Skill directory · Code quality

Code Review and Code Quality agent skills

Skills for reviewing pull requests, refactoring, linting and enforcing code standards. They turn review into a repeatable pass with named checks, so findings are consistent across every change.

94 listed skills
29 repositories
27 with full pages

Every dot is a listed code review and code quality skill, sorted by score.ABCD

Highest-scoring code review skills in the October 22, 2026 snapshot: go-coding-standards from eduardo-sl/go-agent-skills (95/100), pr-babysitter from mblode/agent-skills (91/100) and dimensional-analysis from trailofbits/skills (89/100). Scores come from the Suede Skill Check.

Build a shortlist for your task →

All 94 code review skills

Skill	Repository	What it does
anti-patterns 82/100 · B	avelikiy/great_cto	Lists known SDLC anti-patterns that agents must reject when reviewing architecture, plans, code, or post-mortems, used by the architect, pm, senior-dev, and l3-support agents.
architecture-optimization 76/100 · C	wondelai/skills	Guides a slow, tangled codebase toward being measurably fast, cleanly bounded, and readable, orchestrating eight skills phase by phase with questions at each decision.
birdview 86/100 · B	Qiuner/birdview	Maps evidence-linked architecture, constraints and change scope, and reviews architecture improvement opportunities when requested or when a project enables auto mode.
clean-code 81/100 · B	wondelai/skills	Guides writing readable, maintainable code through disciplined naming, small functions, and clean error handling, including readability reviews of pull requests.
code-auditor 75/100 · C	mhattingpete/claude-skills-marketplace	Audits a codebase across architecture, code quality, security, performance, testing, and maintainability to identify technical debt and give a health check.
code-refactor 75/100 · C	mhattingpete/claude-skills-marketplace	Performs bulk refactoring such as renaming variables and functions across files, replacing deprecated code patterns, and updating API calls.
code-review 83/100 · B	coderabbitai/skills	Runs CodeRabbit CLI reviews, retrieves saved local or GitHub PR fix prompts, and interprets CodeRabbit authentication and review output.
code-review 84/100 · B	phuryn/pm-skills	Reviews code for actionable defects, centering on correctness with performance and security as optional sub-cases, and tries to refute every candidate finding before reporting.
code-reviewer 84/100 · B	jeffallan/claude-skills	Reviews code diffs and files for bugs, security vulnerabilities, code smells, N+1 queries, and naming issues, then produces a prioritized, structured review report.
codebase-architecture 84/100 · B	mblode/agent-skills	Designs module interfaces, deepens shallow modules, and installs enforceable repository guardrails and agent wayfinding to harden a repo.
dimensional-analysis 89/100 · B	trailofbits/skills	Audits code for unit and decimal-scaling bugs and annotates it with dimensional comments recording the units of each value.
finding-duplicate-functions 76/100 · C	obra/superpowers-lab	Audits a codebase for semantic duplication, finding functions that do the same thing under different names or implementations, especially in LLM-generated code.
go-coding-standards 95/100 · A	eduardo-sl/go-agent-skills	Applies Go coding standards and style conventions from Effective Go and Go Code Review Comments, including import ordering, struct initialization, receivers, and formatting rules.
go-defensive-coding 93/100 · A	eduardo-sl/go-agent-skills	Prevents panics and subtle runtime bugs in Go, covering typed-nil interfaces, slice aliasing, integer overflow, defer in loops, defensive copying, and zero-value design.
go-naming 95/100 · A	eduardo-sl/go-agent-skills	Applies Go naming conventions to packages, files, types, functions, methods, receivers, variables, constants, errors, acronyms, and tests, grounded in Effective Go.
iterate-pr 80/100 · B	getsentry/skills	Iterates on a PR until actionable CI passes and high and medium review feedback is addressed, without waiting on approval or merge gates.
linting-neostandard-eslint9 77/100 · C	mcollina/skills	Configures ESLint v9 flat config and neostandard for JavaScript and TypeScript projects, including migrating from legacy .eslintrc files or the standard package.
load-pr-comments 76/100 · C	NeoLabHQ/context-engineering-kit	Loads open, unresolved PR review comments and aggregates them as task files in .specs/comments so parallel agents can fix them.
