Review

Skill eddmann/agent-toolkit/skills/review

Review code against coding guidelines and best practicesFrom its SKILL.md

Install

npx -y skills add eddmann/agent-toolkit --skill review

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

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
2 stars2 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.

SKILL.md

2.6 KB, 593 tokens by cl100k_base, as published. Nobody here has run it

ultrathink: Perform a thorough code review by first reading all relevant code and guidelines, then providing specific, actionable feedback.

Your Task

Review: $ARGUMENTS

Context

Current directory: !pwd
Git status: !git status --short 2>/dev/null | head -20

Guidelines to Apply

Read and apply these standards from the guidelines directory ($GUIDELINES_DIR):

$GUIDELINES_DIR/foundation/code-philosophy.md
$GUIDELINES_DIR/practices/clean-code-practices.md
$GUIDELINES_DIR/practices/design-principles.md
$GUIDELINES_DIR/practices/testing.md
$GUIDELINES_DIR/practices/error-handling.md

Instructions

Phase 1: Load Guidelines

First, read ALL the guideline files above. Understand:

Code philosophy: predictable, boring, declarative, immutable
Clean code: small functions, descriptive naming, early returns, no magic numbers
Design: KISS, single responsibility, dependency injection, composition
Testing: classical school, behavior-focused, AAA pattern, stubs over mocks
Errors: fail fast, don't hide failures, validate at boundaries

Phase 2: Read the Code

Thoroughly read the code to review:

Read all relevant files in the target area
Understand the context - what does this code do?
Trace dependencies - what does it interact with?
Check tests - are behaviors well-tested?

Phase 3: Evaluate Against Guidelines

For each issue found:

Identify the specific guideline being violated
Quote the relevant code with file:line reference
Explain why it matters - what's the risk or cost?
Suggest a fix - be specific and actionable

Phase 4: Provide Summary

Organize your review:

Critical issues - must fix, violates core principles
Improvements - should fix, better aligns with guidelines
Nitpicks - optional, minor style preferences
Praise - what's done well (briefly)

Output Format

For each issue:

### [Critical/Improvement/Nitpick]: Brief title

**Location**: `path/to/file.swift:42`
**Guideline**: [Quote relevant guideline]
**Issue**: [What's wrong]
**Suggestion**: [How to fix]

Critical Rules

DO NOT make changes - this is review only
Cite specific guidelines - not just "this is bad"
Be actionable - every issue should have a clear fix
Include file:line - make issues easy to find

What ships with it

Read from the repository

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

Gives 0 of the 12 instructions most review quality skills give in 593 tokens

Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07

Ask questions one at a timein 81 of 1048, across 64 files
Provide a recommended answer for each questionin 73 of 1048, across 50 files
Explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
Interview the user relentlessly about the planin 38 of 1048, across 13 files
Order findings by severityin 31 of 1048
Resolve each branch of the decision treein 27 of 1048, across 5 files
Run a grilling sessionin 26 of 1048, across 5 files
Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
Create documentation files lazilyin 24 of 1048, across 5 files
Assign severity to every findingin 24 of 1048

Said here and by no other author read

trace dependencies for the target code
check behavior tests for the code
quote relevant code with file line references

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.