code-review-assist

Augments human code review by summarizing changes, surfacing key review questions, assessing test coverage, and identifying low-risk sections. Use when reviewing a diff, PR, or code snippet as a senior review partner.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/code-review-assist/SKILL.md

Quality

Content

67%Weight 40%Scale 1-5

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

A thorough, well-structured review playbook with strong actionability and clear workflow sequencing. The main weakness is verbosity, notably the duplicated conventional-comments definitions and some explanatory prose that over-explains concepts Claude already knows.

Suggestions

Remove the duplicate severity-label definitions: keep them once in Comment Format and reference them from Key Concerns instead of re-listing all four labels.

Tighten the Key Concerns bullets (abstraction integrity, mutation of shared state, premature optimization) to signals and checks rather than paragraphs explaining why the patterns are harmful.

Consider extracting the detailed concern-evaluation criteria into a references file and keeping SKILL.md as an overview, which would improve both conciseness and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient structural guidance, but the conventional-comments severity labels (blocker/suggestion/nitpick/question) are defined verbatim twice (Key Concerns and Comment Format), and several concern bullets explain concepts Claude already knows (e.g., why in-place mutation is error-prone).	3 / 5
Actionability	Concrete, executable structure: fixed response sections, '2-5 concerns', '2-4 sentences', explicit severity labels, and tracking artifacts; as an instruction-only skill the absence of code is acceptable, with only minor gaps.	4 / 5
Workflow Clarity	Clear sequencing — 5-step session planning, one-PR-at-a-time with user response as the checkpoint, and end-of-session coverage tracking — with most checkpoints present; only minor validation gaps.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with no nested references; no bundle files exist, and the cross-references (vmcp-review skill, .claude/rules/) are external but clearly signaled.	4 / 5
	Total	15 / 20 Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description with explicit trigger guidance and concrete capabilities. Minor room to spell out 'pull request' and sharpen the boundary versus autonomous code-review agents.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'summarizing changes, surfacing key review questions, assessing test coverage, and identifying low-risk sections' — with comprehensive coverage and no vague filler.	5 / 5
Completeness	Explicitly states what it does (the four augmentations) and when to use it ('Use when reviewing a diff, PR, or code snippet as a senior review partner').	5 / 5
Trigger Term Quality	Natural user phrases like 'reviewing a diff, PR, or code snippet' map well to what a user would say; 'pull request' is only present as the abbreviation 'PR', leaving a few synonyms unmentioned.	4 / 5
Distinctiveness Conflict Risk	The 'senior review partner' / human-in-the-loop framing carves a distinct niche, though it sits adjacent to a generic code-reviewer agent and could overlap for plain review requests.	4 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: stacklok/toolhive
Path: .claude/skills/code-review-assist/SKILL.md
Commit: ccabad6

Reviewed: about 13 hours ago

Table of Contents

Discovery Implementation Validation

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.