qa-testing

Run QA testing on a page, feature, or full site at one of three depth tiers (smoke, standard, full). Use this skill whenever the user asks to test a page, audit a site, check for bugs, verify a deploy, run a QA sweep, or review accessibility, performance, or SEO basics. Triggers on test, QA, audit, verify, check, is it working, does it look right, broken, 404, image not loading, post-deploy check, regression test. Also triggers proactively after any significant code change or new page launch where verification matters.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable content with executable snippets, explicit validation gates, and clean one-level-deep progressive disclosure. The main weakness is redundancy between the inline full-release matrix and the bundled report template, which costs tokens.

Suggestions

Remove the duplicated release-matrix table from the body and point to the template's checklist instead, keeping only the numeric thresholds inline, to eliminate the conciseness redundancy.

The contrast snippet only runs hardcoded example colors; consider noting how to feed actual computed element colors so the snippet is directly usable on a real page.

Dimension	Reasoning	Score
Conciseness	The body is lean per section (executable snippets, threshold tables, failure heuristics — no explaining of concepts Claude already knows), but the 'Full release matrix' table substantially duplicates the checklist in references/qa-report-template.md, which is verbosity the rubric penalizes; this places it at level-2 'mostly efficient but could be tightened' rather than level-3 where every token earns its place.	2 / 3
Actionability	Provides fully executable, copy-paste-ready console snippets (smoke, standard audit, headers fetch, image/heading/contrast/form/link audits) with specific numeric pass criteria (e.g. 'LCP under 2.5s', 'Meta description: 120 to 160 characters'), matching the level-3 anchor of fully executable code with copy-paste-ready examples; not level 2 because there is no pseudocode or missing key detail.	3 / 3
Workflow Clarity	The six-step Workflow is clearly sequenced and includes an explicit validation gate — 'If any of these fail, do not proceed with deeper testing until the smoke issue is fixed' — plus a remediation loop ('Each failure either gets fixed before ship or filed as a known issue'), matching the level-3 anchor of clear sequence with explicit validation steps and error-recovery feedback.	3 / 3
Progressive Disclosure	SKILL.md is an overview with the detailed report template split out to references/qa-report-template.md (verified to exist), referenced three times via clear markdown links at one level of depth with no nested-reference chains, matching the level-3 anchor of a clear overview with well-signaled one-level-deep references.	3 / 3
	Total	11 / 12 Passed

Description

92%

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 description: concrete actions, rich natural-language triggers, and explicit what/when guidance in third person. The only weakness is overlap language with the accessibility/performance/SEO specialists that creates mild conflict risk.

Suggestions

Tighten distinctiveness by scoping the overlap clause, e.g. 'review accessibility, performance, or SEO basics as part of a broader QA pass (use specialists for deep audits)' so it does not compete with the dedicated skills.

Consider naming the alternatives inline ('use accessibility-audit / performance-optimization for deep dives') so the description itself disambiguates rather than relying on the body's 'When NOT to use' section.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Run QA testing on a page, feature, or full site at one of three depth tiers (smoke, standard, full)', plus 'test a page, audit a site, check for bugs, verify a deploy, run a QA sweep, review accessibility, performance, or SEO basics' — matching the level-3 anchor of multiple specific concrete actions rather than a single domain mention (level 2).	3 / 3
Completeness	Explicitly answers both what ('Run QA testing on a page, feature, or full site at one of three depth tiers') and when ('Use this skill whenever the user asks to test a page, audit a site... Triggers on...'), matching the level-3 anchor of clear what AND when with explicit triggers; not level 2 because the when clause is explicit, not merely implied.	3 / 3
Trigger Term Quality	Excellent coverage of natural phrases users say — 'test, QA, audit, verify, check, is it working, does it look right, broken, 404, image not loading, post-deploy check, regression test' — meeting the level-3 anchor of good coverage of natural terms; it is not level 2 because it includes the common variations (e.g. 'is it working', 'broken', '404'), not just a few keywords.	3 / 3
Distinctiveness Conflict Risk	The general-QA niche with three tiers is reasonably specific, but the phrase 'review accessibility, performance, or SEO basics' overlaps with the dedicated accessibility-audit, performance-optimization, and seo-technical skills, so a user asking to 'check accessibility' could trigger the wrong skill — matching the level-2 'could still overlap with similar skills' anchor rather than the level-3 'unlikely to conflict'.	2 / 3
	Total	11 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: rampstackco/claude-skills
Path: skills/qa-testing/SKILL.md
Commit: bc6d961

Reviewed: about 6 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.