Code Review Claude Skills
2 032 code review skills from 387 authors. They read someone else's code and work through changes before those land. Half of them fit into 1 560 tokens or less — that is what one costs your context window when the agent loads it. 210 ship runnable scripts rather than instructions alone. 3 of them cannot work without an MCP server, most often rube. We also found 250 copies of these same skills sitting in other people's repositories — counted once here, not 250 times.
2 032 unique 387 authors 1 262 updated this month 280 from vendors
Improve code quality and maintainability through systematic identification of code smells and application of proven refactoring patterns.
Manage Git repositories and collaborative workflows — branching strategies, commit hygiene, conflict resolution, pull requests, hooks, and .gitignore management.
Analyze source code for security vulnerabilities using static analysis tools, custom rules, and CI-integrated scanning pipelines.
Applies abstract interpretation using different abstract domains (intervals, octagons, polyhedra, sign, congruence) to statically analyze program variables and infer invariants, value ranges, and relationships. Use when analyzing program properties, inferring loop invariants, detecting potential errors, or understanding variable relationships through static analysis.
Performs abstract interpretation over source code to infer possible program states, variable ranges, and data properties without executing the program. Reports potential runtime errors including out-of-bounds accesses, null dereferences, type inconsistencies, division by zero, and integer overflows. Use when analyzing code for potential runtime errors, performing static analysis, checking safety properties, or verifying program behavior without execution.
Generates clear and structured pull request descriptions from code changes. Use when Claude needs to: (1) Create PR descriptions from git diffs or code changes, (2) Summarize what changed and why, (3) Document breaking changes with migration guides, (4) Add technical details and design decisions, (5) Provide testing instructions, (6) Enhance descriptions with security, performance, and architecture notes, (7) Document dependency changes. Takes code changes as input, outputs comprehensive PR description in Markdown.
Automatically generates change logs from git commits, patches, and pull requests. Use when preparing software releases, creating version summaries, or maintaining CHANGELOG.md files. Analyzes commit messages (including conventional commits), diff/patch files, and PR data to produce categorized Markdown change logs organized by type (Features, Bug Fixes, Breaking Changes, etc.). Ideal for release notes, version updates, and automated changelog maintenance.
Analyze codebases to identify reusable code patterns, duplications, and implementation patterns for future development. Use when refactoring code, identifying technical debt, finding opportunities for abstraction, or documenting common patterns in a directory or module. Outputs pattern catalogs, refactoring suggestions, and reusable template code.
Suggest and apply code refactorings to improve readability, maintainability, and code quality. Use this skill when improving existing code structure, eliminating code smells, applying design patterns, simplifying complex logic, extracting duplicated code, renaming for clarity, or preparing code for new features. Provides specific before/after examples, explains benefits, identifies risks, and ensures behavior preservation through tests.
Conduct comprehensive code reviews identifying bugs, security issues, performance problems, code quality concerns, and best practice violations. Use when reviewing pull requests, examining code changes, evaluating new code, assessing code quality, or providing feedback on implementations. Analyzes code for correctness, security vulnerabilities, performance bottlenecks, maintainability issues, test coverage, documentation quality, and adherence to coding standards. Produces structured markdown reviews with categorized findings, severity ratings, specific examples, and actionable recommendations. Triggers when users ask to review code, check pull requests, evaluate implementations, find bugs, or assess code quality.
Identify and report code smells indicating poor design or maintainability issues in Python code, including duplicate code, magic numbers, hardcoded values, God classes, feature envy, inappropriate intimacy, data clumps, primitive obsession, and long parameter lists. Use when conducting code quality audits, preparing for refactoring, improving codebase maintainability, or performing design reviews. Produces markdown reports with severity ratings, locations, descriptions, and specific refactoring recommendations with before/after examples. Triggers when users ask to find code smells, identify design issues, suggest refactorings, improve code quality, or detect maintainability problems.
Generate abstract Control Flow Graph (CFG) representations of programs showing loops, branches, and function calls for static analysis or verification. Use when users need to: (1) Visualize program control flow structure, (2) Generate CFGs for static analysis tools, (3) Create control flow abstractions for formal verification, (4) Analyze program paths and reachability, (5) Document program structure. Supports both function-level (intraprocedural) and program-level (interprocedural) analysis with multiple output formats (textual, DOT/Graphviz, JSON).
Recommends appropriate software design patterns based on problem descriptions, requirements, or code scenarios. Use when designing software architecture, refactoring code, solving common design problems, or choosing between design approaches. Analyzes the problem context and suggests suitable creational, structural, behavioral, architectural, or concurrency patterns with implementation guidance and trade-off analysis.
