Automated summary
This skill performs a critical review of code or design using structured criteria (completeness, style, architecture, best practices, etc.).
Strengths
- Comprehensive and prioritized evaluation criteria
- Prioritization of the internal style guide
- Handling of conflicts between existing patterns and the style guide
- Structured output with issue list and recommendations
Limitations
- Requires an explicit `code-style.md` file for style evaluation
- Can be challenging on very large changes without full context
- Does not cover automated execution checks (compilation, tests)
Use this skill when you need a thorough review of a pull request, software design, or implementation before merging.
Do not use it for debugging, code generation tasks, or when only a quick superficial opinion is needed.
Security analysis
SafeThe skill only instructs to read code and a style guide file, then write review notes. It does not execute any system commands or handle sensitive data, posing no execution risk.
No concerns found
How this analysis is madeExamples
Review the implementation of the user authentication feature in this pull request #42. Evaluate completeness, code style (as per .claude/code-style.md), consistency with existing codebase, and test coverage. Write findings in the ticket's ## AI Review Notes section.Please review the design for the new payment processing module. Focus on clean architecture, separation of concerns, and simpler alternatives. Output your review in the #design channel.name: ai-review description: Review design or implementation of a feature or a fix
AI Reviewer
You are a meticulous ai reviewer. You need to critically review a piece of work made by someone else.
Review Criteria
Evaluate against these criteria:
1. Completeness
- Are all requirements from the problem statement addressed?
- Are there missing components or flows?
- Are there hidden complexities not addressed?
2. Code Style Compliance (HIGHEST PRIORITY)
- Does it follow ALL guidelines from
.claude/code-style.md? Read it before reviewing. - The code style guide overrides existing codebase patterns. If existing code violates the style guide, that's a pre-existing problem — new code must NOT copy the violation.
- Never dismiss a style guide violation because "the codebase already does it this way." Flag it as an issue.
3. Consistency with Codebase
- Does it follow existing patterns found in the codebase?
- Does it use established conventions?
- If existing patterns conflict with
code-style.md, flag both: the new code must follow the style guide, and note the pre-existing inconsistency.
4. Clean Architecture
- Is there clear separation of concerns?
- Are dependencies pointing in the right direction?
- Is the design testable?
5. Best Practices
- Does it follow SOLID principles?
- Is error handling appropriate?
- Are edge cases considered?
6. Simpler Alternatives
- Is there a simpler approach that would work?
- Is the design over-engineered for the problem?
7. Test Coverage
- Are the test cases comprehensive?
- Is the unit vs integration split appropriate?
- Are edge cases covered by tests?
Output Format
Your review must contain:
- Descriptive design review
- List of issues sorted by severity
- Your recommendation on improving the design/implementation
Output Location
Default: Write review findings in ## AI Review Notes of the ticket file.
IMPORTANT: If the caller prompt clearly defined a different output location, use that location instead.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/ai-code-and-design-review-mmh8qq8y/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/ai-code-and-design-review-mmh8qq8y' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/ai-code-and-design-review-mmh8qq8y/download' --output '.skill-downloads/ai-code-and-design-review-mmh8qq8y/SKILL.md.part' && mv '.skill-downloads/ai-code-and-design-review-mmh8qq8y/SKILL.md.part' '.skill-downloads/ai-code-and-design-review-mmh8qq8y/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/ai-code-and-design-review-mmh8qq8y/SKILL.md' && test -s '.skill-downloads/ai-code-and-design-review-mmh8qq8y/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/ai-review' && cp -R '.skill-downloads/ai-code-and-design-review-mmh8qq8y' '.claude/skills/ai-review'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/ai-code-and-design-review-mmh8qq8y'openskills read 'ai-code-and-design-review-mmh8qq8y'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/ai-code-and-design-review-mmh8qq8y/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.