Skip to content
SkillModel-led101 tokens in use

Refactoring.Guru

Refactoring.Guru-inspired rules for diagnosing code smells, choosing the smallest treatment and stopping on time.

3,324 stars on the repository MIT Licenseciembor/agent-rules-books · refactoring-guru
npx skills add ciembor/agent-rules-books --skill refactoring-guru
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Refactoring.Guru costs

31tokens idle
101tokens in use
13,275tokens, 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 →
Needs attention
  • Frontmatter11/15
  • Structure0/25
  • Examples0/15
  • Output2/15
  • Size15/15
  • 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 →
Fair
  • Development activity44
  • Maintenance72
  • Community52
  • Maturity28
  • Momentum40

This skill loads a compact rule set inspired by the Refactoring.Guru smell and technique catalog. It tells a coding agent to diagnose a smell first, name its cost and the verification path, then apply the smallest technique that treats it.

It groups smells into bloaters, object-orientation abusers, change preventers, dispensables and couplers, and gives pre-checks for extraction, data reorganization and generalization.

What You Get

  • A mini rule set with decision rules, trigger rules and a closing checklist for smell-driven refactoring
  • A nano version for tight context budgets and a full version with the longer catalog notes
  • A skill description that makes the agent load the rules for smell diagnosis and technique choice

Common Use Cases

  • Diagnosing a long method and picking extract method or replace temp with query
  • Removing a middle man or hiding a delegate to cut navigation through object chains
  • Deleting dead code after checking reflection, serialization and plugin use
  • Applying the rule of three before removing duplication

What Makes It Unique

It organises the work by smell category and names the technique to try for each trigger. It also warns when a mechanical treatment is the wrong call, such as a simple conditional or a clear duplicate, and asks that untreated smells are recorded and not hidden. The Fowler-based refactoring set in the repository is organised around the sequence of the change.

Under The Hood

The skill is a SKILL.md with a name and description, plus Markdown files holding the mini, nano and full versions of the rules. The SKILL.md tells the agent to read the mini file before design or code decisions and the full file only for harder tradeoffs. It contains no scripts. It does not fetch web pages, call APIs, run commands or write files; the agent only reads the rule text.

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