dspy-rag-pipeline
Build and optimize RAG pipelines with ColBERTv2 retrieval in DSPy
498 repo starsObserved in 2 repos
Agent Building
Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
eld-sense-activation
PCE (Process-Context Engine) のアクティブコンテキスト構築スキル。タスクに最適化されたコンテキストをコンパイルし、プロセス駆動の投入物を生成する。 トリガー条件: - 新しいタスクを開始する時（「この機能を実装して」） - AIにコード生成を依頼する時 - 複雑な問題解決に着手する時 - 「コンテキストを整理して」 - 「必要な情報をまとめて」
498 repo starsObserved in 2 repos
Agent Building
eld-sense-scope
PCE (Process-Context Engine) のスコープ管理スキル。入れ子プロセス間のコンテキスト継承を設計し、親子間のハンドオフを最適化する。 トリガー条件: - タスクを子タスクに分解する時 - サブエージェントに作業を委譲する時（Task tool使用時） - 並列タスクを起動する時 - 「このタスクを分割して」 - 「サブタスクのコンテキストを設計して」
498 repo starsObserved in 2 repos
Agent Building
eleven-agent-manager
Manage ElevenLabs Conversational AI agent configuration including prompts, voice settings, MCP servers, and conversation settings. Use when updating agent behavior, voice, or integrations.
498 repo starsObserved in 2 repos
Agent Building
engram-generate
Generate project-specific skills from Claude Code session history. Use when: (1) starting work on a new-to-you codebase, (2) onboarding to a project, (3) capturing learned patterns for future sessions.
498 repo starsObserved in 2 repos
Agent Building
episodic-archiver
Episodic Memory Archiver. Stores full conversation transcripts with embeddings and analysis into ArangoDB. Tracks UNRESOLVED sessions for reflection.
498 repo starsObserved in 2 repos
Agent Building
escalation-governance
Guide to deciding whether to escalate from a lower model (haiku/sonnet) to a higher model (sonnet/opus). Triggers: model escalation, haiku to sonnet, sonnet to opus, reasoning depth, task complexity, model selection, capability trade-off Use when: evaluating whether to escalate models, facing genuine complexity requiring deeper reasoning, novel patterns with no existing solutions, high-stakes decisions requiring capability investment DO NOT use when: thrashing without investigation - investigate root cause first. DO NOT use when: time pressure alone - urgency doesn't change task complexity. DO NOT use when: "just to be safe" - assess actual complexity instead. NEVER escalate without investigation first. This is the Iron Law.
498 repo starsObserved in 2 repos
Agent Building
eval-audit
Audit an existing evaluation workflow and produce severity-ranked findings with concrete next actions. Use when inheriting an eval setup, diagnosing quality regressions, or checking LLM evaluation process maturity.
498 repo starsObserved in 2 repos
Agent Building
evolving-status
View Self-Evolving Loop session status, history, and memory metrics
498 repo starsObserved in 2 repos
Agent Building