16,832 skills sorted by stars.
Guide for building production-ready LiveKit voice AI agents with multi-agent workflows and intelligent handoffs. Use when creating...
Principles for writing simple, maintainable Laravel/Livewire code. Use when writing Livewire components, tests, or Blade views. Fo...
Automatically applies when building LLM applications. Ensures proper async patterns for LLM calls, streaming responses, token mana...
Detects common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstraction, and verbose L...
Analyze llm-compact-logger test output and configure enhancements. Use when user shares debug-compact.json or debug-report.json fi...
Reduce LLM API costs without sacrificing quality. Covers prompt caching (Anthropic), local response caching, prompt compression, d...
Diagnoses LLM output failures including hallucinations, constraint violations, format errors, and reasoning issues. Provides root...
Claude acts as manager/architect while delegating all coding to external LLM CLIs (Gemini, Codex, Qwen). Claude never writes code...
Test llm-mux IR translator - cross-format API translation
Comprehensive LLM model evaluation and ranking system. Use when users ask to compare language models, find the best model for a sp...
LLMs, prompt engineering, RAG systems, and AI application development
Generates comprehensive code tutorials on LlmTornado API formatted for Medium publication with examples, explanations, and best pr...
Solved issues, common errors, and debugging techniques for LMS. Use this skill when debugging issues, understanding error codes, f...
Complete story workflow orchestrator for Agile
Detects unsafe spikes in training load and emits SafetyFlags with conservative adjustments.
도메인/기능의 컨텍스트 빠른 파악. Use when:(1) 특정 도메인 이해 필요, (2) 기존 기능 수정 전 파악,(3) 세션 시작 시 컨텍스트 로드.
Load the full content of a previous Claude Code conversation into current context. Use when user asks to "load conversation <uuid>...
Creates comprehensive load test plans with realistic scenarios, traffic models, k6 scripts, and success criteria. Use for "load te...
Use when creating loading indicators, spinners, progress bars, or skeleton screens to communicate system status
Chat with local Ollama models that can explore your codebase using tools.
remote CI (GitHub Actions) 相当のチェックをローカルで実行。Biome check、テスト、ビルドを並列実行し、全てのチェックが成功したことを確認する。PR作成前の事前チェックに使用。
This skill should be used for configuring devloop project settings via .devloop/local.md, git workflow preferences, commit setting...
skill that dictates the deployment strategy for local development
Provide local debugging scripts for Docker including build, run, and environment setup for development workflow.
Use this to run and debug the UI + server locally (Vite dev server, `lotar serve`, ports, SSE).
プロジェクトの .claude/settings.local.json を更新する。「ローカル設定を更新して」「local settings を変更」「個人用設定を変えて」「自分だけの設定」「ローカル permissions を追加」「個人設定ファイルを編集」...
Expert guide for understanding the Local Skills MCP server repository - its structure, architecture, and implementation. Use when...
Manage localization strings, find missing translations, validate .strings files