fuzzing-input-generator

Generate randomized and edge-case inputs to detect unexpected failures, bugs, and security vulnerabilities through fuzz testing. Use when creating test cases for robustness testing, generating adversarial inputs, testing error handling, finding edge cases, or security testing. Produces Python test code with fuzzing inputs for strings, numbers, and structured data focusing on edge cases, invalid inputs, and random valid inputs. Triggers when users ask to generate fuzz tests, create randomized test inputs, test edge cases, find bugs through fuzzing, or generate adversarial test cases.

1.37x

Quality

85%

Does it follow best practices?

Impact

77%

1.37x

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.

Highly actionable with complete, executable examples and a clear workflow, but it carries notable redundancy: input patterns are repeated inline that already exist in the bundled reference. Trimming the duplicated inline patterns would tighten the skill and improve progressive disclosure.

Suggestions

Move the bulk of the Section 4 input-category lists (string/number/JSON) into references/fuzzing-patterns.md and keep only a small representative sample inline, eliminating the duplication between Sections 4 and 5.

Replace the 'Analyze the Target Function' question list with a brief directive plus the signature-extraction example, since Claude already knows how to inspect a function.

Add an explicit validation checkpoint (e.g., 'verify generated fuzz inputs are of the expected shape before running') before the batch run loop in Step 6 to strengthen the feedback loop for batch operations.

Dimension	Reasoning	Score
Conciseness	Mostly efficient executable code, but Sections 4 and 5 substantially duplicate the same string/number/JSON input patterns that also live in references/fuzzing-patterns.md, and the 'Analyze the Target Function' questions pad what Claude already infers.	3 / 5
Actionability	Provides copy-paste-ready, fully executable Python test functions (username, age, JSON API, divide, path traversal) that cover the common cases with concrete assertions.	5 / 5
Workflow Clarity	A clear seven-step sequence with an error-recovery feedback loop in Step 7 (find failure → regression test → fix → re-run) and run/coverage commands, with only minor validation gaps such as no explicit pre-run check that fuzz inputs themselves are well-formed.	4 / 5
Progressive Disclosure	A real reference file is clearly signaled via repeated links to references/fuzzing-patterns.md, but Sections 4–5 inline extensive input lists that duplicate that reference, so content that belongs in the separate file is inlined rather than split out.	3 / 5
	Total	15 / 20 Passed

Description

100%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-targeted description that concretely states capabilities and gives explicit, natural trigger guidance in third person. No material gaps or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—'Generate randomized and edge-case inputs to detect unexpected failures, bugs, and security vulnerabilities' and 'Produces Python test code with fuzzing inputs for strings, numbers, and structured data'—covering the domain comprehensively.	5 / 5
Completeness	Explicitly answers both what ('Generate randomized and edge-case inputs...Produces Python test code...') and when ('Use when...Triggers when...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural terms and synonyms are densely covered: 'fuzz tests', 'randomized test inputs', 'edge cases', 'adversarial inputs', 'error handling', 'security testing', and 'find bugs through fuzzing', matching how a user would phrase the request.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (fuzz-test input generation) with distinctive triggers unlikely to fire for unrelated skills.	5 / 5
	Total	20 / 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 (719 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: ArabelaTso/Skills-4-SE
Path: skills/fuzzing-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.