Comprehensive code refactoring guide based on Martin Fowler's catalog and Clean Code principles, designed for AI agents and LLMs. Contains 43 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionrefactorExecute the skills CLI command in your project's root directory to begin installation:
Fetches refactor from pproenca/dot-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate refactor. Access via /refactor in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
15
total installs
15
this week
95
GitHub stars
0
upvotes
Run in your terminal
15
installs
15
this week
95
stars
Comprehensive code refactoring guide based on Martin Fowler's catalog and Clean Code principles, designed for AI agents and LLMs. Contains 43 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation.
Reference these guidelines when:
| Priority | Category | Impact | Prefix |
|---|---|---|---|
| 1 | Structure & Decomposition | CRITICAL | struct- |
| 2 | Coupling & Dependencies | CRITICAL | couple- |
| 3 | Naming & Clarity | HIGH | name- |
| 4 | Conditional Logic | HIGH | cond- |
| 5 | Abstraction & Patterns | MEDIUM-HIGH | pattern- |
| 6 | Data Organization | MEDIUM | data- |
| 7 | Error Handling | MEDIUM | error- |
| 8 | Micro-Refactoring | LOW | micro- |
struct-extract-method - Extract Method for Long Functionsstruct-single-responsibility - Apply Single Responsibility Principlestruct-extract-class - Extract Class from Large Classstruct-compose-method - Compose Method for Readable Flowstruct-function-length - Keep Functions Under 20 Linesstruct-replace-method-with-object - Replace Method with Method Objectstruct-parameter-object - Introduce Parameter Objectcouple-dependency-injection - Use Dependency Injectioncouple-hide-delegate - Hide Delegate to Reduce Couplingcouple-remove-middle-man - Remove Middle Man When Excessivecouple-feature-envy - Fix Feature Envy by Moving Methodscouple-interface-segregation - Apply Interface Segregation Principlecouple-preserve-whole-object - Preserve Whole Object Instead of Fieldsname-intention-revealing - Use Intention-Revealing Namesname-avoid-abbreviations - Avoid Abbreviations and Acronymsname-consistent-vocabulary - Use Consistent Vocabularyname-searchable-names - Use Searchable Namesname-avoid-encodings - Avoid Type Encodings in Namescond-guard-clauses - Replace Nested Conditionals with Guard Clausescond-polymorphism - Replace Conditional with Polymorphismcond-decompose - Decompose Complex Conditionalscond-consolidate - Consolidate Duplicate Conditional Fragmentscond-special-case - Introduce Special Case Objectcond-lookup-table - Replace Conditional with Lookup Tablepattern-strategy - Extract Strategy for Algorithm Variantspattern-template-method - Use Template Method for Shared Skeletonpattern-factory - Use Factory for Complex Object Creationpattern-open-closed - Apply Open-Closed Principlepattern-composition-over-inheritance - Prefer Composition Over Inheritancepattern-extract-superclass - Extract Superclass for Common Behaviordata-encapsulate-collection - Encapsulate Collectiondata-replace-primitive - Replace Primitive with Objectdata-encapsulate-record - Encapsulate Record into Classdata-split-variable - Split Variable with Multiple Assignmentsdata-replace-temp-with-query - Replace Temp with Queryerror-exceptions-over-codes - Use Exceptions Instead of Error Codeserror-custom-exceptions - Create Domain-Specific Exception Typeserror-fail-fast - Fail Fast with Preconditionserror-separate-concerns - Separate Error Handling from Business Logicmicro-remove-dead-code - Remove Dead Codemicro-inline-variable - Inline Trivial Variablesmicro-simplify-expressions - Simplify Boolean Expressionsmicro-rename-for-clarity - Rename for ClarityRead individual reference files for detailed explanations and code examples:
references/{prefix}-{slug}.mdFor the complete guide with all rules expanded: AGENTS.md
Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
pproenca/dot-skills
pproenca/dot-skills
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
refactor reduced setup friction for our internal harness; good balance of opinion and flexibility.
Registry listing for refactor matched our evaluation — installs cleanly and behaves as described in the markdown.
We added refactor from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Registry listing for refactor matched our evaluation — installs cleanly and behaves as described in the markdown.
refactor reduced setup friction for our internal harness; good balance of opinion and flexibility.
refactor is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
refactor fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
I recommend refactor for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Useful defaults in refactor — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
Solid pick for teams standardizing on skills: refactor is focused, and the summary matches what you get after install.
showing 1-10 of 56