Code Review

Use when the user asks to review this code, review a pull request for bugs, give feedback on an implementation, check a diff, or asks LGTM?. Produces a structured review with MUST/SHOULD/CONSIDER findings on correctness, security, performance and tests. Not for finding a bug's root cause (use dev-loop-debugging-strategy) or writing the PR text (use dev-loop-pr-writer).

45 stars 6 forksGit & Code Review

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add j4flmao/agent-skills --skill code-review
Manual install
git clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/dev-loop/code-review ~/.claude/skills/code-review

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Code Review

**Version:** 1.1.0
**Author:** j4flmao
**License:** MIT

---

## Purpose

Provide systematic, structured code reviews covering correctness, architecture, clarity, performance, security, and tests. Every finding is actionable, prioritized by severity, and anchored to a specific file and line.

---

## Agent Protocol

### Trigger

Exact user phrases: "review this code", "code review", "review PR", "check this implementation", "is this code good", "LGTM?", "feedback on code".

### Input Context

Before activating, verify:
- The code or diff to review is provided or accessible.
- The language/stack is known.
- The project's coding standards or conventions are available.

### Output Artifact

No file output. This skill produces structured review text.

### Response Format

Answer exactly:
```
## Code Review: {file/scope}

### [MUST] {short title}
- **File**: `src/path/file.ts:42`
- **Issue**: {what's wrong}
- **Why**: {impact}
- **Fix**: {suggested approach}

### [SHOULD] {short title}
...

### [CONSIDER] {short title}
...

### Positive
- {what's done well}
```

No preamble. No postamble. No explanations. No filler/hedging/transitions. Compress output -- why use many token when few do trick. No explanations of what code review is.

### Completion Criteria

This skill is complete when:
- [ ] All findings are classified with severity [MUST]/[SHOULD]/[CONSIDER].
- [ ] Every finding includes exact file and line number.
Read the full skill on GitHub

Details

Skill name
code-review
Path
skills/dev-loop/code-review/SKILL.md
License
MIT
Repo updated
17 November 2026

FAQ

What does the Code Review skill do?

Use when the user asks to review this code, review a pull request for bugs, give feedback on an implementation, check a diff, or asks LGTM?. Produces a structured review with MUST/SHOULD/CONSIDER findings on correctness, security, performance and tests. Not for finding a bug's root cause (use dev-loop-debugging-strategy) or writing the PR text (use dev-loop-pr-writer).

How do I install the Code Review skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill code-review. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Code Review popular?

It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.

Related skills

Agent Observability

45

j4flmao/agent-skills

Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).

DevOps & Cloud

AI Agent Architectures

45

j4flmao/agent-skills

Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).

AI, LLMs & Agents

AI Agent Core Loop

45

j4flmao/agent-skills

Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).

AI, LLMs & Agents

Data Data Versioning

45

j4flmao/agent-skills

Use when the user asks about data versioning with DVC or lakeFS, Git-like branches for data, data snapshots, rollback of a bad load or reproducible training data. Produces versioning workflow, branching model and reproducibility checks. Not for Iceberg/Delta time travel (use data-data-lake) or experiment logging (use ml-experiment-tracking).

Git & Code Review

Humanizer Ru

38

jeremybrasher/grokbot-skills

Проверяет русскоязычный текст на следы машинной генерации (40 regex-маркеров с реестром доказательств) и по явной просьбе пользователя переписывает его естественным языком. Демо: vladimir-human.github.io/humanizer-ru. Отвечает на просьбы вида «очеловечь», «убери гпт-шность», «звучит как нейросеть», «проверь на ИИ», «убери штампы», «убери канцелярит», «сделай живым». Detects AI-generated Russian text and humanizes it on request. Не предназначен для текста не на русском, исходного кода, юридических документов и художественной прозы.

Git & Code Review11

Dev Loop Changelog Generator

45

j4flmao/agent-skills

Use when the user asks to generate a CHANGELOG.md, release notes, semantic versioning bumps, or automate changelogs from conventional commits with release-please, changesets or semantic-release. Produces changelog entries and release automation config. Not for PR descriptions (use dev-loop-pr-writer) or branching strategy (use dev-loop-git-workflow).

Git & Code Review

Browse the most popular Claude skills, all git & code review skills, or write your own with the skills generator.