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

92%

Does it follow best practices?

Impact

82%

1.28x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Evaluation results

94%

14%

Generating a Test Suite for a User Authorization Module

Path analysis and constraint-based test suite generation

Criteria

Without context

With context

Uses path_analyzer module

70%

100%

Uses input_generator module

80%

100%

Calls analyze_code_paths

50%

100%

Calls generate_test_suite or generate_for_path

100%

paths_report.txt produced

100%

print_paths used for report

100%

test_suite.json produced

100%

test_suite.json has path metadata

100%

Edge cases included

100%

Inputs cover denied paths

100%

50%

Inputs cover tier paths

100%

3-step workflow order

71%

68%

27%

Maximizing Coverage of a Deeply Nested Discount Engine

Coverage-guided iterative generation with hybrid strategies

Criteria

Without context

With context

Iterative coverage loop

30%

Seed corpus initialization

62%

Coverage tracking set

37%

87%

Prioritizes deeply nested paths

10%

30%

Branch distance or mutation toward uncovered

60%

70%

Strategy switch on stall

coverage_log.txt produced

57%

71%

Coverage log records new-coverage decisions

71%

100%

test_corpus.json produced

100%

Corpus covers deeply nested path

100%

Uses path_analyzer tooling

100%

Inputs include edge cases

87%

100%

85%

13%

Building Semantically Meaningful Tests for a Medical Triage Classifier

LLM-driven semantic input generation with validation

Criteria

Without context

With context

Uses path_analyzer tooling

100%

LLM API called for generation

100%

LLM prompt includes function source

77%

100%

Constraint-based fallback

25%

Input validation performed

100%

test_suite.json produced

100%

generation_method field present

62%

50%

clinical_description field present

44%

66%

Covers immediate paths

100%

generation_report.txt produced

100%

Validation failures documented

75%

Semantically realistic inputs

100%

Repository: ArabelaTso/Skills-4-SE
Commit: 0f00a4f

Evaluated: 29 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Generating a Test Suite for a User Authorization Module Maximizing Coverage of a Deeply Nested Discount Engine Building Semantically Meaningful Tests for a Medical Triage Classifier

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.