pr-issue-search
Find related GitHub issues for a pull request by extracting from branch name, commit messages, or searching GitHub. Use when the user asks to find related issues, link issues to a PR, or search for GitHub issues to reference.
100
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 clearly communicates its purpose, methods, and trigger conditions. It uses third person voice, lists concrete actions, includes natural trigger terms, and has an explicit 'Use when' clause with multiple trigger scenarios. It closely matches the good examples in the rubric.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: extracting from branch name, extracting from commit messages, and searching GitHub. These are clear, actionable methods for finding related issues. | 3 / 3 |
Completeness | Clearly answers both what ('Find related GitHub issues for a pull request by extracting from branch name, commit messages, or searching GitHub') and when ('Use when the user asks to find related issues, link issues to a PR, or search for GitHub issues to reference'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'GitHub issues', 'pull request', 'PR', 'related issues', 'link issues', 'branch name', 'commit messages'. These cover common variations of how users would phrase such requests. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche: finding and linking GitHub issues to PRs. The combination of PR context + issue discovery is specific enough to avoid conflicts with general GitHub skills or broader 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 a well-crafted skill that efficiently guides Claude through a clear multi-step process for finding related GitHub issues. It provides concrete commands, regex patterns, tool payloads, and output formats without any unnecessary explanation. The examples section effectively covers all the edge cases (GitHub issues, Jira tickets, keyword search, no issues found).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No unnecessary explanations of what GitHub issues are or how git works. The regex patterns, branch naming conventions, and tool invocations are all novel information Claude needs. The examples are compact and illustrative. | 3 / 3 |
Actionability | Provides executable bash commands, specific regex patterns for extraction, concrete MCP tool JSON payloads, and exact output format strings. The fallback from `gh` CLI to GitHub MCP is fully specified with copy-paste ready arguments. | 3 / 3 |
Workflow Clarity | Clear three-step sequential workflow with an explicit early-exit condition ('Stop as soon as you have issue numbers'). Each step has a concrete action and the progression from branch name → commit messages → keyword search is logical. Step 3 only triggers when prior steps fail, which is a well-defined feedback mechanism. | 3 / 3 |
Progressive Disclosure | For a skill of this size (~80 lines) with a single focused task, the content is well-organized into logical sections (Strategy with numbered steps, Output Format, Examples) without needing external references. No monolithic walls of text; each section is appropriately scoped. | 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
d8db24a
- 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.