code-quality-review — Claude Code skill: what it does, how to install
code-quality-review evaluates code across eight dimensions, prioritizing correctness and security risks over cosmetic formatting.
MIT ★ 587 updated 2026-10-26
/plugin marketplace add rsmdt/the-startup
/plugin install team@the-startupWhat code-quality-review does
The skill evaluates code changes across correctness, design, readability, security, performance, testability, accessibility, and error handling. Each finding follows a structured format containing priority, exact code location, impact analysis, and a concrete remediation snippet.
A built-in constraint bars the agent from nitpicking minor styling issues at the expense of substantive logic flaws. When UI or input-output paths change, the workflow verifies accessibility standards and edge-case handling against project reference checklists.
What it helps with
- inspect code changes for logic bugs and security flaws
- audit user-facing paths for accessibility and error handling
- prioritize technical debt by operational impact
- generate actionable remediation snippets for code findings
Example prompts for the agent
- Run code-quality-review on the latest changes in src/auth
- Review checkout.ts using code-quality-review and focus on error handling
- Perform a code-quality-review check on my staged pull request
How to install code-quality-review
1Plugin marketplace
/plugin marketplace add rsmdt/the-startup/plugin install team@the-startupThis installs the whole team plugin with all its skills
2Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill code-quality-review -a claude-code3Manually: put the files in place
~/.claude/skills/code-quality-review/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/code-quality-review/
1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill code-quality-review -a codex2Manually: put the files in place
.agents/skills/code-quality-review/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill code-quality-review -a cursor2Manually: put the files in place
.cursor/skills/code-quality-review/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install rsmdt/the-startup plugins/team/skills/quality/code-quality-review2Manually: put the files in place
.github/skills/code-quality-review/SKILL.md1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill code-quality-review -a gemini-cli2Platform CLI
gemini skills install https://github.com/rsmdt/the-startup --path plugins/team/skills/quality/code-quality-reviewManually: put the files in place
.devin/skills/code-quality-review/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about code-quality-review
How to install code-quality-review in Claude Code?
Add the marketplace source with /plugin marketplace add rsmdt/the-startup, then install the package by running /plugin install team@the-startup.
What does code-quality-review do?
It inspects code changes across eight quality dimensions and outputs prioritized findings complete with impact analysis and fix instructions.
How does the skill prioritize review findings?
Issues are categorized from LOW to CRITICAL. Correctness, security risks, and user impact always take precedence over low-value stylistic comments.
Source text
SKILL.md · MIT
---
name: code-quality-review
description: Unified code review skill for correctness, design, readability, security, performance, testability, accessibility, and error-handling conventions. Use when reviewing changes, enforcing quality standards, or identifying technical debt.
---
## Persona
Act as a senior reviewer who evaluates code quality holistically and provides prioritized, actionable feedback.
**Review Target**: $ARGUMENTS
## Interface
ReviewFinding {
priority: CRITICAL | HIGH | MEDIUM | LOW
dimension: Correctness | Design | Readability | Security | Performance | Testability | Accessibility | ErrorHandling
title: string
location: string
observation: string
impact: string
suggestion: string
}
State {
target = $ARGUMENTS
findings = []
strengths = []
}
## Constraints
**Always:**
- Prioritize issues that affect correctness, security, and user impact first.
- Include observation, impact, and concrete fix for each finding.
- Verify accessibility and error-handling standards when UI/I/O code is touched.
- Keep feedback constructive and implementation-focused.
**Never:**
- Focus on stylistic nits over substantive risks.
- Report findings without clear remediation guidance.
- Ignore security/performance/accessibility implications on user-facing paths.
## Reference Materials
- `reference/anti-patterns.md` — Common code anti-patterns and remediation strategies
- `reference/feedback-patterns.md` — Effective code review feedback patterns and templates
- `reference/checklists.md` — Per-dimension quality checklists for thorough reviews
## Workflow
### 1. Gather Context
- Understand change scope, intent, and affected user/system paths.
### 2. Review Core Dimensions
- Check correctness, design, readability, security, performance, and testability.
### 3. Apply Cross-Cutting Standards
- Validate accessibility and error-handling behavior where relevant.
### 4. Prioritize Findings
- Rank by impact and urgency; avoid noisy low-value comments.
### 5. Deliver Review
- Provide concise summary, strengths, and prioritized actionable findings.
© Rudolf S. · MIT · rsmdt/the-startup