testing-validator

Comprehensive testing validation for Claude Code skills through functional testing, example validation, integration testing, regression testing, and edge case testing. Task-based testing operations with automated example execution, manual scenario testing, and test reporting. Use when testing skill functionality, validating examples execute correctly, ensuring integration works, preventing regressions, or conducting comprehensive functional quality assurance.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/testing-validator/SKILL.md

Quality

Content

48%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 content is well-sequenced with checklists and clear per-operation workflows, but it is heavily padded with concepts Claude already knows and illustrative output blocks, and it relies on reference and script files that are not actually bundled. Tightening the body and providing the referenced files would substantially improve it.

Suggestions

Cut the per-operation 'Example' output blocks and the conceptual explanations of what functional/integration/regression/edge-case testing are; Claude already knows these — keep only the concrete process steps, checklists, and pass criteria.

Either create the referenced references/*.md guide files and scripts/*.py scripts, or remove the 'For More Information' and 'Automation Scripts' sections that point to them, so navigation does not lead to dead links.

Move the detailed per-operation guidance into the corresponding reference files and keep SKILL.md as a concise overview pointing one level deep, reducing the body from ~825 lines toward a lean overview.

Dimension	Reasoning	Score
Conciseness	At ~825 lines the body is noticeably verbose, re-explaining concepts Claude already knows (the nature of functional, integration, regression, and edge-case testing) and padding each operation with 100+ line illustrative example-output blocks that earn little per token.	2 / 5
Actionability	Some concrete guidance exists (e.g. 'python3 scripts/validate-examples.py /path/to/skill' and report formats/checklists), but most operations are abstract methodology steps and the referenced scripts do not exist, leaving execution incomplete.	3 / 5
Workflow Clarity	Each operation has a clearly numbered 5-step process with a validation checklist and PASS/PARTIAL/FAIL criteria, though explicit validate→fix→retry feedback loops are only weakly present outside Operation 4.	4 / 5
Progressive Disclosure	Section structure and a 'For More Information' navigation block are present, but the per-operation detail and giant examples are inlined rather than split into the referenced files, and all six referenced references/.md and three scripts/.py files do not exist.	3 / 5
	Total	12 / 20 Passed

Description

88%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-structured description that clearly states both the skill's purpose and explicit trigger conditions with concrete operations. The only weakness is slightly repetitive trigger phrasing that reuses the operation list rather than adding richer natural synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete testing operations — 'functional testing, example validation, integration testing, regression testing, and edge case testing' plus 'automated example execution, manual scenario testing, and test reporting' — giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both what ('Comprehensive testing validation ... through functional testing, example validation ...') and when ('Use when testing skill functionality, validating examples execute correctly ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases like 'testing skill functionality, validating examples execute correctly, ensuring integration works, preventing regressions' are things users would say, but coverage leans on synonyms of the operation list and offers few distinct natural variations or file extensions.	4 / 5
Distinctiveness Conflict Risk	The skill has a clear niche (functional validation of Claude Code skills) with distinct triggers, but broad phrases like 'comprehensive functional quality assurance' and generic 'testing' create minor overlap risk with related QA/testing skills.	4 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (832 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
referenced_paths_exist	Referenced path issues: 14 missing	Warning

	Total	13 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/testing-validator/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.