List the registered rag evaluation questions (probes) — print every entry in `.noory/rag/probes.json` as a table.
Remove a rag evaluation question (probe) — delete an item by ID from `.noory/rag/probes.json`. Example utterances "remove probe", "delete the auth-flow probe", "drop this…
RAG-specific prompt engineering techniques and best practices. RAG 專屬提示工程技術與最佳實踐。 Use when: building retrieval-augmented generation pipelines, grounding LLM answers in documents,…
Index quality cleanup — alias merge · community re-detection · community summary generation. Utterance examples "rag rebalancing", "rag-rebalance", "graph cleanup", "entity…
Re-chunk and re-extract entities from only the changed files, then load them into the vector/graph. Example utterances "rag reindex", "rag update", "rag-reindex", "reflect the…
Remove an indexing source — take it out of settings and clean up the chunks/entity mentions belonging to that source.
Use when designing or fixing the retrieval side of a RAG system, choosing chunking strategy (fixed-size / recursive / semantic), implementing hybrid search (BM25 + dense) with RRF…
Search RAG database for relevant content. Use for semantic queries over processed documents, code, or papers.
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval.
Guide to the three patterns for sharing a rag index/materials with a team. Example utterances "how to share rag", "share the index with my team", "how do I give it to someone…
RAG-specific best practices for LlamaIndex, ChromaDB, and Celery workers. Covers ingestion, retrieval, embeddings, and performance.
Build Retrieval Augmented Generation (RAG) pipelines with vector databases, embeddings, and context-aware responses. Adapted from Anthropic's Claude Cookbooks.
Report the current rag index status — file/chunk/entity/relation/community counts, embedding model, disk usage.
Build Retrieval-Augmented Generation (RAG) Q&A systems with Claude or OpenAI. Use for creating AI assistants that answer questions from document collections, technical libraries,…
Build Retrieval-Augmented Generation systems to enhance LLMs with external knowledge. Use for question answering, document search, knowledge bases, reducing hallucinations, and…
Evaluate RAG pipelines with Ragas, measuring faithfulness, answer relevancy, context precision and recall, building golden datasets, and wiring threshold gates into CI for…
Prüft Rahmenverträge, Einzelabrufe, Statements of Work und tatsächliche Projektsteuerung im Sozialversicherungsstatus Prüfer.
Verknüpft Rahmenvertrag, Bestellungen und Leistungsanlagen durch klare Abschlussmechanik, Parteizuordnung, Versionen, Vorrang und Fortgeltung offener Einzelaufträge.
Modélise le raisonnement juridique d'un magistrat français pour l'analyse de dossiers civils. Utiliser ce skill pour analyser un litige et identifier les questions juridi — from…
Activate autonomous Ralph Wiggum loop mode for iterative task completion. Use when you have a well-defined task with clear completion criteria that benefits from persistent,…
Iterative development loop methodology for autonomous AI work. Configure self-correcting coding loops that iterate until completion criteria are met, integrate with Archon for…
Execute an autonomous development loop that picks one task per iteration, implements it, verifies it, and commits the result — each iteration in a fresh context window.
Autonomous feature development - setup and execution. Triggers on: ralph, set up ralph, run ralph, run the loop, implement tasks.
Long-running iterative development loops with pacing control and verifiable progress. Use when tasks require multiple iterations, many discrete steps, or periodic reflection with…
P2P chat between Claude Code instances using real-a2a. Use when chatting with other Claudes, joining a P2P room, or communicating agent-to-agent.
RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.
AgentDB integration specialist for RAN ML systems with vector storage, pattern recognition, and distributed training coordination.
Causal inference and discovery for RAN optimization with Graphical Posterior Causal Models (GPCM), intervention effect prediction, and causal relationship learning.
DSPy-based mobility optimization with temporal patterns, handover management, and 15% improvement target.
Comprehensive RAN optimization with swarm coordination, cognitive consciousness, and 15-minute closed-loop autonomous cycles.
Reinforcement learning engineering for RAN systems with policy gradients, experience replay, and AgentDB integration.
