Total 50,277 skills, Code Quality has 2282 skills
Showing 12 of 2282 skills
Find dead code using parallel subagent analysis and optional CLI tools, treating code only referenced from tests as dead. Use when the user asks to "find dead code", "find unused code", "find unused exports", "find unreferenced functions", "clean up dead code", or "what code is unused". Analysis-only — does not modify or delete code.
Review a PR linked to a kspec task, post findings as inline comments, and merge only when all quality gates pass. You NEVER fix code — you review and comment. If issues found, kick back to worker.
Trigger this skill when the user wants to start an asynchronous PR review, run background checks on a PR, or check the status of a previously started async PR review.
This skill should be used when the user asks to "set up ESLint", "configure ESLint rules", "fix ESLint errors", "migrate to flat config", or needs guidance on JavaScript/TypeScript linting best practices.
This skill should be used when the user asks to "write JavaScript code", "follow JavaScript style guide", "format JS files", "create Node.js scripts", or needs guidance on JavaScript/Node.js coding standards and best practices.
Pre-flight check before pushing to production. Catches TypeScript errors, accidentally staged secrets, pending migrations, and hygiene gaps before they hit live users.
Use this skill when implementing game programming patterns - state machines for character/AI behavior, object pooling for performance-critical spawning, event systems for decoupled game communication, or the command pattern for input handling, undo/redo, and replays. Triggers on game architecture, game loop design, entity management, finite state machines, object pools, observer/event bus, command queues, and gameplay programming patterns.
Reviews changes for correctness, edge cases, style, security, and maintainability with severity levels (Blocker/Major/Minor/Nit). Use before finalizing changes.
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.
Discovers and injects project-specific coding guidelines from .trellis/spec/ before implementation begins. Reads spec indexes, pre-development checklists, and shared thinking guides for the target package. Use when starting a new coding task, before writing any code, switching to a different package, or needing to refresh project conventions and standards.
Detect and remediate Go anti-patterns: premature interface abstraction, goroutine overkill, context soup, error wrapping mistakes, generic abuse, channel misuse, unnecessary function extraction, and interface pollution. Use when reviewing Go code for quality, detecting over-engineering, or when user mentions "anti-pattern", "code smell", "Go mistake", or "bad Go". Do NOT use for feature implementation, performance optimization without a code smell, or non-Go languages.
Multi-language code quality gate with auto-detection and language-specific linters. Use when user asks to "run quality checks", "quality gate", "lint all", "check everything", "pre-commit checks", or "is this code ready to commit". Use for verifying code quality across polyglot repos. Do NOT use for single-language linting (use code-linting) or comprehensive code review (use systematic-code-review).