Tooluck logoTooluck
SKILL.md

code-review-web

Agent skill fromrampstackco/claude-skills

Review web application code for bugs, security issues, performance problems, and stack-specific anti-patterns. Use this skill whenever the user wants to review code, debug a production issue, investigate a build failure, audit security, or check a PR before merging. Triggers on code review, review my code, debug, build error, broken, not working, why is X failing, check this code, security check, PR review, audit code, refactor. Also triggers when investigating 4xx or 5xx errors, deploy failures, environment variable issues, and CMS integration problems.

How to install code-review-web

install code-review-web
# install the claude-skills pack with the skills CLI
npx skills add rampstackco/claude-skills

# or add only this skill to Claude Code: copy the folder

skills/code-review-web/

# into

~/.claude/skills/code-review-web/ (all projects)

.claude/skills/code-review-web/ (one project)

skills/code-review-web/SKILL.md

MITFull file
1# Code Review for Web
2
3Review and debug web application code with a focus on the patterns that actually break production. Stack-agnostic principles in SKILL.md. Stack-specific patterns in references.
4
5---
6
7## When to use
8
9- Reviewing a pull request before merging
10- Debugging a production issue
11- Investigating a build failure
12- Auditing security or performance of existing code
13- Investigating environment variable or configuration issues
14- Triaging a "the site is broken" report
15
16## When NOT to use
17
18- Writing a new feature spec (use `pm-spec-writing`)
19- Pre-launch QA against the running site (use `qa-testing`)
20- Performance deep-dive on Core Web Vitals (use `performance-optimization`)
21- Deep accessibility compliance review (use `accessibility-audit`)
22
23---
24
25## Required inputs
26
27- The code, PR, error message, or symptom under review
28- Access to logs (build logs, function logs, server logs) if debugging
29- The stack (framework, hosting, database) - even at high level
30
31If just a symptom is provided ("the site is broken"), the workflow's first step is gathering enough context to investigate.
32
33---
34
35## The framework: 5 review dimensions
36
37Every code review covers five dimensions. Pick the depth based on the situation.
38
39### 1. Correctness
40
41Does the code do what it claims to do?
42
43- Logic matches the intent stated in the spec or PR description
44- Edge cases handled (empty states, error states, network failures)
45- Off-by-one errors, null/undefined handling, async race conditions
46…

Excerpt shown under the repository's MIT license.

More skills in claude-skills

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates