pr-review-queue
Add a pull request to the MetaMask PR review queue project board. Use when the user asks to add a PR to the review queue, submit a PR for review tracking, or add to the MetaMask project board.
96
95%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 defines a narrow, specific task with explicit trigger guidance. The 'Use when...' clause provides good coverage of natural user phrasings. The only minor weakness is that it describes a single action, so there's limited specificity in terms of multiple capabilities, though this may simply reflect the skill's narrow scope.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a specific domain (MetaMask PR review queue project board) and one action (add a pull request), but only describes a single concrete action rather than listing multiple specific capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (add a pull request to the MetaMask PR review queue project board) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'pull request', 'PR', 'review queue', 'submit a PR', 'review tracking', 'MetaMask project board'. These cover multiple natural phrasings a user might use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific combination of MetaMask, PR review queue, and project board. Very unlikely to conflict with other skills given the narrow, well-defined niche. | 3 / 3 |
Total | 11 / 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, well-crafted skill. It provides a clear, step-by-step workflow with fully executable commands, appropriate use of dynamic field fetching instead of hardcoded values, and a clean structure that respects Claude's intelligence. The only minor note is that error handling (e.g., what if the PR URL is invalid or the user lacks permissions) is not addressed, but this is a minor gap for a skill of this nature.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section serves a purpose. No unnecessary explanations of what GitHub Projects are or how GraphQL works. The content assumes Claude knows how to use `gh` CLI and GraphQL mutations, and only provides the specific commands and field names needed. | 3 / 3 |
Actionability | Fully executable `gh` CLI commands and GraphQL mutations are provided with clear placeholder variables. Each step has copy-paste-ready code with specific flags, field names, and jq selectors. The date format computation is explicitly specified. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with dependencies between steps explicitly noted (e.g., step 1 produces field IDs used in steps 4-5, step 2 produces the item node ID). The instruction to dynamically fetch priority options rather than hardcode them serves as a validation/correctness checkpoint. The user interaction point (AskQuestion for priority) is clearly placed. | 3 / 3 |
Progressive Disclosure | For a single-purpose skill of this size (~80 lines), the content is well-organized with clear sections (Input, Method with numbered steps, Output). No need for external file references given the scope, and the structure makes it easy to follow without being a wall of text. | 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.