CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

72%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-structured with clear sequencing and an explicit error-handling section, befitting a thin orchestration wrapper. Its weaker dimensions are actionability and workflow clarity, where placeholders and reliance on the wrapped skill leave some guidance incomplete and validation checkpoints implicit.

Suggestions

Replace the 'REVIEW-PR' placeholder in the Step 2 progress display with a concrete instruction (e.g., the exact Skill invocation line) so the guidance is copy-paste ready.

Add an explicit validation checkpoint in Step 2 (e.g., 'confirm arn-code-review-pr returned successfully before proceeding to Step 3') rather than relying solely on its internal completion.

Make the chain-exit handoff in Step 3 fully actionable by specifying the git push form (e.g., 'git push origin <current-branch>') instead of a bare 'git push'.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains concepts Claude already knows, and every line (Step 0 config gate, input routing, the AskUserQuestion options) earns its place, matching the level-3 lean-and-efficient anchor.

3 / 3

Actionability

Concrete invocations are present ('Skill: arn-code:arn-code-review-pr', 'Skill: arn-code:arn-implementing', 'git push') with a real AskUserQuestion menu, but it leans on a placeholder ('Reviewing PR: REVIEW-PR -> [fix / defer / plan]') and delegates the actual review work to the wrapped skill rather than giving copy-paste-ready commands, so it sits at 'some concrete guidance but incomplete' rather than fully executable.

2 / 3

Workflow Clarity

Steps 0–3 are clearly sequenced with gating checks (Step 0 completion, Platform=none branch) and an error-handling section, but Step 2's review invocation has no explicit validation checkpoint of its own — it defers validation to the wrapped skill and only offers a retry/abort on failure, so checkpoints are partly implicit.

2 / 3

Progressive Disclosure

This is a short single-purpose orchestration skill under 50 lines with well-organized sections (Step 0, Workflow Step 1–3, Error Handling) and one explicitly-signaled external reference path, so per the simple-skills note it earns the top score without needing external file splits.

3 / 3

Total

10

/

12

Passed

Description

92%Weight 40%Scale 1-3

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 is specific, trigger-rich, and explicitly pairs a what-clause with a when-clause, making it strong on completeness and trigger quality. Its main weakness is the wrapper-to-base relationship with arn-code-review-pr, which creates some trigger overlap risk.

Suggestions

Differentiate from arn-code-review-pr in the description, e.g. note it is the entry point that chains back to arn-implementing, so a user saying 'review PR' picks the right skill.

Trim a few redundant trigger variants (e.g. 'check review' vs 'check PR comments') to keep the list tight without losing coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: 'validate PR review comments, categorize findings, and fix or defer issues' plus 'prerequisite checks, input routing, invoking the review skill, and offering the chain exit', matching the level-3 anchor of several specific concrete actions.

3 / 3

Completeness

Explicitly answers both what ('validate PR review comments, categorize findings, and fix or defer issues') and when ('should be used when the user says...'), satisfying the level-3 'clearly answers both what AND when with explicit triggers' anchor.

3 / 3

Trigger Term Quality

Covers a broad spread of natural phrasings a user would actually say — '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' — matching the level-3 good coverage anchor; not level 2 because common variations are well represented.

3 / 3

Distinctiveness Conflict Risk

PR-review triggers are clearly niche-specific, but as a thin wrapper around 'arn-code-review-pr' its triggers could overlap with that base skill for a user simply saying 'review PR', so it sits at 'somewhat specific but could still overlap' rather than a clean, conflict-free niche.

2 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
AppsVortex/arness
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.