7 refactoring skills for Claude Code — 66 techniques, 23 code smells from refactoring.guru
Skill Claude CodeCodex
Use when methods are too long, contain duplicate code, or have complex expressions that need simplification — covers Extract Method, Inline Method, Extract Variable, and 6 more techniques.
Skill Claude CodeCodex
Use when reviewing code for functional programming quality — covers Pure Functions, Immutability, Map/Filter/Reduce, Function Composition, Higher-Order Functions, Currying, Functors/Monads, and Pattern Matching with red flags and anti-patterns.
Skill Claude CodeCodex
Use when managing inheritance hierarchies, extracting shared behavior, deciding between inheritance and delegation, or dealing with Refused Bequest, Parallel Inheritance, or Speculative Generality smells.
Skill Claude CodeCodex
Use when responsibilities are in the wrong class, classes are too large or too small, or coupling between classes needs to change — covers Move Method, Extract Class, Hide Delegate, and 5 more techniques.
Skill Claude CodeCodex
Use when data handling needs improvement — encapsulating fields, replacing primitives with objects, replacing type codes, managing associations, or fixing Data Class and Primitive Obsession smells.
Skill Claude CodeCodex
Use when conditional logic is complex, nested, duplicated, or uses type codes instead of polymorphism — covers Decompose Conditional, Guard Clauses, Replace Conditional with Polymorphism, and 5 more techniques.
Skill Claude CodeCodex
Use when method interfaces are confusing, parameters are excessive, or method responsibilities are unclear — covers Rename Method, Add/Remove Parameter, Introduce Parameter Object, Preserve Whole Object, and 9 more techniques.
Skill Claude CodeCodex needs its repo
Use when the user asks to refactor code, review code quality, or fix code smells — orchestrates the full refactoring pipeline from detection through fix, with parallel worktree isolation per independent refactoring group.
Skill Claude CodeCodex
Use when you have identified a code smell and need to select the right refactoring technique, assess risk, and prioritize the work — maps all 23 code smells to specific fix paths, difficulty levels, and risk ratings.
Skill Claude CodeCodex
Use when you want to improve the signal-to-noise ratio of any code review. Teaches confidence scoring, false positive reduction, severity calibration, and when to escalate vs. flag. Load this skill alongside review-cheat-sheet to ensure your findings are well-calibrated before posting comments.
Skill Claude CodeCodex
Use when reviewing a REST API PR or design — covers resource naming, HTTP semantics, status codes, versioning, pagination, breaking vs non-breaking change classification, error response format, rate limiting, and idempotency, with a structured checklist for sign-off.
Skill Claude CodeCodex
Use when configuring or running static analysis in CI pipelines — covers tool selection by language, CI gate configuration, what to automate vs what to review, false positive management, and anti-patterns that undermine automated review value.
Skill Claude CodeCodex
Use when starting any code review and you need a single-page master reference that covers all review dimensions, maps each check to a deeper skill, and tells you when to stop the PR outright.
Skill Claude CodeCodex
Use when conducting a structured code review — covers the full review process across 7 quality dimensions (Logic/Correctness, Security, Performance, Maintainability, Error Handling, Testing, API Design) with actionable questions per dimension, severity classification for findings, and a final review checklist.
Skill Claude CodeCodex
Use when you need to allocate limited review time for maximum defect-detection yield — covers risk-based ordering, time-boxing, when to stop, diff-size thresholds, and anti-patterns that waste review bandwidth.
Skill Claude CodeCodex needs its repo
Use when writing review comments to ensure feedback is actionable, constructive, and clearly communicates what must change and why. Covers comment templates by severity, tone and framing, vague vs actionable comparisons, and when to use blocking vs suggesting comments.
Skill Claude CodeCodex
Use when you need to measure and improve review effectiveness — covers defect escape rate, false positive rate, review cycle time, comment resolution rate, reviewer agreement, and coverage metrics with formulas, healthy ranges, and anti-patterns to avoid.
Skill Claude CodeCodex
Use when reviewing code for SOLID principle violations and clean code quality issues — covers all 5 SOLID principles (SRP, OCP, LSP, ISP, DIP) and core practices (DRY, KISS, YAGNI, Law of Demeter) with detection red flags and fix strategies.
Skill Claude CodeCodex
Use when you need end-to-end examples of the full code review diagnostic flow — each walkthrough traces: detect the issue, calibrate confidence and severity, write the review comment, and decide the verdict. Covers security, performance, AI-generated code, and concurrency scenarios across Python, Go, TypeScript, and…
Skill Claude CodeCodex
Use when reviewing Rust code — covers ownership and borrowing pitfalls, lifetime annotation discipline, unsafe block justification, error handling with Result/Option, async Send/Sync constraints, trait design, and common anti-patterns. Load alongside review-accuracy-calibration to ensure findings are well-calibrated…
Skill Claude CodeCodex
Use when reviewing or designing search and indexing systems — covers Elasticsearch/OpenSearch mapping design, index lifecycle management, query patterns, aggregation patterns, pagination strategies, bulk indexing, PostgreSQL full-text search, and search anti-patterns with red flags and fix strategies across JSON…
Skill Claude CodeCodex
Use when reviewing code for security vulnerabilities — covers Injection, Broken Authentication, Sensitive Data Exposure, XXE, Broken Access Control, Security Misconfiguration, XSS, Insecure Deserialization, Vulnerable Components, Insufficient Logging, Secret Management, CSRF, Rate Limiting, and Input Validation with…
Skill Claude CodeCodex
Use when designing AI agents that improve from experience — covers learning signal detection, instinct extraction, confidence scoring, feedback loop architecture, pattern graduation pipelines, memory-backed learning, safety constraints, and self-learning anti-patterns with examples in TypeScript and Python.
Skill Claude CodeCodex
Master navigation and dispatch index for all 70 skills — invoke this skill first when unsure which skill covers your task. Maps common scenarios, tasks, and questions to the right skill via a quick dispatch table, domain category index, and decision FAQ.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: