Discover devops llm ai skills, compare source repositories and read the instructions for each workflow.
Explains step-based workflow system for Synapse plugin actions. Use when the user mentions "BaseStep", "StepRegistry", "Orchestrator", "StepResult", "BaseStepContext", "step-based workflow", "workflow steps", "...
Explains how to execute Synapse plugins programmatically. Use when the user mentions "run_plugin", "ExecutionMode", "LocalExecutor", "RayActorExecutor", "RayJobExecutor", "PluginDiscovery", "from_path", "from_m...
Explains result schema classes for Synapse plugin actions. Use when the user mentions "TrainResult", "InferenceResult", "ExportResult", "UploadResult", "WeightsResult", "MetricsResult", "result_model", "result...
Explains how to use Synapse RuntimeContext API. Use when the user asks about "RuntimeContext", "ctx.", "logging", "progress tracking", "set_progress", "set_metrics", "log_message", "BaseStepContext", "TrainCont...
Multi-perspective AI council for designing, validating, and improving trading strategies with 5 specialized agents.
Analyze code performance, detect bottlenecks, suggest optimizations for algorithms, queries, and resource usage. Use when improving application performance or investigating slow code.
AIフィードバックループ最適化スキル。プロンプト→出力→評価→改善の反復サイクルを自動化。段階的改善、A/Bテスト、収束判定、ベスト出力選択で最高品質の結果を生成。
Copilot CLIに処理を委譲するスキル。ユーザーが「Copilotに聞いて」「Copilotで確認して」「Copilotに任せて」などと明示的に依頼したときに使用する。GitHub Copilot CLIの機能を活用して、コマンドの提案やGit操作の説明な...
Analyze application logs to detect errors, patterns, anomalies, and generate insights. Use when troubleshooting issues or analyzing system behavior.
Process and generate Word documents with formatting, tables, and images. Use when working with Word documents or generating reports.
Generate structured meeting notes with action items, decisions, and summaries from transcripts. Use when documenting meetings or creating meeting summaries.
LLMプロンプトの最適化・テスト支援スキル。プロンプトのパフォーマンス評価、改善提案、A/Bテスト、ベストプラクティス適用、再現性検証を行います。
AI出力の品質を自動検証するスキル。事実確認、論理性、一貫性、幻覚（ハルシネーション）検出、バイアス分析、安全性チェックを実施し、改善提案を提供。
AI生成コンテンツの総合品質チェックスキル。読みやすさ、正確性、関連性、独自性、SEO、アクセシビリティ、エンゲージメント、文法・スタイルを多角的に評価。
AI応答を洗練・改善するスキル。粗い出力を流暢で専門的な文章に変換。構造化、明確化、詳細化、トーン調整、専門性向上、読みやすさ改善を実施。
High-performance semantic search and document parsing toolkit. Use PROACTIVELY for searching across documentation, YAML manifests, configuration files, or any text where semantic understanding is needed. Partic...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or to...
Comprehensive research workflow for feature implementation planning. Use this skill when gathering information about how to implement features, understanding technology choices, researching APIs and libraries,...
Guideline for generating AI prompt or coding agent rules
Guide for creating effective skills. Use when users want to create or update a skill that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Create and configure Claude Code hooks for customizing agent behavior. Use when the user wants to (1) create a new hook, (2) configure automatic formatting, logging, or notifications, (3) add file protection or...
Analyze images and generate comprehensive JSON profiles for style recreation. Use when users upload images for visual analysis, style extraction, AI image generation prompts, or need detailed breakdowns of comp...
Analyzes meeting transcripts to uncover behavioral patterns and communication insights. Identifies conflict avoidance, filler words, conversation dominance, and listening gaps. Use for professionals seeking to...
Create specialized Claude Code sub-agents with custom system prompts and tool configurations. Use when users ask to create a new sub-agent, custom agent, or task-specific AI workflows.
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.