pr-babysitter 91/100 · A	mblode/agent-skills	Monitors or repairs an open GitHub PR, handling CI failures, conflicts, review threads, and merge readiness while reporting state changes.
receiving-code-review 84/100 · B	obra/superpowers	Guides handling code review feedback with technical rigor and verification, rather than performative agreement or blind implementation, especially when feedback is unclear or questionable.
requesting-code-review 79/100 · C	obra/superpowers	Guides requesting a code review after completing tasks, implementing major features, or before merging, to verify the work meets requirements.
review-local-changes 78/100 · C	NeoLabHQ/context-engineering-kit	Reviews uncommitted working-tree changes, including untracked files, and returns actionable improvement suggestions before committing, when nothing has been pushed yet.
review-pr 78/100 · C	NeoLabHQ/context-engineering-kit	Reviews an existing GitHub pull request and posts inline review comments on its diff, for changes that are already on an opened PR.
terraform-style-guide 80/100 · B	hashicorp/agent-skills	Generates and reviews Terraform HCL code that follows HashiCorp's official style conventions and best practices.
tidy 87/100 · B	mblode/agent-skills	Reviews a local diff, branch diff, or PR with file and line findings in confirmed and plausible tiers, and can apply the fixes.
traiage-review 74/100 · C	NeoLabHQ/context-engineering-kit	Prioritizes the changed code in a repository to decide what a human must review.
write-discoverable-code 72/100 · C	modem-dev/skills	Sets rules for writing and renaming functions, types, constants, files, and error messages so coding agents and humans can find code through plain-text search.
arch-linux-triage 59/100 · D	github/awesome-copilot	Triage and resolve Arch Linux issues with pacman, systemd, and rolling-release best practices.
archetype-review-base 77/100 · C	avelikiy/great_cto	Shared review framework that every domain reviewer (pci, oracle, gov, edtech, healthcare, mlops, etc.) MUST follow. Defines the output artifact…
autofix 70/100 · C	coderabbitai/skills	Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly
birdview-review 70/100 · C	Qiuner/birdview	Review and improve codebase architecture with source-backed current/proposed diagrams, tradeoffs and verification. Use for birdview-review or…
code-improver 89/100 · B	trailofbits/skills	Runs an autonomous review-and-fix improvement loop over any code target — a skill, plugin, module, or directory — using a reviewer the user names…
code-maturity-assessor 84/100 · B	trailofbits/skills	Systematic code maturity assessment using Trail of Bits' 9-category framework. Analyzes codebase for arithmetic safety, auditing practices, access…
code-review 75/100 · C	getsentry/skills	Perform code reviews following Sentry engineering practices. Use when reviewing pull requests, examining code changes, or providing feedback on code…
code-review 81/100 · B	mattpocock/skills	Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented…
code-reviewer 76/100 · C	infrasity-labs/dev-gtm-claude-skills	Code review automation for TypeScript, JavaScript, Python, Go, Swift, Kotlin, C#, .NET, Java, C, C++, Rust, Ruby, PHP, and Dart/Flutter. Analyzes…
code-simplifier 81/100 · B	getsentry/skills	Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Use when asked to "simplify code"…
command-development 76/100 · C	anthropics/claude-plugins-official	This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments"…
comment-code-generate-a-tutorial 63/100 · D	github/awesome-copilot	Transform this Python script into a polished, beginner-friendly project by refactoring the code, adding clear instructional comments, and generating…
creating-secrets-using-best-practices 74/100 · C	aws/agent-toolkit-for-aws	Creates and manages secrets in AWS Secrets Manager following security best practices. Always use this skill when creating secrets — it sets up…
critique 66/100 · D	NeoLabHQ/context-engineering-kit	Comprehensive multi-perspective review using specialized judges with debate and consensus building
csharp-docs 65/100 · D	github/awesome-copilot	Ensure that C# types are documented with XML comments and follow best practices for documentation.
dart-run-static-analysis 69/100 · D	flutter/skills	Execute `dart analyze` to identify warnings and errors, and use `dart fix --apply` to automatically resolve mechanical lint issues. Use during…
