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

77%

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

77%

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

A well-structured, highly actionable code-review skill with clear sequenced workflows and feedback checkpoints. It loses points for some redundant conceptual explanation and for keeping everything inline with no progressive disclosure to separate reference files.

Suggestions

Trim explanations of concepts Claude already knows (why in-place mutation is risky, why optimizations carry maintenance cost) and keep only the concrete detection signals and suggested fixes.

Consider splitting the detailed checklists (abstraction-integrity signals, mutation patterns, the vMCP anti-pattern integration) into a reference file linked from SKILL.md to reduce inline length and enable progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly tailored, actionable guidance, but it explains concepts Claude already knows — e.g. "In-place mutation is a significant source of subtle bugs..." and "Optimizations add maintenance cost (invalidation, staleness, lifecycle management)" — which could be trimmed, landing at the "mostly efficient but could be tightened" anchor.	2 / 3
Actionability	Concrete and specific throughout: a fixed 8-section response structure, conventional-comment severity labels with definitions, explicit abstraction-integrity signals, and a directive to "enumerate the full input matrix (type × field combinations, flag × state permutations)" — instruction-only guidance that is fully actionable.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (Session Planning 1-5, review sections 1-8, tracking 1-2) with explicit feedback loops — "Present PRs one at a time... let the user respond, and only then move to the next" and "All draft comments must be presented to the user for review before posting — no exceptions."	3 / 3
Progressive Disclosure	No bundle files exist and all guidance is inline in a single ~152-line SKILL.md; the content is well-sectioned but nothing is split into one-level-deep reference files, so it matches "some structure but content that should be separate is inline" rather than a clearly split overview.	2 / 3
	Total	10 / 12 Passed

Description

77%

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 description that explicitly states both capabilities and a use-when trigger with concrete actions. Weakest on trigger-term variation coverage and distinctiveness from a generic code-reviewer agent.

Suggestions

Broaden trigger terms to include common phrasings users would say, e.g. "Use when reviewing a pull request, diff, patch, or code snippet for code review".

Sharpen distinctiveness by contrasting the human-in-the-loop framing in the description itself, e.g. "Use when the user is actively reviewing a PR themselves and wants a senior review partner — not for autonomous review."

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "summarizing changes, surfacing key review questions, assessing test coverage, and identifying low-risk sections" — matching the anchor for enumerating several specific actions rather than naming only a domain.	3 / 3
Completeness	Clearly answers both what ("Augments human code review by...") and when ("Use when reviewing a diff, PR, or code snippet as a senior review partner"), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Natural terms appear ("reviewing a diff, PR, or code snippet"), but coverage is limited to these three with no common variations such as "pull request", "code review", or "patch", so it sits at the "some relevant keywords but missing common variations" anchor.	2 / 3
Distinctiveness Conflict Risk	The "augments human code review / senior review partner" framing is a distinct niche, but the trigger "reviewing a diff, PR, or code snippet" is generic to code review and would also match an autonomous code-reviewer agent, so overlap risk remains.	2 / 3
	Total	10 / 12 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: cd373ec

Reviewed: 2 days 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.