All categories
Code Review & Quality
Code review, refactoring, debugging, maintainability, and engineering quality
- 15,943
- 665
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse code review & quality skills
Showing 12,097–12,120 of 15,943 skills
- CollectionEnterprise systematic code review orchestrator with TRUST 5 principles,Votes: 0GitHub stars: 24
- CollectionAnalyzes codebases to identify technical debt, performance bottlenecks, and architectural improvements with prioritized, actionable recommendations. Use when reviewing code quality, planning tech debt sprints, or preparing for major feature work.Votes: 0GitHub stars: 24
- CollectionA meta-skill for documenting and creating reusable skills for Claude Code agents. Use when you discover a technique, pattern, or workflow worth documenting for reuse across projects.Votes: 0GitHub stars: 24
- CollectionCollect pending worktree commits into a PR for review. Use this skill when subdirectory worktrees have accumulated 4-7+ commits that should be batched together and submitted for review. Invoked with /collect-for-pr or automatically when monitoring worktree status.Votes: 0GitHub stars: 24
- CollectionComprehensive static code analysis to enforce architectural patterns, conventions, and code quality standards.Votes: 0GitHub stars: 24
- CollectionStore project-specific insights and context into file-based memory. Use after completing tasks that reveal important details about THIS codebase. Use when user says "--project-store" or "--learn" (you decide which scope, may use both) or after discovering project-specific patterns. Skip for universal patterns (use coder-memory-store) or routine work.Votes: 0GitHub stars: 24
- CollectionRetrieve project-specific insights from file-based memory. Use when working on features, encountering domain-specific questions, or user says "--project-recall" or "--recall" (you decide which scope, may use both). Skip for routine tasks or universal pattern questions (use coder-memory-recall). MUST be invoked using Task tool to avoid polluting main context.Votes: 0GitHub stars: 24
- CollectionGitHub workflow automation for LiquidationHeatmap. Generate standardized PR descriptions, issue templates, and commit messages. Reduces token usage by 70% on repetitive GitHub operations.Votes: 0GitHub stars: 24
- CollectionInteractive slash command creator for Claude Code. Triggers when user mentions creating commands, slash commands, command templates, command arguments, or wants to build a new command workflow.Votes: 0GitHub stars: 24
- CollectionCRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.Votes: 0GitHub stars: 24
- CollectionThe meta-skill of using skills effectively. Learn when to invoke which skill, how to chain them together, and how to develop your own. Master the Arcanea skill system itself.Votes: 0GitHub stars: 24
- CollectionDelegate asynchronous coding tasks to Jules (Google's AI coding agent) to maximize efficiency. Use for code reviews, refactoring, adding tests, bug fixes, and documentation. Proactively suggest Jules delegation when appropriate. Invoke when user asks to interact with Jules, create sessions, check task status, or when tasks are suitable for async delegation.Votes: 0GitHub stars: 24
- CollectionCreate and manage agents (orchestrators, skills, sub-agents). Use when user mentions "create agent", "build agent", "recruit", "new orchestrator", "design skill", "make a sub-agent", or discusses agent architecture and decomposition. Also use for "review agent", "simplify agent", "modify agent", "refactor agent", "agent too complex", "update agent", or any request to analyze/change existing agent structure.Votes: 0GitHub stars: 24
- CollectionExtract and summarize review comments from GitHub PRs. Use when analyzing PR reviews, checking unresolved issues, or responding to CodeRabbit feedback.Votes: 0GitHub stars: 24
- CollectionCreate Claude Code subagents - specialized AI assistants for specific tasks. Use when setting up project workflows or creating task-specific agents.Votes: 0GitHub stars: 24
- CollectionEnterprise comprehensive code review automation with AI-powered quality analysis, TRUST 5 enforcement, multi-language support, Context7 integration, security scanning, performance analysis, test coverage validation, and automated review feedback generationVotes: 0GitHub stars: 24
- CollectionEnterprise systematic code review orchestrator with TRUST 5 principles, multi-language support, Context7 integration, AI-powered quality checks, SOLID principle validation, security vulnerability detection, and maintainability analysis across 25+ programming languages; activates for code reviews, quality standard validation, TRUST 5 enforcement, architectural audits, and automated review automationVotes: 0GitHub stars: 24
- CollectionRevises book chapters based on feedback. Use when user says 'revise chapter X', 'improve chapter [number]', 'rewrite the opening of chapter X', 'make chapter X more [adjective]', or provides feedback on a chapter.Votes: 0GitHub stars: 24
- CollectionEnsures CLAUDE.md, README.md, and CHANGELOG.md are updated before git push operationsVotes: 0GitHub stars: 24
- Collectiontailwind expert with self-populating documentationVotes: 0GitHub stars: 24
- Collectionreact expert with self-populating documentationVotes: 0GitHub stars: 24
- Collectionnextjs expert with self-populating documentationVotes: 0GitHub stars: 24
- Collectiongit expert with self-populating documentationVotes: 0GitHub stars: 24
- Collectionclerk expert with self-populating documentationVotes: 0GitHub stars: 24