Skip to content
SkillModel-led4,551 tokens in use

code-review-and-quality

Review every change on five axes with severity labels, change sizing rules and a checklist before it merges.

119,377 stars on the repository MIT Licenseaddyosmani/agent-skills · skills/code-review-and-quality
npx skills add addyosmani/agent-skills --skill code-review-and-quality
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing code-review-and-quality costs

83tokens idle
4,551tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. 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

shelldetected

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
  • Frontmatter12/15
  • Structure25/25
  • Examples15/15
  • Output10/15
  • Size11/15
  • Resources10/15

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 activity96
  • Maintenance100
  • Community76
  • Maturity32
  • Momentum40

Code Review and Quality guides an agent through reviewing a diff or pull request, whether the code came from itself, another agent or a person. Each change is judged on correctness, readability, architecture, security and performance.

The skill sets an approval standard of improving overall code health, adds structural remedies for common problems and covers change descriptions, review speed, dependency upgrades and dead code.

What You Get

  • A five-axis review method with concrete questions per axis
  • Structural remedies such as replacing conditional chains with a typed model
  • Change sizing and description guidance
  • A review checklist template and verification list

Common Use Cases

  • Reviewing a pull request before merge
  • Evaluating code written by another agent
  • Reviewing a bug fix and its regression test
  • Reviewing a dependency upgrade

What Makes It Unique

The skill pairs review criteria with practices for the reviewer: finding presumptive blockers such as a refactor that moves complexity around, confirming the checkout is clean before running probes, and treating zero findings as a valid result. It also covers a multi-model pattern where one model writes and another reviews.

Under The Hood

The skill is a single SKILL.md of instructions. It links to the security and performance checklists in the repository and to the security-and-hardening, performance-optimization and constraint-driven-development skills. The reviewer may run git status, git rev-parse and the project’s test suite on the checkout.

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