deslop-shared-libs 70/100 · C	garrytan/gstack	Find worthwhile shared-code extractions in recent work. (gstack)
django-perf-review 83/100 · B	getsentry/skills	Django performance code review. Use when asked to "review Django performance", "find N+1 queries", "optimize Django", "check queryset performance"…
dotnet-best-practices 62/100 · D	github/awesome-copilot	Ensure .NET/C# code meets best practices for the solution/project.
dx-audit 87/100 · B	mblode/agent-skills	Audits libraries, CLIs, and SDKs using 38 rules for public contracts, package exports, piped output, errors, and configuration. Use when asked to…
find-bugs 75/100 · C	getsentry/skills	Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review…
generate-custom-instructions-from-codebase 69/100 · D	github/awesome-copilot	Migration and code evolution instructions generator for GitHub Copilot. Analyzes differences between two project versions (branches, commits, or…
geofeed-tuner 72/100 · C	github/awesome-copilot	Use this skill whenever the user mentions IP geolocation feeds, RFC 8805, geofeeds, or wants help creating, tuning, validating, or publishing a…
gh-review-requests 82/100 · B	getsentry/skills	Fetch unread GitHub notifications for open PRs where review is requested from a specified team or opened by a team member. Use when asked to "find…
go-refactoring 95/100 · A	eduardo-sl/go-agent-skills	Safe refactoring workflow for Go: behavior-preserving steps, compiler-checked renames, extracting packages, breaking circular dependencies, and…
guidelines-advisor 84/100 · B	trailofbits/skills	Smart contract development advisor based on Trail of Bits' best practices. Analyzes codebase to generate documentation/specifications, review…
improve-code-quality 76/100 · C	wondelai/skills	Guided journey from a working-but-untested vibe-coded prototype to a production-ready product with tests, clean structure, a business-rules…
intended-vs-implemented 81/100 · B	phuryn/pm-skills	The method for finding the gap between what a system is supposed to do and what the code actually does — the class of bug generic scanners miss…
java-docs 61/100 · D	github/awesome-copilot	Ensure that Java types are documented with Javadoc comments and follow best practices for documentation.
java-refactoring-extract-method 62/100 · D	github/awesome-copilot	Refactoring using Extract Methods in Java Language
java-refactoring-remove-parameter 62/100 · D	github/awesome-copilot	Refactoring using Remove Parameter in Java Language
java-springboot 65/100 · D	github/awesome-copilot	Get best practices for developing applications with Spring Boot.
kaizen 70/100 · C	NeoLabHQ/context-engineering-kit	Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation…
kotlin-springboot 65/100 · D	github/awesome-copilot	Get best practices for developing applications with Spring Boot and Kotlin.
launching-ec2-instance-with-best-practices 74/100 · C	aws/agent-toolkit-for-aws	Launches an EC2 instance with secure, cost-efficient defaults including AMI selection, burstable instance sizing, least-privilege IAM roles…
legacy-modernizer 84/100 · B	jeffallan/claude-skills	Designs incremental migration strategies, identifies service boundaries, produces dependency maps and migration roadmaps, and generates API facade…
make-repo-contribution 71/100 · C	github/awesome-copilot	All changes to code must follow the guidance documented in the repository. Before any issue is filed, branch is made, commits generated, or pull…
mcore-linting-and-formatting 62/100 · D	NVIDIA/skills	Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
mcore-split-pr 66/100 · D	NVIDIA/skills	Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
move-code-quality 64/100 · D	1NickPappas/move-code-quality-skill	Analyzes Move language packages against the official Move Book Code Quality Checklist. Use this skill when reviewing Move code, checking Move 2024…
pr-improver 93/100 · A	trailofbits/skills	Runs an autonomous review-and-fix improvement loop over the current branch's changes until a PR review comes back clean, scoped mechanically to the…
pr-review-expert 72/100 · C	infrasity-labs/dev-gtm-claude-skills	Use when the user asks to review pull requests, analyze code changes, check for security issues in PRs, or assess code quality of diffs.
