Creates GitHub pull requests with auto-generated summaries. Use this skill whenever the user wants to create a PR, open a pull request, submit changes for review, or push their branch for review - even if they don't explicitly say "PR".
94
95%
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 strong skill description with excellent trigger terms and completeness. The 'Use this skill whenever...' clause covers multiple natural phrasings users might employ. The main weakness is that the capability description could be more specific about what actions are performed beyond just creating PRs with summaries.
Suggestions
Add more specific concrete actions to improve specificity, e.g., 'Creates GitHub pull requests with auto-generated summaries, sets base/target branches, and adds reviewers.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (GitHub pull requests) and one specific action (auto-generated summaries), but doesn't list multiple concrete actions beyond creating PRs. Could mention things like setting base branch, adding reviewers, or formatting the summary. | 2 / 3 |
Completeness | Clearly answers both 'what' (creates GitHub pull requests with auto-generated summaries) and 'when' (explicit 'Use this skill whenever...' clause with multiple trigger scenarios). The when clause is detailed and actionable. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'create a PR', 'open a pull request', 'submit changes for review', 'push their branch for review'. These are phrases users would naturally say, and the note about not needing to explicitly say 'PR' is helpful. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to GitHub PR creation with auto-generated summaries. The specific triggers around pull requests, submitting changes for review, and pushing branches for review create a distinct niche unlikely to conflict with other skills like general git operations or code review skills. | 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 a high-quality skill that provides a clear, actionable workflow for creating GitHub PRs. It respects Claude's intelligence by not over-explaining concepts, provides executable commands at every step, and includes appropriate safety checkpoints (asking before committing/pushing). The structure is clean and the scope is well-bounded.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It doesn't explain what a PR is, what git does, or how gh works. Every section serves a purpose and instructions are direct. Minor verbosity in step 4 ('look at ALL commits on the branch, not just the latest one') but overall very token-efficient. | 3 / 3 |
Actionability | Provides specific, executable bash commands at every step. The gh pr create command includes a complete, copy-paste-ready format with heredoc syntax. Commands for checking state, detecting base branch, and analyzing diffs are all concrete and specific. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with logical progression: understand state → handle uncommitted changes → handle pushing → analyze → create → report. It includes explicit user-approval checkpoints before committing and pushing (destructive/irreversible operations), and handles edge cases like missing remote tracking branches and non-default base branches. | 3 / 3 |
Progressive Disclosure | For a single-purpose skill under 80 lines with no need for external references, the content is well-organized with clear section headers and a logical flow. The prerequisite check is separated from the main workflow, and each step is its own subsection. No bundle files are needed for this scope. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
defdc4d
Table of Contents
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.