Code Review

Code Review is a Quality skill for Claude Code, published by kdlbs in kandev.

679 stars95 forkson kdlbs/kandevAdded 2026/08/23+3% in starsRepository updated 2026/08/23

acpagent-orchestrationagentic-aiagentic-development-environmentai-agentsclaude-codecode-reviewcoding-agentsdeveloper-toolsgithub-copilotgolangkanbannextjsopen-sourceself-hostedtask-managertuivibe-codingworkflow-automationworktrees

Install in seconds

Install Code Review

Copy Code Review into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/kdlbs/kandev/tree/main/.agents/skills/code-review ~/.claude/skills/code-review

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/kdlbs/kandev.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .agents/skills/code-review/SKILL.md in kdlbs/kandev
Installs to: ~/.claude/skills/code-review
Collection: One of 25 skills cataloged from this repository
Category: Quality — 1354 skills

What Code Review does

Code Review reviews changed code for quality, security, and architecture compliance when you explicitly ask for a local review or a PR finding needs investigation. It expects file-and-line findings with reasons and fixes.

Code Review is cataloged under Quality on DirSkills. Code Review comes from a repository tagged acp, agent-orchestration, agentic-ai, agentic-development-environment and ai-agents.

Documentation

README

Excerpt

Code Review

Planner Entry

Run this local review only when the user explicitly asks or an actionable PR/CI finding requires it. Do not use it automatically before opening a PR: the two configured PR AI reviewers are the semantic-review gate.

Review the current changes in the codebase (Go backend + Vite/React SPA monorepo). Every finding needs a file_path:line_number reference, an explanation of why it matters, and a concrete fix.

Start from intent and evidence: read the spec/task first when available, then changed tests before production code. Tests reveal the expected behavior and whether the change is actually verified.

Available skills

/tdd — Recommend when flagging untested logic. The author can use this to add tests.

Steps

This is the opening of the README. Read the full README on GitHub.

Commands Code Review provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/tdd
/mobile-parity

Frequently asked about Code Review

What else does kdlbs publish alongside Code Review?
Code Review is one of 25 skills that DirSkills catalogs from kdlbs/kandev, the repository it ships in. Its siblings there include ACP Debug, Add Integration and Clean Branches. Each one is a separate skill with its own page in this directory, installs the same way Code Review does, and is maintained by kdlbs in that same repository. The rest of the collection is listed on the kdlbs/kandev page.
How does Code Review compare to other Quality skills?
Code Review ranks #1072 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Code Review against them. Open each page to compare what they document and how they install.