pr-screenshots 69/100 · D	github/awesome-copilot	Embed before/after screenshots and annotated images in pull request descriptions. Covers PR description patterns, image upload for Azure DevOps and…
pr-writer 78/100 · C	getsentry/skills	Create or refresh reviewer-facing PR titles and descriptions. Use when opening a PR, updating its title or body, or preparing branch changes for…
refactor 69/100 · D	github/awesome-copilot	Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god…
refactor-method-complexity-reduce 69/100 · D	github/awesome-copilot	Refactor given method `${input:methodName}` to reduce its cognitive complexity to `${input:complexityThreshold}` or below, by extracting helper…
refactor-plan 74/100 · C	github/awesome-copilot	Create a concrete plan before starting a multi-file refactor. Use when the user asks to plan, sequence, scope, or safely execute a refactor across…
refactoring-patterns 81/100 · B	wondelai/skills	Apply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code…
remove-technical-debt 76/100 · C	wondelai/skills	Guided journey from a large aged codebase everyone fears to touch to one that is safe to change, legible, bounded, and resilient - paid down in…
resolve-fixed-pr-comments 70/100 · C	NeoLabHQ/context-engineering-kit	Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed…
review-and-refactor 58/100 · D	github/awesome-copilot	Review and refactor code in your project according to defined instructions
review-implementing 78/100 · C	mhattingpete/claude-skills-marketplace	Process and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code review notes, or asks to…
review-walkthrough 84/100 · B	trailofbits/skills	Generates an interactive HTML walkthrough for reviewing code changes. Use only when explicitly called.
scaffold-exercises 75/100 · C	mattpocock/skills	Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold…
second-opinion 89/100 · B	trailofbits/skills	Gets independent code reviews from Codex or Antigravity for uncommitted changes, branch diffs, and commits. Use when the user requests an external…
securing-s3-buckets 84/100 · B	aws/agent-toolkit-for-aws	Create and secure S3 buckets following AWS best practices for access control, encryption, monitoring, and remediation of misconfigurations. Use when…
semantic-kernel 67/100 · D	github/awesome-copilot	Create, update, refactor, explain, or review Semantic Kernel solutions using shared guidance plus language-specific references for .NET and Python.
shipping-artifacts 81/100 · B	phuryn/pm-skills	The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture…
skill-development 73/100 · C	anthropics/claude-plugins-official	This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description"…
slang-shader-engineer 81/100 · B	github/awesome-copilot	Use when working with Slang shaders, shader modules, HLSL-compatible GPU code, graphics pipelines, compute shaders, tessellation, ray tracing…
software-design-philosophy 81/100 · B	wondelai/skills	Manage software complexity through deep modules, information hiding, and strategic programming. Use when the user mentions "module design", "API too…
spec-to-code-compliance 86/100 · B	trailofbits/skills	Check code against the documentation that specifies it - which requirements hold, which the code contradicts, which are absent, and what the code…
Suede AI Code Skills 93/100 · A	JasonColapietro/suede-creator-skills	Use when explicitly asked "review this PR" or to grade a diff, branch, or commit range. Suede AI returns evidence-backed P0-P3 findings, fix paths…
typing-exclusion-worker 75/100 · C	getsentry/skills	Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a…
vercel-react-best-practices 67/100 · D	vercel-labs/agent-skills	React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring…
working-with-legacy-code 81/100 · B	wondelai/skills	Safely change and test untested codebases using Feathers' "Working Effectively with Legacy Code". Use when the user mentions "legacy code", "no…
yeet 72/100 · C	openai/skills	Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).

How to choose code review and code quality skills

Pick a review skill whose checks match what your team blocks merges on. A review that reports what you would fix is more useful than a long generic list.

Language-specific review skills catch idioms a general reviewer misses; pair one with a general review skill rather than replacing it.

Refactoring skills change many files. Run them on a branch with tests, and ask for the change in small, reviewable steps.