Skill UI

Provides detailed evaluation of machine learning models using plugin metrics to assess accuracy, precision, recall, F1, and other key indicators, helping users compare models and validate performance before deployment.

This skill provides structured patterns for combining vector similarity search with traditional keyword-based search. It is essential for building advanced Retrieval-Augmented Generation (RAG) systems, sophisticated search engines, or any retrieval task requiring high recall. Use this when pure semantic understanding is insufficient, and precise matching of specific terms (like names or codes) is necessary.

Memory provides persistent context across multiple coding sessions. It stores crucial project decisions, user preferences (like preferred package managers or specific libraries), and architectural conventions in a local memory file. This ensures that the AI maintains consistency, recalls past choices automatically, and applies project-specific rules without needing constant reminders, significantly improving workflow continuity and reliability.

Automates Recallai operations through Composio's Rube MCP toolkit by discovering current tool schemas via RUBE_SEARCH_TOOLS, verifying recallai connections, and running schema-compliant RUBE_MULTI_EXECUTE_TOOL workflows.

This comprehensive guide outlines best practices for optimizing vector indexes for production systems. It covers critical techniques such as tuning HNSW parameters, implementing quantization strategies, and optimizing memory usage. Use this when you need to balance search latency, recall, and scalability for large-scale vector databases.

Provides Python access to openFDA endpoints for drugs, devices, foods, veterinary products, and substances, enabling regulatory analysis, safety monitoring, recalls tracking, and pharmacovigilance research.

This tool allows users to explicitly save critical, project-specific facts, conventions, or debugging insights to a dedicated auto-memory file. Use it when the knowledge is too important or specialized to rely on the AI's automatic context capture. It ensures persistent recall of architectural decisions, tool gotchas, or team preferences across multiple sessions and projects.

RecallMax dramatically enhances AI agent memory capabilities by cleanly injecting massive external contexts (500K-1M tokens) without hallucination drift. It automatically summarizes lengthy conversations, preserving tone, intent, and key facts. Furthermore, it compresses multi-turn interaction histories into high-density token sequences, ensuring agents maintain perfect recall across complex and long-running sessions.

This skill guides security teams on systematically tuning SIEM detection rules in platforms like Splunk and Elastic. It focuses on reducing alert fatigue and false positives by analyzing historical alert volumes, establishing environmental baselines, creating context-aware whitelists, and measuring detection efficacy using metrics like precision and recall. This is crucial for maturing a Security Operations Center (SOC).

Describes how to use the MemOS local memory toolkit to recall past conversations, search shared histories, and choose the right memory tool when automatic recall is insufficient.

Recall and persist long-term semantic memory via OpenViking MCP tools. Use at task start to retrieve relevant prior knowledge, and during/after work to store durable facts, preferences, decisions, and lessons. Ideal for coding, configuration, debugging, multi-step tasks, and tool-based workflows. Not for casual chat or simple trivia.

EverOS OpenClaw Plugin integrates persistent, long-term memory capabilities into OpenClaw using the ContextEngine API. It goes beyond simple memory slots by automatically recalling relevant past context before a reply and saving new conversation content after a turn. This allows users to chat naturally while ensuring context, preferences, and key details persist across multiple sessions, eliminating the need for manual memory calls.