Skill

code-review

AI-powered code review patterns. Use when reviewing code changes, checking code quality, finding bugs or security issues, or running fix-review cycles.

npx claudepluginhub nassimbf/ftitos-claude-code

Tool Access

This skill uses the workspace's default tool permissions.

Preview

AI-powered code review patterns for autonomous development workflows.

SKILL.md

Similar Skills

cache-components

139.3k

Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.

cache-components

mcp-builder

124.2k

Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).

9 files

anthropics-skills-13

Stats

Stars2

Forks0

Last CommitApr 18, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Code Review

AI-powered code review patterns for autonomous development workflows.

When to Use

Review code changes or staged/uncommitted changes

Check code quality, find bugs, or security issues

PR review or pull request feedback

Implement a feature and review it

Fix issues found in review

How to Review

1. Run Automated Checks First

Before any manual review, run:

# Build check (type errors) npm run build # or equivalent # Lint check npm run lint # or equivalent # Test suite npm test # or equivalent

If automated checks fail, report as highest priority. Only proceed to manual review if all pass.

2. Review Focus Areas

Sandbox / production path consistency -- same response shapes in all code paths

API response shape matches frontend expectations -- fields present in both

SELECT clause completeness -- new columns included in queries

Error handling with rollback -- optimistic updates recover on failure

Security -- auth checks, input validation, injection prevention

3. Present Results

Group findings by severity:

Critical: Blocks ship (security, data loss, auth bypass)

High: Should fix before merge (logic errors, missing validation)

Medium: Improve when convenient (code quality, naming)

4. Fix-Review Cycle

For autonomous workflows:

Implement the requested feature

Run automated checks

Review code for issues

Fix each issue systematically

Re-run checks and review until clean

Review Checklist

All automated checks pass (build, lint, test)

No hardcoded secrets or credentials

Input validated at system boundaries

Error handling present for all I/O operations

No N+1 query patterns introduced

Response shapes consistent across code paths

Destructive actions have confirmation

New code has corresponding tests

Code Review

AI-powered code review patterns for autonomous development workflows.

When to Use

Review code changes or staged/uncommitted changes
Check code quality, find bugs, or security issues
PR review or pull request feedback
Implement a feature and review it
Fix issues found in review

How to Review

1. Run Automated Checks First

Before any manual review, run:

# Build check (type errors)
npm run build    # or equivalent

# Lint check
npm run lint     # or equivalent

# Test suite
npm test         # or equivalent

If automated checks fail, report as highest priority. Only proceed to manual review if all pass.

2. Review Focus Areas

Sandbox / production path consistency -- same response shapes in all code paths
API response shape matches frontend expectations -- fields present in both
SELECT clause completeness -- new columns included in queries
Error handling with rollback -- optimistic updates recover on failure
Security -- auth checks, input validation, injection prevention

3. Present Results

Group findings by severity:

Critical: Blocks ship (security, data loss, auth bypass)
High: Should fix before merge (logic errors, missing validation)
Medium: Improve when convenient (code quality, naming)

4. Fix-Review Cycle

For autonomous workflows:

Implement the requested feature
Run automated checks
Review code for issues
Fix each issue systematically
Re-run checks and review until clean

Review Checklist

All automated checks pass (build, lint, test)
No hardcoded secrets or credentials
Input validated at system boundaries
Error handling present for all I/O operations
No N+1 query patterns introduced
Response shapes consistent across code paths
Destructive actions have confirmation
New code has corresponding tests