arn-code-review-pr
This skill should be used when the user says "review PR", "review pull request", "check PR comments", "review PR feedback", "review PR 123", "analyze PR comments", "validate PR review", "address PR feedback", "fix PR issues", "what did the reviewer say", "review Bitbucket PR", or wants to validate GitHub or Bitbucket PR review comments, categorize findings, and optionally connect back into the Arness pipeline for fixes. Do NOT use this for creating PRs (use arn-code-ship) or reviewing implementation quality (use arn-code-review-implementation).
89
87%
Does it follow best practices?
Impact
—
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 description excels at trigger term coverage and distinctiveness, with an extensive list of natural user phrases and explicit negative boundaries that prevent conflicts with related skills. Its main weakness is that the actual capabilities ('what it does') are somewhat buried and could be more prominently and specifically enumerated at the beginning. The description is functional and effective for skill selection but is slightly front-loaded with trigger phrases at the expense of a clear capability summary.
Suggestions
Restructure to lead with a concise capability summary (e.g., 'Fetches and analyzes PR review comments from GitHub or Bitbucket, categorizes findings by severity, and optionally routes fixes into the Arness pipeline.') before listing trigger phrases.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions some concrete actions like 'validate PR review comments', 'categorize findings', and 'connect back into the Arness pipeline for fixes', but the bulk of the description is trigger phrases rather than a clear enumeration of specific capabilities. The 'what it does' portion is relatively thin compared to the trigger list. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (validate PR review comments, categorize findings, connect into Arness pipeline for fixes) and 'when' (extensive list of trigger phrases plus explicit 'Use when' and 'Do NOT use' guidance). The negative triggers for disambiguation are a strong addition. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'review PR', 'review pull request', 'check PR comments', 'review PR feedback', 'address PR feedback', 'fix PR issues', 'what did the reviewer say', 'review Bitbucket PR'. These are highly natural phrases a user would actually type. | 3 / 3 |
Distinctiveness Conflict Risk | The description is highly distinctive with explicit negative boundaries ('Do NOT use this for creating PRs (use arn-code-ship) or reviewing implementation quality (use arn-code-review-implementation)'), which clearly delineates this skill from related skills and minimizes conflict risk. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%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-structured, highly actionable skill with clear multi-step workflows, explicit validation checkpoints, and good progressive disclosure via external reference files. The dual-platform support (GitHub/Bitbucket) adds necessary length but is handled cleanly with parallel sections. The main area for improvement is minor verbosity—some sections could be tightened without losing clarity, and the error handling section at the end partially duplicates inline error handling.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long but most content is necessary given the dual-platform (GitHub/Bitbucket) support and multi-step workflow. However, there's some redundancy in error handling (repeated at end after being covered inline), and some sections could be tightened—e.g., the runtime check blocks and the detailed commit/push flow. It doesn't over-explain concepts Claude knows, but it's not maximally lean either. | 2 / 3 |
Actionability | The skill provides specific, executable CLI commands throughout (gh api, gh pr view, bkt pr comments, git commands), concrete categorization tables, exact flag names and options, and step-by-step procedures with real command syntax. The guidance is copy-paste ready and leaves little ambiguity about what to execute. | 3 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced (Steps 1-6) with explicit validation checkpoints: verifying platform availability, confirming PR identity, filtering comments, validating each comment against code, running tests after fixes (with retry up to 3 attempts and revert on failure), and asking before committing. Feedback loops are present for fix verification and error recovery. | 3 / 3 |
Progressive Disclosure | The skill references external files appropriately (pr-report-format.md, deferred-issue-template.md, testing-patterns.md) for detailed templates and formats, keeping the main skill focused on workflow. References are one level deep and clearly signaled with full paths. The main document serves as a clear overview with well-organized sections. | 3 / 3 |
Total | 11 / 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 | |
- Repository
- AppsVortex/arness
- Commit
1fe948f
- 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.