Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.
87
85%
Does it follow best practices?
Impact
87%
1.97xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Quality
Discovery
N/ABased on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
Something went wrong
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 high-quality skill that provides a comprehensive, actionable workflow for exploratory web application testing. Its greatest strengths are the concrete command examples, clear evidence-collection protocols differentiated by issue type, and good progressive disclosure with external references. The main weakness is moderate verbosity in the guidance section, where several points reiterate what's already covered in the workflow steps.
Suggestions
Consolidate the Guidance section by removing points that duplicate workflow instructions (e.g., 'write findings incrementally' and 'repro is everything' are already covered in steps 4-5). Keep only guidance that adds new information not present in the workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-written but has some redundancy. Several guidance points repeat information already covered in the workflow (e.g., 'write findings incrementally' is stated in both the workflow and guidance sections). The guidance section could be tightened, and some explanations like the snapshot command differences are borderline unnecessary for Claude. | 2 / 3 |
Actionability | Excellent actionability throughout. Every step includes concrete, executable bash commands with specific flags and arguments. The evidence collection process is fully specified with exact command sequences for screenshots, video recording, and report writing. The distinction between interactive and static issue documentation is clear with copy-paste ready commands. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced with numbered phases, explicit validation points (verify reproducibility before collecting evidence), and clear decision logic (interactive vs static issues). The instruction to document issues immediately rather than batching them serves as a built-in checkpoint. The wrap-up phase includes verification that summary counts match actual issues. | 3 / 3 |
Progressive Disclosure | Content is well-structured with a clear overview workflow, detailed per-step instructions, and appropriate delegation to external files. The issue taxonomy and exploration checklist are correctly referenced in a separate file rather than inlined. The report template is kept as a separate file with clear copy instructions. References are one level deep and clearly signaled in a table. | 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 |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
fa043a4
Table of Contents
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.