Check a single PR's CI status, review comments, and requested changes. Fix actionable failures and address feedback. "check PR 1234", "what's the status of my PR", "address review comments on #500".
99
100%
Does it follow best practices?
Impact
—
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 strong skill description that concisely communicates specific capabilities (checking CI status, review comments, fixing failures, addressing feedback) with natural trigger examples that users would actually type. It uses third person voice correctly and is clearly scoped to single-PR operations, reducing conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: check CI status, review comments, requested changes, fix actionable failures, and address feedback. These are clear, concrete capabilities. | 3 / 3 |
Completeness | Clearly answers 'what' (check CI status, review comments, requested changes; fix failures and address feedback) and 'when' through explicit example triggers that serve as usage guidance. The example phrases effectively function as trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would actually say: 'check PR 1234', 'what's the status of my PR', 'address review comments on #500', plus terms like 'CI status', 'review comments', 'requested changes', and 'PR'. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to a single PR's CI status, review comments, and requested changes. The 'single PR' qualifier and specific trigger examples like 'check PR 1234' and '#500' make it distinct from broader CI/CD 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, well-crafted skill that provides concrete, executable guidance for checking and acting on PR status. It efficiently covers all PR states (merged, closed, open with CI failures, open with review comments) with specific CLI commands and GraphQL queries. The workflow is clearly sequenced with appropriate conditional branching and a standardized report format.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place—no explanations of what PRs or CI are, no padding. The skill assumes Claude knows git, GitHub CLI, and GraphQL, and jumps straight into actionable commands. The conditional branching (merged/closed/failing/review) is tightly written. | 3 / 3 |
Actionability | Fully executable gh CLI commands and GraphQL queries are provided for every step—gathering PR state, reading inline comments, resolving threads, replying to comments, and pushing fixes. Commands are copy-paste ready with clear placeholders. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (gather state → branch by PR status → act → report) with explicit conditional paths for merged, closed, CI-failing, and review-comments scenarios. Validation is implicit but appropriate—CI re-runs after push, and the report step serves as a final checkpoint. The feedback loop of fix → push → reply → resolve is well-defined. | 3 / 3 |
Progressive Disclosure | For a single-purpose skill with no bundle files, the content is well-organized into numbered sections with clear headers. The skill is appropriately self-contained at ~80 lines and doesn't need external references. Content is logically split by PR state, making navigation easy. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
c0aa985
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.