directed-test-input-generator

Generate targeted test inputs to reach specific code paths and hard-to-reach behaviors in Python code. Use when: (1) Targeting uncovered branches or specific execution paths, (2) Need coverage-guided test generation, (3) Want to leverage LLM understanding of code semantics for meaningful test inputs, (4) Testing boundary conditions and edge cases systematically, (5) Combining symbolic reasoning with fuzzing. Provides path analysis, constraint solving, coverage-guided strategies, and LLM-driven semantic generation for comprehensive test input creation.

1.28x

Quality

81%

Does it follow best practices?

Impact

82%

1.28x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

71%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-structured, actionable skill body with real executable examples and clean progressive disclosure. Main weakness is content redundancy across overlapping sections and reliance on a few undefined helper functions in examples.

Suggestions

Consolidate the overlapping 'Common Use Cases' and 'Advanced Strategies' sections with 'Core Techniques' to remove duplicated coverage-guided and boundary-testing examples.

Replace or implement the fictional helpers (execute_with_coverage, mutate_toward_uncovered, query_llm_for_realistic_inputs) referenced in examples, or mark those snippets as illustrative pseudocode.

Merge the 'Quick Start' workflow and the 'Example Workflow' under 'Tools Reference' into a single canonical end-to-end example to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	Largely code-driven with no basic-concept padding, but substantial redundancy across 'Core Techniques', 'Common Use Cases', and 'Advanced Strategies' (e.g., Use Case 3 duplicates Section 4, and there are two near-identical workflow intros) that could be tightened.	3 / 5
Actionability	Provides copy-paste-ready imports that match real bundle exports (analyze_code_paths, TestInputGenerator, EdgeCaseGenerator), but several examples invoke fictional helpers (execute_with_coverage, mutate_toward_uncovered, query_llm_for_realistic_inputs) not present in the bundle.	4 / 5
Workflow Clarity	A clear 3-step Quick Start (analyze, generate, execute & verify coverage) with an explicit verification checkpoint and iterative refinement use cases; minor gaps in formal validation steps.	4 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references to real files (coverage_strategies.md, llm_patterns.md) and bulleted navigation of their contents; bulk detail appropriately split into reference files.	5 / 5
	Total	16 / 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, specific description that clearly states capabilities and provides an explicit numbered trigger list. Third-person voice is maintained throughout with no over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Generate targeted test inputs to reach specific code paths', 'path analysis, constraint solving, coverage-guided strategies, and LLM-driven semantic generation') with comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both what ('Generate targeted test inputs...') and when with a concrete numbered 'Use when: (1)...(5)...' trigger list.	5 / 5
Trigger Term Quality	Good keyword coverage ('test inputs', 'coverage', 'boundary conditions', 'edge cases', 'fuzzing') that developers would naturally say, though a few natural synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (directed, path-coverage-guided test input generation in Python) with distinct triggers and minimal overlap risk with general testing 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/directed-test-input-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.