Identify design quality issues in code including high coupling, low cohesion, God classes, long methods, and other code smells. Use when: (1) Reviewing code architecture and design quality, (2) Identifying refactoring opportunities, (3) Detecting God classes or classes with too many responsibilities, (4) Finding high coupling or low cohesion issues, (5) Analyzing code maintainability and technical debt. Detects coupling smells, cohesion problems, complexity issues, size violations, and encapsulation problems with actionable refactoring suggestions.
Intelligent code refactoring using IDE-level tools (rename, find-references, go-to-definition), AST-aware pattern matching, and TDD verification. Use for safe, large-scale refactoring with precision.
Restructure and improve Isabelle or Coq proofs to enhance readability, modularity, and maintainability without changing semantics. Use when proofs are long and monolithic, have repeated patterns, use unclear naming, lack documentation, or when the user asks to refactor, clean up, improve, or reorganize their formal proofs.
Automatically generate user-facing release notes from git commits, pull requests, changelogs, and code changes. Use when preparing software releases, creating version announcements, documenting what changed between versions, or communicating updates to users. Analyzes commit messages, PR descriptions, and code diffs to produce categorized markdown release notes organized by New Features, Improvements, Bug Fixes, and Breaking Changes. Focuses on user-visible changes while filtering out internal/technical details. Triggers when users ask to generate release notes, create changelog, write version announcement, or summarize changes for a release.
Hardware verification tool for checking functional equivalence between two RTL designs (Verilog). Use when users need to: (1) Verify if two RTL versions are functionally equivalent, (2) Compare original vs. refactored RTL code, (3) Validate design changes or optimizations, (4) Identify semantic vs. cosmetic differences, (5) Generate counterexamples for non-equivalent designs. Analyzes interface alignment, state variables, logic differences, and produces detailed equivalence verdicts with plain language explanations. Particularly effective for design verification, code reviews, and regression testing of RTL modifications.
Analyzes and verifies semantic equivalence between two functions, classes, or modules by examining control flow, data flow, and observable behavior. Use when comparing code implementations (refactored vs original, different implementations of same functionality, migration verification), determining if two code artifacts produce identical behavior, identifying behavioral differences between code versions, or validating that code changes preserve semantics. Supports formal reasoning and symbolic execution approaches.
Analyze source code statically to detect potential functional bugs including null dereferences, incorrect condition checks, unreachable code, inconsistent state updates, logic errors, resource leaks, and type mismatches. Report suspicious code locations with detailed explanations, severity levels, and confidence assessments. Use when reviewing code for bugs, performing code audits, or when the user asks to find bugs, detect issues, analyze code for problems, or perform static analysis.
Verify code correctness statically against specifications using type checking, contract verification, and formal methods. Use when: (1) Verifying type safety and null safety in Python, Java, or C/C++ code, (2) Checking design-by-contract specifications (preconditions, postconditions, invariants), (3) Validating code against formal specifications, (4) Ensuring code quality and correctness before runtime, (5) Finding potential bugs through static analysis. Supports Python (mypy, contracts), Java (javac, JML), and provides verification scripts and contract specification guidelines.
Detect and analyze areas with high maintenance cost, poor design, or accumulated technical debt. Use this skill when reviewing codebases for quality issues, planning refactoring efforts, conducting code audits, assessing project health, identifying maintenance hotspots, or prioritizing technical improvements. Analyzes code smells, architectural issues, dependency problems, test quality, documentation gaps, and provides actionable recommendations with priority rankings.
|- Guidelines and best practices for refactoring consecutive prints, single-line string concatenations, and complex output blocks into triple-quoted multi-line string literals (''' or """) in Dart.
|- Guidelines for handling long lines in Dart code to adhere to the 80-column rule. The `lines_longer_than_80_chars` lint.
|- Guidelines for maintaining external Dart packages, covering versioning, publishing workflows, and pull request management. Use when updating Dart packages, preparing for a release, or managing collaborative changes in a repository.
The only path to a commit. Routed to when the user invokes /commit or otherwise instructs codeArbiter to persist staged changes. Nine gated phases — permission, branch, classification, verification (test/lint/secrets), behavioral proof, diff review, selective stage, message, commit. Nothing reaches version control without clearing every gate; "it looks good" is not authorization.
The behavior-preserving restructure gate. Routed to by /refactor for a rename, extract, inline, move, dedup, or internal-implementation swap. Six gated phases prove behavioral parity through unmodified pre-existing tests; any diff that classifies as `feat` is not a refactor and is routed to tdd. A modified pre-existing test is rejected as evidence — it is a behavior change in disguise.
