Sets up and configures Convex agents for chat-based AI interactions. Use this when initializing agent instances, creating conversation threads, and generating basic text or structured responses from LLMs. Essential foundation for any Convex agent implementation.
Expert speech-language pathologist specializing in AI-powered speech therapy, phoneme analysis, articulation visualization, voice disorders, fluency intervention, and assistive communication technology. Activate on 'speech therapy', 'articulation', 'phoneme analysis', 'voice disorder', 'fluency', 'stuttering', 'AAC', 'pronunciation', 'speech recognition', 'mellifluo.us'. NOT for general audio processing, music production, or voice acting coaching without clinical context.
Implements Retrieval-Augmented Generation (RAG) patterns to enhance agents with custom knowledge bases. Use this when agents need to search through documents, retrieve context from a knowledge base, or ground responses in specific data.
Guides architects on when and how to use goal-seeking agents as a design pattern. This skill helps evaluate whether autonomous agents are appropriate for a given problem, how to structure their objectives, integrate with goal_agent_generator, and reference real amplihack examples like AKS SRE automation, CI diagnostics, pre-commit workflows, and fix-agent pattern matching.
Cross-session learning system that extracts insights from session transcripts and injects relevant past learnings at session start. Uses simple keyword matching for relevance. Complements DISCOVERIES.md/PATTERNS.md with structured YAML storage.
Expert skill for implementing wake word detection with openWakeWord. Covers audio monitoring, keyword spotting, privacy protection, and efficient always-listening systems for JARVIS voice assistant.
AgentDB Reinforcement Learning Training operates on 3 fundamental principles:
Conversational interface for managing MCP (Model Context Protocol) server configurations in Claude Code
6-phase investigation workflow for understanding existing systems. Auto-activates for research tasks. Optimized for exploration and understanding, not implementation. Includes parallel agent deployment for efficient deep dives and automatic knowledge capture to prevent repeat investigations.
Real-time communication coach for navigating partner/relationship texts. Analyzes incoming messages for emotional subtext, suggests thoughtful responses, helps de-escalate conflict, and provides follow-up conversation strategies. Expert in attachment theory, nonviolent communication (NVC), Gottman research, and healthy relationship dynamics. Activate on "what should I say", "how to respond", "partner text", "relationship message", "what does this mean", "text my partner", "conversation with partner". NOT for manipulation tactics, revenge/ghosting advice, replacing couples therapy, or abusive relationships (seek professional help).
Sends, saves, retrieves, and manages messages within agent conversations. Use this when handling user messages, displaying conversation history, and working with UIMessages for rich rendering.
CRITICAL - Invoke FIRST before ANY Task tool call. This skill gates all agent dispatch. If you are about to use Task tool, STOP and invoke this skill. Enforces oberprompt principles. Triggers on "Task tool", "launch agent", "spawn agent", "dispatch agent", "parallel agents", "subagent", "background agent", "Explore agent", "general-purpose agent", "Bash agent", "Plan agent".
Manages context passing between DAG nodes and spawned agents. Handles context summarization, selective forwarding, and token budget optimization. Activate on 'bridge context', 'pass context', 'summarize context', 'context management', 'agent context'. NOT for execution (use dag-parallel-executor) or aggregation (use dag-result-aggregator).
Extracts key learnings from conversations, debugging sessions, and failed attempts. Use at session end or after solving complex problems to capture insights. Automatically suggests updates to: DISCOVERIES.md (learnings), PATTERNS.md (reusable solutions), new agent creation (repeated workflows). Ensures knowledge persists across sessions.
Proactive context window management via token monitoring, intelligent extraction, and selective rehydration. Use when approaching token limits or needing to preserve essential context. Complements /transcripts and PreCompact hook with proactive optimization.
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.
Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI/Anthropic/Claude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on "LLM streaming", "SSE", "token stream", "chat UI", "real-time AI". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.
Build production computer vision pipelines for object detection, tracking, and video analysis. Handles drone footage, wildlife monitoring, and real-time detection. Supports YOLO, Detectron2, TensorFlow, PyTorch. Use for archaeological surveys, conservation, security. Activate on "object detection", "video analysis", "YOLO", "tracking", "drone footage". NOT for simple image filters, photo editing, or face recognition APIs.
Guides architects on when and how to use goal-seeking agents as a design pattern. This skill helps evaluate whether autonomous agents are appropriate for a given problem, how to structure their objectives, integrate with goal_agent_generator, and reference real amplihack examples like AKS SRE automation, CI diagnostics, pre-commit workflows, and fix-agent pattern matching.
Semantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classification, similarity matching. NOT for counting objects, fine-grained classification (celebrities, car models), spatial reasoning, or compositional queries. Activate on "CLIP", "embeddings", "image similarity", "semantic search", "zero-shot classification", "image-text matching".
Assigns confidence scores to agent outputs based on multiple factors including source quality, consistency, and reasoning depth. Produces calibrated confidence estimates. Activate on 'confidence score', 'how confident', 'certainty level', 'output confidence', 'reliability score'. NOT for validation (use dag-output-validator) or hallucination detection (use dag-hallucination-detector).
AgentDB Vector Search Optimization operates on 3 fundamental principles:
6-phase investigation workflow for understanding existing systems. Auto-activates for research tasks. Optimized for exploration and understanding, not implementation. Includes parallel agent deployment for efficient deep dives and automatic knowledge capture to prevent repeat investigations.
