arn-reviewing-pr
This skill should be used when the user says "reviewing pr", "arness reviewing pr", "review PR", "review pull request", "check PR comments", "PR feedback", "address PR feedback", "fix PR issues", "what did the reviewer say", "handle review comments", "review PR 123", "arn-reviewing-pr", "PR review", "check review", or wants to validate PR review comments, categorize findings, and fix or defer issues. Chains back to arn-implementing if substantial fixes are needed.
80
76%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/arn-code/skills/arn-reviewing-pr/SKILL.mdQuality
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.
The description excels at trigger term coverage and completeness, providing an exhaustive list of natural phrases and clearly stating both what the skill does and when to use it. Its main weakness is that the capability description ('validate PR review comments, categorize findings, and fix or defer issues') could be more specific about the concrete actions performed. The heavy reliance on listing trigger phrases makes it functional but somewhat verbose.
Suggestions
Expand the capability description with more concrete actions, e.g., 'Fetches PR review comments from GitHub, categorizes them as actionable fixes vs. style suggestions, applies code fixes inline, and marks resolved comments.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions some actions like 'validate PR review comments, categorize findings, and fix or defer issues' and 'chains back to arn-implementing if substantial fixes are needed,' but these are somewhat vague and not comprehensively detailed. It doesn't describe the concrete steps or mechanisms involved. | 2 / 3 |
Completeness | The description explicitly answers both 'what does this do' (validate PR review comments, categorize findings, fix or defer issues) and 'when should Claude use it' (with a comprehensive list of trigger phrases and conditions). The 'Use when' guidance is clearly embedded. | 3 / 3 |
Trigger Term Quality | The description includes an extensive list of natural trigger phrases users would say, such as 'review PR', 'review pull request', 'check PR comments', 'PR feedback', 'address PR feedback', 'fix PR issues', 'what did the reviewer say', and 'handle review comments'. These cover many natural variations well. | 3 / 3 |
Distinctiveness Conflict Risk | The description is clearly focused on PR review handling with distinct triggers like 'reviewing pr', 'PR feedback', 'address PR feedback'. It also clarifies its relationship to 'arn-implementing' for handoff, making its niche clear and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%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 orchestration skill with clear workflow sequencing and good decision branching at each step. Its main weaknesses are some redundancy between the workflow steps and the error handling section, and moderate actionability since most concrete work is delegated to the invoked review skill. The skill does a good job of defining its scope as a thin wrapper and providing clear chain exits.
Suggestions
Consolidate error handling into the workflow steps where the errors actually occur, rather than repeating them in a separate section, to reduce redundancy.
Remove the introductory paragraph explaining what the skill does vs. what it delegates — the workflow itself makes this clear, and the explanation consumes tokens without adding value for Claude.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some redundant explanations. The preamble about being a 'thin orchestration wrapper' and what it handles could be tighter. The error handling section partially repeats information already covered in the workflow steps (e.g., platform not configured, no PR for current branch). | 2 / 3 |
Actionability | The skill provides a clear sequence of actions and specific invocation syntax for the review skill, but it delegates almost all concrete work to `arn-code-review-pr`. The skill itself is an orchestration wrapper, so actionability is inherently limited, but the completion handoff options and git push command are concrete. The `Skill: arn-code:arn-code-review-pr` invocation syntax is specific but the ensure-config step relies on reading an external file without summarizing what to expect. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Step 0 through Step 3) with explicit decision points and branching logic. Error handling is comprehensive with specific recovery actions for each failure mode. The completion handoff includes clear conditional branching based on outcomes, and the progress indicator is a nice touch. | 3 / 3 |
Progressive Disclosure | The skill appropriately delegates to `arn-code-review-pr` and references `ensure-config.md` for configuration, showing good structural intent. However, with no bundle files provided, the referenced paths cannot be verified. The skill itself is reasonably sized but the error handling section partially duplicates workflow content rather than being cleanly separated or omitted. | 2 / 3 |
Total | 9 / 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.