Skip to content
SkillModel-led952 tokens in use

Code Reviewer

Reviews pull requests for bugs, security issues, N+1 queries and test gaps, and writes a report ranked from critical to minor with a verdict.

12,471 stars on the repository MIT LicenseJeffallan/claude-skills · skills/code-reviewer
/plugin marketplace add jeffallan/claude-skills /plugin install fullstack-dev-skills@fullstack-dev-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Code Reviewer costs

129tokens idle
952tokens in use
7,112tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter15/15
  • Structure22/25
  • Examples15/15
  • Output15/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity36
  • Momentum40

Code Reviewer runs a five-step review: understand the context, check structure, inspect the details, review the tests and write the feedback. It summarizes the pull request intent in one sentence before it begins and reports critical findings as soon as it sees them.

The skill is restricted to the Read, Grep and Glob tools, so it can look at code and cannot change it.

What You Get

  • A summary of the change with an overall assessment
  • Critical, major and minor issues, each with specific actionable advice
  • Specific praise for good patterns
  • Questions for the author
  • A verdict: approve, request changes or comment

Common Use Cases

  • Reviewing a pull request before merge
  • Auditing a module for code quality
  • Spotting N+1 queries and SQL injection risks
  • Finding refactoring opportunities
  • Responding to review comments on your own change

What Makes It Unique

It declares allowed-tools of Read, Grep and Glob, which keeps the review read-only. Six reference files cover a review checklist, common issues, feedback examples, a report template, spec compliance and receiving feedback, two of which are adapted from the obra superpowers project under the MIT license.

Under The Hood

The skill is a SKILL.md with six reference files and no scripts. Its frontmatter limits the agent to reading and searching files, so it does not run shell commands, write files, fetch web pages or call outside APIs. It loads the checklist and example references when the task needs them.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers