Name: skill-tester
Rating: 72.8 (1 reviews)
Author: alirezarezvani

skill-tester

Validate, test, and score the quality of skills within the claude-skills ecosystem. Comprehensive meta-skill: structure validation, Python script testing (syntax + imports + runtime + output format), multi-dimensional quality scoring with letter grades and tier classification (BASIC/STANDARD/POWERFUL). Use when authoring a new skill, auditing existing skills for tier promotion, setting up pre-commit hooks for skill quality, or integrating skill QA into CI.

Quality

90%

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

The canonical home for this skill is skill-tester in alirezarezvani/claude-skills

Quality

Content

88%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 runnable commands, a clear validation-gated verification loop, and good sectioning. The main weakness is a dangling reference to a references/ directory that contains no actual files.

Suggestions

Either populate references/ with the structure spec, tier matrix, and scoring rubric the tools implement, or remove the closing 'References:' line so it does not point at a non-existent directory.

Consider trimming the advisory tier table and scope note into a single concise line, since both reiterate the write-a-skill exception for new skills.

Move the per-tool detail under 'What Each Tool Checks' into a short reference file if the body grows, keeping SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and purpose-driven with no padding about concepts Claude already knows, but the tier table and troubleshooting section carry minor instances that could be trimmed. Not a 5 because a few passages (advisory tier table, scope note) are slightly more than minimal; not a 3 because it is efficient overall and assumes Claude's competence.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands with exact repo-root paths in Quick Start and CI Integration, plus a concrete Verification Loop covering the common run/validate/score cases.	5 / 5
Workflow Clarity	The Verification Loop section gives a clear three-step sequence with explicit exit-0 validation checkpoints and a feedback loop ('If any step fails, apply the top improvement_roadmap item and re-run all three — never report a partial pass'), matching the validate-fix-retry anchor. No destructive/batch cap applies since validation is present.	5 / 5
Progressive Disclosure	Content is well-organized into clearly signaled sections (Quick Start, What Each Tool Checks, Tier Classification, CI Integration, Verification Loop, Troubleshooting), but the closing 'References: references/ holds...' line points to a directory with no actual bundle files — a dangling navigation reference. Not a 5 because of that broken pointer; not a 3 because the inline structure is solid.	4 / 5
	Total	18 / 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, third-person description that concretely names capabilities and provides explicit 'Use when' triggers covering authoring, auditing, pre-commit hooks, and CI integration. Minor room for improvement only in synonym/variation coverage of trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'structure validation, Python script testing (syntax + imports + runtime + output format), multi-dimensional quality scoring with letter grades and tier classification (BASIC/STANDARD/POWERFUL)' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (validate, test, and score skills) and 'when' ('Use when authoring a new skill, auditing existing skills for tier promotion, setting up pre-commit hooks for skill quality, or integrating skill QA into CI') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural triggers like 'authoring a new skill', 'auditing existing skills for tier promotion', 'pre-commit hooks', 'integrating skill QA into CI', but lacks synonyms or common variations for some terms. Not a 5 because coverage stops short of comprehensive synonym/file-extension breadth; not a 3 because several genuinely natural user phrases are present.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (skill QA/testing) with distinct triggers tied to authoring, auditing, and CI integration, making conflict with unrelated skills unlikely.	5 / 5
	Total	19 / 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
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/skill-tester/SKILL.md
Commit: 19392f7

Reviewed: ~16 hours 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.