evidence-collector
Reviews web application UI using Playwright screenshot captures to identify visual bugs, broken interactive elements, layout regressions, and specification mismatches. Produces structured evidence-based QA reports with screenshot references, pass/fail verdicts, and prioritised fix lists. Use when asked to QA a web page, find UI bugs, run visual testing, check screenshot evidence, validate an implementation against a spec, review responsive layout, or verify interactive elements like accordions, forms, and navigation menus.
93
92%
Does it follow best practices?
Impact
Pending
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 an excellent skill description that hits all the marks. It provides specific concrete actions, comprehensive trigger terms covering natural user language, explicit 'Use when' guidance, and a clearly distinctive niche combining Playwright screenshots with visual QA reporting. The description is well-structured, concise, and uses appropriate third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: reviewing UI via Playwright screenshots, identifying visual bugs, broken interactive elements, layout regressions, specification mismatches, and producing structured QA reports with screenshot references, pass/fail verdicts, and prioritised fix lists. | 3 / 3 |
Completeness | Clearly answers both 'what' (reviews web UI using Playwright screenshots, identifies visual bugs, produces structured QA reports) and 'when' with an explicit 'Use when...' clause listing multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'QA a web page', 'find UI bugs', 'visual testing', 'screenshot evidence', 'validate against a spec', 'responsive layout', 'accordions', 'forms', 'navigation menus'. These are highly natural phrases a user would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Playwright-based visual QA of web UIs with screenshot evidence. The combination of Playwright screenshots, visual bug detection, and structured QA reports makes it unlikely to conflict with general testing or code review skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable QA skill that provides concrete commands, clear multi-step workflows with validation gates, and appropriate progressive disclosure to external files. The report template is somewhat verbose inline given that it references an external qa.md for the full template, but overall the skill is effective and well-organized. The automatic fail triggers and decision gate logic add valuable safety guardrails for a QA process.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining basic concepts, but the report template section is quite lengthy and could be referenced from the external qa.md file instead of being inline. Some repetition exists between the decision gate rules and the general operating rules. | 2 / 3 |
Actionability | Provides concrete bash commands for capturing screenshots, specific file patterns to check, exact grep commands, a structured testing table with specific evidence file names, and a complete report template with examples of spec compliance notation. Highly actionable throughout. | 3 / 3 |
Workflow Clarity | Clear 4-step sequential workflow with explicit validation at each stage. Step 4 serves as a decision gate with automatic fail triggers, creating a feedback loop. The progression from evidence capture → analysis → interactive testing → decision is well-structured with clear checkpoints. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled references to external files: the capture script (qa-playwright-capture.sh), the full QA methodology (ai/agents/qa.md), and the full report template. The inline content is appropriately scoped as an overview, with deeper details delegated one level deep. | 3 / 3 |
Total | 11 / 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
- OpenRoster-ai/awesome-agents
- Commit
010799b
- 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.