context-manager
Comprehensive context and token usage management for Claude Code. Use this skill when working with large codebases, managing context window budget, optimizing file loading strategies, or when responses indicate...
发现 research debugging 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Comprehensive context and token usage management for Claude Code. Use this skill when working with large codebases, managing context window budget, optimizing file loading strategies, or when responses indicate...
Analyzes codebases to identify technical debt, performance bottlenecks, and architectural improvements with prioritized, actionable recommendations. Use when reviewing code quality, planning tech debt sprints,...
Chrome拡張機能(Manifest V3)の開発ガイド。tabCapture、Content Scripts、Service Worker、Offscreen Documentの実装時に使用。
ファイル分析スキル - プログレス表示のデモ用
Analyze ANY web project - detect if Web3 DApp, research dependencies via WebSearch, understand business functions from code AND UI screenshots, generate test requirements.
Systematic debugging by tracing data backwards from symptom to root cause. Uses HelixDB for relationships, Repo Prompt for inspection. Trigger when investigating bugs or unexpected behavior.
Python logging made (stupidly) simple. Focuses on a single, global logger with progressive disclosure to deep source understanding.
Implement error tracking, performance monitoring, and user issue detection. Use when adding error handling, Web Vitals reporting, or debugging production issues.
Find bugs, security vulnerabilities, and code quality issues in branch changes. Use when reviewing code for bugs, security issues, or quality problems. Thorough but concise reporting.
This skill should be used when the user asks about "refactoring", "code smells", "extract method", "extract class", "rename refactoring", "move method", or when improving code structure without changing behavio...
This skill should be used when the user asks about "code complexity", "cyclomatic complexity", "cognitive complexity", "code metrics", "maintainability index", "code coverage", or when measuring code quality qu...
Show the name of the currently active profile
Show the configuration of a profile
코드 탐색, 코드 분석, 탐색, 코드 구조, 심볼 분석 - Use when exploring or analyzing code. Systematic code exploration workflow using Serena MCP tools for symbol navigation and reference tracking.
코드 리뷰, 코드리뷰, 리뷰, PR 리뷰, 검토 - Expert at reviewing code for quality, adherence to architectural principles, security, and performance. Use this to ensure code meets project standards before merging...
디버깅, 디버그, 버그, 에러, 오류, 버그 수정 - Specialized in identifying root causes of bugs, analyzing error logs, and providing robust fixes. Use this when the user reports an error, unexpected behavior, or n...
Fast visual testing and screenshot automation for breathe-together-v2. Use when you need to capture screenshots of the 3D scene, compare visual changes before/after code modifications, or test different Leva co...
Systematic debugging approaches for isolating and fixing software defects
Systematic debugging approaches for isolating and fixing software defects
Performs comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and maintainability. Use when user wants to audit code quality, identify technical debt, find securi...
Review overall codebase health, architecture, and patterns using Google's engineering principles. Takes optional focus area. Use when the user wants to review code quality, assess architecture, or says "/review...
Systematic optimization hunter. Finds memory optimizations AND bugs - both are valuable. Run /validate-correctness when bugs are discovered.
Reviews memory optimization patches using a 5-persona peer review system. Requires unanimous approval backed by benchmarks. Bugs discovered during review are valuable - invoke /validate-correctness to validate...
Measure, compare, and improve eo-processor performance safely. Use when adding/changing Rust compute kernels, refactoring hot paths, or making performance claims. Provides a repeatable benchmark protocol with c...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。