pr-manual-testing
Generate Gherkin-format manual testing steps from code changes for pull request descriptions. Use when the user asks for manual testing steps, Gherkin test scenarios, or QA steps for a PR.
95
93%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
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 well-crafted skill description that concisely communicates a specific capability with clear trigger conditions. It uses third person voice, lists concrete actions, and includes an explicit 'Use when' clause with natural trigger terms. The description is distinctive enough to avoid conflicts with related but different skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists a specific concrete action: 'Generate Gherkin-format manual testing steps from code changes for pull request descriptions.' This clearly describes what the skill does with a specific output format (Gherkin), input (code changes), and context (pull request descriptions). | 3 / 3 |
Completeness | Clearly answers both 'what' (generate Gherkin-format manual testing steps from code changes for PR descriptions) and 'when' (explicit 'Use when' clause with three trigger scenarios: manual testing steps, Gherkin test scenarios, or QA steps for a PR). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'manual testing steps', 'Gherkin test scenarios', 'QA steps', 'PR'. These cover the main variations a user would naturally use when requesting this type of output. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Gherkin-format manual testing steps specifically for PRs. The combination of Gherkin format, manual testing, and PR context makes it very unlikely to conflict with other skills like general testing, code review, or PR description skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%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-crafted skill that efficiently teaches Gherkin scenario generation for PRs. It excels in conciseness and actionability with complete, copy-paste-ready examples at multiple complexity levels. The only notable gap is the lack of a verification step in the workflow to ensure generated scenarios adequately cover the actual code changes.
Suggestions
Add a verification step after writing scenarios, e.g., 'Review each scenario against the diff to confirm all user-facing behavior changes are covered and no changed code path is untested.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. The keyword definitions are brief and necessary (Gherkin-specific conventions Claude needs to follow), examples are minimal but illustrative, and there's no padding or explanation of obvious concepts. | 3 / 3 |
Actionability | Provides a concrete template, three complete executable Gherkin examples covering different complexity levels (single scenario, multiple scenarios with background, data tables), and a clear step-by-step process starting with the exact git command to run. | 3 / 3 |
Workflow Clarity | The 4-step process is clear and sequenced, but there's no validation checkpoint—no step to verify the generated scenarios actually cover the changed code paths, or to cross-check scenarios against the diff. For a generative task this is less critical than for destructive operations, but a review/verification step would strengthen it. | 2 / 3 |
Progressive Disclosure | Content is well-structured with clear sections (Format, Steps, Template, Examples, Reference). The reference to a sample feature file for advanced patterns is a clean one-level-deep pointer. The skill is appropriately self-contained for its scope. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- MetaMask/metamask-mobile
- Commit
bee9b14
- 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.