pr-description
Generate a complete pull request description following the MetaMask Mobile PR template. Use when the user asks to generate a PR description, fill the PR template, or create a pull request body.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 solid skill description that clearly communicates its purpose and when to use it, with good trigger term coverage and strong distinctiveness through the MetaMask Mobile scoping. The main weakness is that it could be more specific about the concrete actions involved (e.g., summarizing changes, filling template sections like description, testing steps, screenshots).
Suggestions
Add more specific sub-actions to increase specificity, e.g., 'Analyzes code changes, summarizes modifications, fills template sections including description, testing steps, and screenshots.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (pull request descriptions) and a specific action (generate a complete PR description following the MetaMask Mobile PR template), but doesn't list multiple concrete sub-actions like filling specific template sections, adding test plans, linking issues, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (generate a complete PR description following the MetaMask Mobile PR template) and 'when' (explicit 'Use when' clause with three trigger scenarios: generate PR description, fill PR template, create pull request body). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'PR description', 'PR template', 'pull request body', 'generate a PR description', 'fill the PR template', 'create a pull request'. Good coverage of common variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific mention of 'MetaMask Mobile PR template', which clearly scopes this to a particular project and task. Unlikely to conflict with generic code or documentation skills. | 3 / 3 |
Total | 11 / 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 encodes project-specific CI requirements and conventions that Claude wouldn't know. The workflow is clear and the table of exact section titles with guidance is particularly valuable. The main gap is the lack of an explicit validation step to verify the generated output contains all 7 required section titles before writing the file, which is important given CI enforcement.
Suggestions
Add a validation step after assembling the output to verify all 7 required section titles are present exactly as specified, before writing the file — this would catch errors that CI would otherwise flag.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place — the workflow steps are terse, the table encodes CI-enforced constraints that Claude wouldn't know, and there's no explanation of basic concepts. The content is dense with project-specific knowledge. | 3 / 3 |
Actionability | Provides concrete bash commands for context collection, exact section title strings required by CI, specific output file naming conventions with sanitization rules, and precise formatting requirements (e.g., `- [x]` for author checklist, `Fixes: #NUMBER`). Fully actionable. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced and logically ordered. However, there's no explicit validation checkpoint — step 7 mentions running a readiness check but explicitly says 'do not block,' and there's no step to verify the output file matches the required 7 section titles before finishing. For a task that CI validates, a verification step would be valuable. | 2 / 3 |
Progressive Disclosure | Cleanly delegates to sub-skills (pr-title, pr-issue-search, pr-changelog, pr-manual-testing, pr-readiness-check) with 'see X skill if available' references. Points to `.github/pull-request-template.md` for the full template. Content is well-structured with workflow, template sections table, and output format as distinct sections. | 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.