The test-first gate. Routed to by /feature (after the spec is approved), /fix, and /refactor before any implementation code is written. Six gated phases — obligation scan, red, green, obligation verify, coverage, lint. No feature code exists before Phase 1 clears; nothing reaches commit-gate until all six are green.
The only path to a commit. Routed to when the user invokes /commit or otherwise instructs codeArbiter to persist staged changes. Nine gated phases — permission, branch, classification, verification (test/lint/secrets), behavioral proof, diff review, selective stage, message, commit. Nothing reaches version control without clearing every gate; "it looks good" is not authorization.
The behavior-preserving restructure gate. Routed to by /refactor for a rename, extract, inline, move, dedup, or internal-implementation swap. Six gated phases prove behavioral parity through unmodified pre-existing tests; any diff that classifies as `feat` is not a refactor and is routed to tdd. A modified pre-existing test is rejected as evidence — it is a behavior change in disguise.
The test-first gate. Routed to by /feature (after the spec is approved), /fix, and /refactor before any implementation code is written. Six gated phases — obligation scan, red, green, obligation verify, coverage, lint. No feature code exists before Phase 1 clears; nothing reaches commit-gate until all six are green.
Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing.
Open a pull request the only sanctioned way — clear every BLOCK-level review finding, then stage the PR. Never a direct write to the default branch.
Restructure code with behavioral parity proven through unmodified pre-existing tests, then refactor. No behavior change.
Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.
The only path to a commit. Routed to when the user invokes /commit or otherwise instructs codeArbiter to persist staged changes. Nine gated phases — permission, branch, classification, verification (test/lint/secrets), behavioral proof, diff review, selective stage, message, commit. Nothing reaches version control without clearing every gate; "it looks good" is not authorization.
The behavior-preserving restructure gate. Routed to by /refactor for a rename, extract, inline, move, dedup, or internal-implementation swap. Six gated phases prove behavioral parity through unmodified pre-existing tests; any diff that classifies as `feat` is not a refactor and is routed to tdd. A modified pre-existing test is rejected as evidence — it is a behavior change in disguise.
The test-first gate. Routed to by /feature (after the spec is approved), /fix, and /refactor before any implementation code is written. Six gated phases — obligation scan, red, green, obligation verify, coverage, lint. No feature code exists before Phase 1 clears; nothing reaches commit-gate until all six are green.
Open a pull request the only sanctioned way — clear every BLOCK-level review finding, then stage the PR. Never a direct write to the default branch.
Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing.
The behavior-preserving restructure gate. Routed to by /refactor for a rename, extract, inline, move, dedup, or internal-implementation swap. Six gated phases prove behavioral parity through unmodified pre-existing tests; any diff that classifies as `feat` is not a refactor and is routed to tdd. A modified pre-existing test is rejected as evidence — it is a behavior change in disguise.
Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.
The only path to a commit. Routed to when the user invokes /commit or otherwise instructs codeArbiter to persist staged changes. Nine gated phases — permission, branch, classification, verification (test/lint/secrets), behavioral proof, diff review, selective stage, message, commit. Nothing reaches version control without clearing every gate; "it looks good" is not authorization.
The test-first gate. Routed to by /feature (after the spec is approved), /fix, and /refactor before any implementation code is written. Six gated phases — obligation scan, red, green, obligation verify, coverage, lint. No feature code exists before Phase 1 clears; nothing reaches commit-gate until all six are green.
>- Pre-change blast-radius report for a symbol or file. Walks tree-sitting references, augments with a plain-text scan over non-parsed files (configs, plain docs), and clusters affected sites by feature (`_FEATURES.md`) or top-level package. Use when about to refactor, rename, or delete something in a repo you don't own — "what breaks if I change `validateUser`", "who calls this", "is this safe to remove", "where is this used", "blast radius", "impact analysis". This is the CONVERGENT pre-change risk skill — for "what is this repo?" use exploring-codebases; for "where is X?" use searching-codebases.
Close a GitHub issue with a synthesis comment as a flowing graph — validate the synthesis, post the closing comment, close, then run a pluggable callback (e.g. memory store) detached. Use when closing an issue should also capture the LEARNING (not just the diff log) and when the post-close work shouldn't block the close ack.
Multi-conversation methodology for iterative stateful work with context accumulation. Use when users request work that spans multiple sessions (research, debugging, refactoring, feature development), need to build on past progress, explicitly mention iterative work, work logs, project knowledge, or cross-conversation learning.
Apply semi-formal certificate reasoning to code analysis — patch verification, fault localization, patch equivalence. Use when reviewing patches, hunting bugs across scopes, comparing fixes, or when code reasoning requires tracing execution across files/modules. Triggers on code review, bug localization, patch comparison, name shadowing, scope analysis, regression checking.