test-automator

Master AI-powered test automation with modern frameworks, self-healing tests, and comprehensive quality engineering. Build scalable testing strategies with advanced CI/CD integration. Use PROACTIVELY for testing automation or quality assurance.

Quality

36%

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/test-automator/SKILL.md

Quality

Content

10%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 body is a persona dump rather than an actionable skill: long buzzword lists of capabilities and knowledge Claude already possesses, with no code, commands, or validation steps. It needs to be drastically shortened and rebuilt around concrete, executable guidance.

Suggestions

Replace the capability/knowledge/behavioral enumerations with a few concrete, copy-paste-ready examples (e.g., a Playwright test snippet, a CI/CD parallel-test config, a self-healing locator pattern).

Cut content that restates what Claude already knows (TDD red-green-refactor, framework tool lists) and keep only skill-specific decisions, gotchas, and recipes.

Add explicit validation/feedback-loop steps to the 'Response Approach' (e.g., run the suite, check for flaky tests, re-run on failure) and move large reference material into separate files in references/.

Dimension	Reasoning	Score
Conciseness	The 200+ line body is a wall of enumerated capabilities, behavioral traits, and a knowledge base that extensively restates concepts Claude already knows (TDD cycles, Playwright/Selenium, CI/CD tools), adding heavy padding rather than skill-specific knowledge.	1 / 5
Actionability	No concrete code, commands, or executable guidance anywhere; it only describes ('Clarify goals', 'Apply relevant best practices and validate outcomes') rather than instructing, matching the 'entirely vague or abstract' anchor.	1 / 5
Workflow Clarity	The 'Response Approach' gives a rough numbered sequence but steps are abstract ('Analyze testing requirements', 'Design comprehensive test strategy') with no validation checkpoints or feedback loops, fitting just above the incoherent anchor.	2 / 5
Progressive Disclosure	Despite section headers, the skill is a monolithic single file with no bundle files; the large capability and knowledge enumerations clearly belong in separate reference files or should be cut, so structure is minimal.	2 / 5
	Total	6 / 20 Passed

Description

62%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.

The description covers both what the skill does and when to use it with a distinct test-automation niche, but leans on buzzwords ('Master', 'comprehensive', 'advanced') and offers only generic trigger terms. Tightening the language and adding concrete trigger synonyms would raise it.

Suggestions

Replace buzzwords ('Master', 'comprehensive quality engineering', 'advanced CI/CD') with concrete actions like 'generate self-healing UI tests, orchestrate parallel test suites in CI'.

Expand the 'Use when' clause with natural trigger phrases users actually say: 'QA', 'automated testing', 'test framework setup', 'flaky tests'.

Drop the 'Use PROACTIVELY' phrasing in favor of explicit 'Use when...' trigger conditions tied to user requests.

Dimension	Reasoning	Score
Specificity	Names the domain and several actions ('self-healing tests', 'Build scalable testing strategies', 'CI/CD integration'), but they remain abstract and buzzword-laden ('Master', 'comprehensive quality engineering', 'advanced'), so not a clear 4.	3 / 5
Completeness	Both 'what' (test automation, self-healing tests, CI/CD integration) and 'when' ('Use PROACTIVELY for testing automation or quality assurance') are present, though the 'when' is generic and could be more specific, so not a 5.	4 / 5
Trigger Term Quality	Includes relevant triggers ('testing automation', 'quality assurance') but misses common natural synonyms users say like 'QA', 'automated testing', 'test framework', or 'test suite'.	3 / 5
Distinctiveness Conflict Risk	The test-automation framing is a fairly distinct niche with minimal conflict risk, though the broad 'quality assurance' phrasing leaves minor overlap with general engineering skills, keeping it below 5.	4 / 5
	Total	14 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/test-automator/SKILL.md
Commit: 3eff4af

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.