Agent Building skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

prompt-testing-evaluation

プロンプトのテスト、評価、反復改善を専門とするスキル。A/Bテスト、評価メトリクス、自動化されたプロンプト品質保証により、本番環境で信頼性の高いプロンプトを実現します。 Anchors: • Test-Driven Development: By Example (Kent Beck) / 適用: Red-Green-Refactorサイクル / 目的: 反復的な品質改善 • LLM-as-a-Judge pattern / 適用: 自動評価とスコアリング / 目的: スケーラブルな品質評価 • A/B Testing for AI Systems / 適用: プロンプト比較実験設計 / 目的: データドリブンな改善 Trigger: Use when testing prompts, evaluating prompt quality, running A/B tests on prompts, implementing automated prompt evaluation, or establishing continuous prompt improvement cycles. Keywords: prompt testing, A/B testing, evaluation metrics, LLM-as-a-judge, prompt quality, automated evaluation, regression testing

498 repo starsObserved in 2 repos

Agent Building

GitHub

prompt-versionierung

Prompt-Versionen für den 3D-Review verwalten: Versionierung der Spaltenprompts und Zeilenprompts. Normen: technisch/governance. Prüfraster: Versionsnummer, Aenderungsprotokoll, aktive Version. Output: Prompt-Versionsprotokoll. Abgrenzung: nicht Prompt-Erstellung.

498 repo starsObserved in 2 repos

Agent Building

GitHub

prompt-versioning-management

プロンプトのライフサイクル管理を専門とするスキル。バージョン管理、デプロイ戦略、ロールバック、変更追跡により、本番環境で安全かつ効率的なプロンプト運用を実現します。 Anchors: • The Pragmatic Programmer (Andrew Hunt, David Thomas) / 適用: 手順設計と実践的改善 / 目的: 体系的なバージョン管理 • Continuous Delivery (Jez Humble) / 適用: デプロイパイプラインとロールバック戦略 / 目的: 安全なリリースプロセス • Semantic Versioning 2.0.0 / 適用: バージョン番号付けルール / 目的: 変更の影響範囲の明確化 Trigger: Use when managing prompt versions, deploying prompts to production, implementing rollback strategies, tracking prompt changes, or establishing prompt lifecycle management. Keywords: prompt versioning, semantic versioning, deployment strategy, rollback, change tracking, prompt lifecycle, blue-green deployment

498 repo starsObserved in 2 repos

Agent Building

GitHub

Proxy Pay Mcp

Proxy MCP server integration for agent payments. Use MCP tools to create intents, issue cards within policy, and track transactions. Supports agent tokens for autonomous runs and OAuth for interactive clients.

498 repo starsObserved in 2 repos

Agent Building

GitHub

rag-manager

Librarian of the Epsilon Ecosystem. Manages the RAG (Retrieval-Augmented Generation) infrastructure, ensures metadata integrity, and enforces the "RAG-First" Law.

498 repo starsObserved in 2 repos

Agent Building

GitHub

rag-optimization

RAG 파이프라인 최적화 스킬. 검색 품질, 리랭킹, 쿼리 확장, 하이브리드 검색 관련 작업에서 자동으로 활성화됩니다. retrieval, rerank, embedding, vector search, semantic search 키워드에 반응합니다.

498 repo starsObserved in 2 repos

Agent Building

GitHub

rag-pipeline

Use when building Retrieval-Augmented Generation systems. Covers document chunking, embedding generation, vector indexing, semantic search, context building, and integration of retrieval with LLM completion for accurate Q&A on Physical AI textbook content.

498 repo starsObserved in 2 repos

Agent Building

GitHub

ralph-loop-guide

Ralph Loop Best Practices - Guidelines for effective autonomous iteration. Based on Anthropic's official ralph-loop plugin. Helps design prompts for iterative AI development with clear completion signals.

498 repo starsObserved in 2 repos

Agent Building

GitHub

ralph-resume

Resume a PAUSED Ralph session — retry failed task, skip, or abort

498 repo starsObserved in 2 repos

Agent Building

GitHub

ralph-router

Routes to appropriate Ralph skills based on agent role and task signals

498 repo starsObserved in 2 repos

Agent Building

GitHub