Raxol terminal framework for TUI apps and AI agents in Elixir. TRIGGER when: code imports Raxol modules (Raxol.Agent, Raxol.Headless, Raxol.Core), mix.exs lists :raxol or…
Symphony: the Raxol tracker-driven coding-agent orchestrator (raxol_symphony, pre-alpha). Turns tracker issues into autonomous agent runs in isolated workspaces, surfaces evidence…
專責處理 RIF (Required Behavior Frame) 類型的需求。讀取規格目錄結構，生成/審查 Event Handler 設計與實作。支援冪等性、重試、死信佇列。
Search channels, inspect threads, move files, and send or edit Slack messages through an agent-oriented CLI with structured output.
Connect an MCP-capable assistant to Google Drive search, file reads, and Google Sheets cell updates with mcp-gdrive.
Design know-how for read-only instruments (計器) — aggregate readings over stored state (distributions, compositions, cluster structure) that inform the operator before an…
Scan reagent barcodes or IDs, log expiration dates, and generate multi-level alerts before reagent expiry to support laboratory inventory management.
Software project manager skill. Analyzes a plan (plan-index.md, a sub-plan, or a freeform task list), bundles directly-related or dependency-chained tasks into single-agent units,…
Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement.
Rechtsabteilungs-Fachmodul für KI-Code und Trainingsdaten im Lizenzvertrag: AI-assisted coding wird mit Warranty, Audit, Indemnity und Source-Hygiene geregelt.
Build recommendation systems with collaborative filtering, matrix factorization, hybrid approaches. Use for product recommendations, personalization, or encountering cold start,…
Update the project's CLAUDE.md to match its current structure and conventions.
Wrap Claude Code, Codex, Gemini CLI, OpenClaw, or another agent command with AgentSight to capture processes, files, network destinations, prompts, and reports.
Orchestrate multi-agent collaborative document synthesis through 6 phases - Divergence, Synthesis, Commentary, Consolidation, Reality Check, Final Merge.
Remove all agent-memory references to a session, mechanism, or identifier
Für Verl-023 · Redaktionsvertrag, Freelancer und Arbeitnehmer: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Use OMNI to distill noisy terminal output before coding agents read it while preserving recoverable raw logs for exact follow-up inspection.
Use rtk when an agent keeps wasting context on noisy shell output from large repos and you need smaller command responses before the model sees them.
Connect coding agents to a Token Savior MCP server for structural code navigation, persistent recall, compact command output, and token-aware project context reuse.
Use Honey to make coding agents emit less code, less prose, and denser agent-to-agent handoffs while preserving correctness boundaries.
Prüft deutsche einfache, qualifizierte, Zwischen-, Dienst- und Ausbildungszeugnisse vollständig nach dem Ampelsystem (🔴/🟠/🟢).
Refines a v1 project plan into agent-ready tasks with clear context, implementation steps, and validation criteria. Use after /plan-project has produced a v1 plan.
Agent-Selbstreflexions-Coach. Aktivieren wenn ein Agent einen Error / Tool-Failure / Exit-Code-Knall trifft. Klassifiziert in 3 Schritten (NORMAL/VERMEIDBAR/TECHNISCH) + ggf.
Synchronizes your local `~/.claude/skills/`, `~/.claude/agents/`, and `~/.claude/blueprints/` installation against the canonical Agent OS skill, agent, and blueprint library.
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
Discover, programmatically verify, and register a GitHub-linked AI co-author identity. Use only when attribute-ai-commits reports status missing for the current agent, or when…
Prüft vor Freigabe Vollständigkeit, Richtigkeit, Aktualitaet, Irreführungsfreiheit, Quellenstand und Plausibilitaet aller Pflichtangaben. Output Finalcheck-Protokoll.
Prüft vor Freigabe Vollständigkeit, Richtigkeit, Aktualitaet, Irreführungsfreiheit, Quellenstand und Plausibilitaet aller Pflichtangaben.
Reinforces an AI agent by turning Monte Carlo's agent-health diagnosis into code fixes. Reads the daily health report for an agent's workflows, ranks the diagnosed issues,…