Multi review

Skill SamyakJhaveri/loam/seed/.claude/skills/multi-review

Copier template that bootstraps AI-agent-optimized project setups: layered context routing, curated skills, and an enforced validation gate — synced across projects.

Install

npx -y skills add SamyakJhaveri/loam --skill multi-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Multi-agent parallel code review with 4 reviewers (style, correctness, security, performance). Use before merging a feature branch, before committing a non-trivial change, or when a second pair of eyes is needed. Complements /validate (which checks pipeline correctness); review checks code quality. NOT for: single-line trivial changes, commit-message review, or replacing /validate — use both, not either.

SKILL.md

1.6 KB, 296 tokens by cl100k_base, as published. Nobody here has run it

Multi-Agent Code Review

Structured code review using parallel subagents for thorough coverage.

Arguments

$ARGUMENTS — optional: file paths or commit range to review (default: staged changes)

Workflow

Phase 1: Identify Scope

If arguments specify files/commits, use those
Otherwise, review staged changes (git diff --cached)
If nothing is staged, review unstaged changes (git diff)

Phase 2: Parallel Review

Launch 4 subagents simultaneously, each reviewing the same changes:

Style Agent — naming, formatting, consistency with existing code
Correctness Agent — logic errors, off-by-one, null/undefined risks
Security Agent — injection, path traversal, secret exposure, OWASP top 10
Performance Agent — unnecessary allocations, O(n²) where O(n) is possible

Phase 3: Synthesize

Collect all findings
Deduplicate overlapping concerns
Prioritize by severity: critical > high > medium > low

Phase 4: Report

Present findings grouped by severity:

## Critical
- [issue + file:line + suggestion]

## High
- ...

## Medium / Low
- ...

## Summary
N issues found (X critical, Y high, Z medium/low)
Recommendation: APPROVE / NEEDS CHANGES

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.