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.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that excels across all dimensions. It clearly defines what the skill does (QA testing at three depth tiers), when to use it (with an extensive and natural list of trigger terms), and includes both reactive and proactive trigger conditions. The description is concise yet comprehensive, with excellent coverage of natural language variations users would actually employ.
| 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)'. It specifies the scope (page/feature/site) and the tiered approach, plus mentions accessibility, performance, and SEO basics. | 3 / 3 |
Completeness | Clearly answers both 'what' (run QA testing at three depth tiers covering accessibility, performance, SEO) and 'when' (explicit 'Use this skill whenever...' clause plus a detailed trigger list and proactive trigger conditions). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including both formal ('QA', 'regression test', 'audit') and informal/natural language ('is it working', 'does it look right', 'broken', '404', 'image not loading'). These are terms users would actually say. | 3 / 3 |
Distinctiveness Conflict Risk | The QA testing niche with specific depth tiers (smoke, standard, full) and the focus on page/site verification creates a clear, distinct identity. The trigger terms are well-scoped to testing/verification rather than general development tasks. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable QA skill with excellent executable snippets and clear tiered workflow. Its main weakness is length — the inline snippets for every sub-audit make the file long, and some content (failure patterns, required inputs) could be trimmed or relocated. The referenced template file doesn't exist in the bundle, which slightly undermines the progressive disclosure structure.
Suggestions
Move the specific QA snippets (image audit, heading hierarchy, contrast, form audit, external link audit) into a separate reference file like `references/qa-snippets.md` to reduce the main skill's token footprint.
Remove or significantly trim the 'Failure patterns' section — most points are general QA wisdom that Claude already knows, not skill-specific operational guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of tables and structured snippets, but includes some unnecessary sections like 'When NOT to use' cross-references, 'Failure patterns' that state obvious QA principles, and the 'Required inputs' section which is largely self-evident. The contrast spot-check function and some snippets are lengthy but earn their place as executable code. | 2 / 3 |
Actionability | Excellent actionability with fully executable JavaScript console snippets for every tier and specific QA dimension. The smoke test, standard audit, image audit, heading hierarchy, contrast check, form audit, and external link audit snippets are all copy-paste ready with clear pass/fail criteria. | 3 / 3 |
Workflow Clarity | The workflow section provides a clear 6-step sequence with tier selection as the first decision point. The smoke test includes an explicit gate ('If any of these fail, do not proceed with deeper testing until the smoke issue is fixed'), and the failure patterns section reinforces validation discipline. Each tier has explicit pass criteria serving as checkpoints. | 3 / 3 |
Progressive Disclosure | The skill references `references/qa-report-template.md` which is appropriate for progressive disclosure, but no bundle files were provided so this reference is unverifiable. The main content is quite long (~300 lines) with all snippets inline; the specific QA snippets section (image audit, heading hierarchy, contrast, form audit, external links) could reasonably be split into a reference file to keep the main skill leaner. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- rampstackco/claude-skills
- Commit
8e70d03
- Reviewed
Table of Contents
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.