Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Build conversational AI voice agents with ElevenLabs Platform. Configure agents, tools, RAG knowledge bases, multi-voice, and Scribe STT across React, React Native, or Swift. Prevents 34 documented er…
Compare and evaluate embedding models for semantic search
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domain…
Generate EnergyPlus building simulations from natural language descriptions or building images. Use when user asks to 'create building simulation', 'generate IDF', 'simulate X-story building', provide…
Enhance talk notes with Blinkist-style summaries and timestamps. Use when asked to "enhance talk", "improve talk notes", "add timestamps", "blinkist-style talk summary", or "make talk notes better". A…
22 production-ready AI agents with database-driven orchestration for security reviews, code quality analysis, deployment validation, infrastructure checks, and compliance. Auto-activates for security …
Expert in temporal event detection, spatio-temporal clustering (ST-DBSCAN), and photo context understanding. Use for detecting photo events, clustering by time/location, shareability prediction, place…
Given a research goal, use existing skills, training reports, and references to propose a small, concrete experiment plan.
ElizaOS - TypeScript framework for building autonomous AI agents with multi-platform support (Discord, Telegram, Twitter, Farcaster), blockchain integration (EVM, Solana), plugin architecture, multi-a…
Generate and manage text embeddings for semantic search, clustering, and similarity tasks
Real-time breaking news monitor using Grounding API. Continuously scans for market-moving events, classifies urgency (CRITICAL/HIGH/MEDIUM), and triggers immediate alerts to War Room and Notification …
Translate English content to Thai with cultural adaptation for idioms, formality levels (กระผม/ผม/ครับ/ค่ะ/นะ), honorifics, and context-appropriate register. Use when translating to Thai, adapting cul…
Entropy-driven sim2real transfer. Uses maximum entropy RL, domain randomization, and information-theoretic bridging to close the reality gap.
AI and technology ethics review including ethical impact assessment, stakeholder analysis, and responsible innovation frameworks
Provides three production-ready ML training examples (sentiment classification, text generation, RedAI trade classifier) with complete training scripts, deployment configs, and datasets. Use when user…
Capture task outcomes, score performance, and derive rules as token priors for continual learning without model weight changes. Use for post-task feedback, experience capture, pattern extraction, and …
Extract actionable tasks assigned to the user from email text. Filters out informational emails (announcements, newsletters, ads, automated reports) and only processes emails with clear action request…
Implement reusable embedding functions using Gemini embedding models via LangChain with proper error handling and batching for sitemap-crawled content.
Manage emotion detection, LED responses, and mood-based automations for Ezra. Use when working on emotional regulation features, smart home responses, or the Chaos Orb.
Enhance book notes with Blinkist-style summaries. Use when asked to "enhance notes", "improve book notes", "add key insights", "expand notes", or "make notes better". Adds Core Message, Key Insights, …
Episodic Memory Archiver. Stores full conversation transcripts with embeddings and analysis into ArangoDB. Tracks UNRESOLVED sessions for reflection.
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effe…
A specialized Skill that deeply analyzes the nature of tasks based on LLM and determines the appropriate executor (claudecode/codex/coderabbit/user). It replaces simple keyword-based judgments.
Multi-expert evaluation pattern for structured analysis and decision-making. PROACTIVELY activate for: (1) Analyze with expert perspectives, (2) Get multiple viewpoints on a topic, (3) Evaluate option…