Discover research debugging skills, compare source repositories and read the instructions for each workflow.
Analyze Cloudflare architecture and predict monthly costs with optimization recommendations. Use this skill when the user asks about costs, billing, pricing, or wants to understand their Cloudflare spend. Works...
ALWAYS USE FIRST when exploring, searching, or researching this codebase. Use symbol_tree MCP tool before grep/glob/read. Provides instant architecture overview, function relationships, and call graphs without...
Expert Polyglot Frontend Engineer (20+ years exp). Strict adherence to documentation/references. Obsessed with performance, implementation details, and evidence-based coding.
Discover available effects, actions, and placeholders in a Sandestin project. Use when asking what effects exist, searching for functionality, or needing example invocations. Keywords: effects, actions, dispatc...
デバッグ・レビュー・問題報告時に使用。誠実なコミュニケーションと根本原因分析を徹底。
パフォーマンス最適化やプロファイリング時に使用。計測とよくあるボトルネックをカバー。
バグやテスト失敗に遭遇した際に使用。修正前の4フェーズ根本原因分析を強制。
Analyze files in a codebase to understand structure, find patterns, extract metadata, and generate summaries. Use when exploring unfamiliar codebases, documenting project structure, or when users ask about file...
Systematic code review and evaluation tool for Python/FastAPI projects. Use when reviewing PRs, evaluating code quality, checking architecture compliance, or providing feedback on implementations. Triggers on "...
Guides creating detailed execution plans for features, refactors, and code changes. Use when user requests a gameplan, or when user invokes /gameplan.
曲を設計視点で分析し、analysis/{slug}.mdに保存。曲の本質、構造、コード進行、アレンジメントを言語化する。
デバッグエンジニアとして回答。現象の整理、原因の網羅的列挙、最短での切り分け手順を提案する。
Guide for creating Claude Code hooks that respond to events during execution. This skill should be used when users want to create or configure hooks for validation, automation, context injection, or workflow co...
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Expertise in reviewing code for style, security, and performance. Use when the user asks for "feedback," a "review," or to "check" their changes.
Supabase-specific analytics patterns for dashboards including RLS-aware queries, time-series analysis, cohort analysis, and tenant-isolated aggregations. Use when building analytics features for the Vete platfo...
Systematically debug issues in PhotoClove by examining code, state, logs, and data flow. Automatically invoked when investigating bugs, errors not working as expected, or tracing problems through the codebase....
Automatically investigate logs when errors occur, debugging issues, or troubleshooting problems. Check frontend logs (LogViewer) and backend logs (daily log files) for error patterns. Use when user reports bugs...
Diagnose runtime errors, test failures, and unexpected behavior. Use when encountering errors, test failures, build issues, or performance problems. Provides root cause analysis and fix proposals.
Debug and trace MachinaMed medical agent errors in GKE environments. Use for investigating agent failures, tracing invocations, analyzing MALFORMED_FUNCTION_CALL errors, and generating comprehensive error repor...
Deep analysis of codebase vs documentation alignment. Detects drift, identifies undocumented code, extracts missing glossary terms, and provides actionable recommendations without making changes.
Detect over-engineering and YAGNI violations. Stricter than /review. Use when asked to "critique my code", "find over-engineering", or "check for unnecessary complexity".
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Trigge...
Evaluate logging coverage, error tracking, debugging capabilities, and monitoring patterns. Use when investigating production issues becomes difficult, after incidents, or when expanding monitoring coverage.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.