ('null handling', 'overflow conditions', 'empty inputs', 'concurrent access patterns').	5 / 5
Distinctiveness Conflict Risk	Clear niche (edge-case/boundary test generation) with distinctive triggers; not a 5 because it could overlap with a more general test-generation or testing skill.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (671 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: ArabelaTso/Skills-4-SE
Path: skills/edge-case-generator/SKILL.md
Commit: 4f38503

Reviewed: 8 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.