pr-create
Create a GitHub pull request from the current branch. Validates preconditions, generates title and description, and opens the PR as draft. Use when the user asks to create a PR, open a pull request, or submit changes for review.
100
100%
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 an excellent skill description that clearly communicates what the skill does (creates GitHub PRs with validation, title/description generation, and draft mode), when to use it (explicit trigger clause with natural language variations), and is distinctly scoped to PR creation. It follows third-person voice, is concise, and covers the key trigger terms users would naturally use.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: validates preconditions, generates title and description, opens the PR as draft. These are clear, actionable steps. | 3 / 3 |
Completeness | Clearly answers both what ('Create a GitHub pull request from the current branch. Validates preconditions, generates title and description, and opens the PR as draft') and when ('Use when the user asks to create a PR, open a pull request, or submit changes for review'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'create a PR', 'open a pull request', 'submit changes for review', 'GitHub pull request', 'current branch'. Good coverage of common variations. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to GitHub PR creation specifically, with distinct triggers like 'pull request', 'PR', and 'submit changes for review'. Unlikely to conflict with other skills like general git operations or code review skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill that demonstrates strong workflow design with clear precondition checks, concrete executable commands, appropriate fallback patterns, and well-structured output templates. It efficiently delegates to related skills without deep nesting, and includes thoughtful details like parallel execution of independent steps and user consent gates for destructive actions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. Every section serves a purpose—no explanations of what a PR is, no unnecessary context about git or GitHub. The parallel execution note and fallback pattern are both genuinely useful additions, not padding. | 3 / 3 |
Actionability | Provides fully executable commands (git checks, gh CLI with exact flags, MCP tool invocation with complete JSON), specific abort conditions, concrete output templates, and clear fallback paths. Copy-paste ready throughout. | 3 / 3 |
Workflow Clarity | Clear 5-step sequence with explicit validation checkpoints (precondition checks with specific abort conditions), user consent gates via AskQuestion tool, parallel step optimization clearly marked, and a well-defined output format. Error recovery is handled via abort messages and user prompts. | 3 / 3 |
Progressive Disclosure | Appropriately references external skills (pr-description, pr-codeowners, pr-review-queue) with 'see X skill if available' pattern—one level deep, clearly signaled. The main content stays focused on the PR creation workflow without inlining those concerns. | 3 / 3 |
Total | 12 / 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.