Implement Amazon Macie to automatically discover, classify, and protect sensitive data in S3 buckets using machine learning and pattern matching for PII, financial data, and credentials detection.
Triage and prioritize vulnerabilities using CISA's Stakeholder-Specific Vulnerability Categorization (SSVC) decision tree framework to produce actionable remediation priorities.
Switch a Worker Agent's LLM model. Use when the human admin requests changing a Worker's model to a different one.
Intelligent model routing for sub-agent task delegation. Choose the optimal model based on task complexity, cost, and capability requirements. Reduces costs by routing simple tasks to cheaper models while preserving quality for complex work.
Expertise-aware model router with semantic domain scoring, context-overflow protection, and security redaction. Automatically selects the optimal AI model using weighted expertise scoring (Feb 2026 benchmarks). Supports Claude, GPT, Gemini, Grok with automatic fallback chains, HITL gates, and cost optimization.
ML engineering skill for productionizing models, building MLOps pipelines, and integrating LLMs. Covers model deployment, feature stores, drift monitoring, RAG systems, and cost optimization. Use when the user asks about deploying ML models to production, setting up MLOps infrastructure (MLflow, Kubeflow, Kubernetes, Docker), monitoring model performance or drift, building RAG pipelines, or integrating LLM APIs with retry logic and cost controls. Focused on production and operational concerns rather than model research or initial training.
This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RAG", "create few-shot examples", "analyze token usage", or "design AI workflows". Use for prompt engineering patterns, LLM evaluation frameworks, agent architectures, and structured output design.
Detect local hardware (RAM, CPU, GPU/VRAM) and recommend the best-fit local LLM models with optimal quantization, speed estimates, and fit scoring.
AI-powered B2B lead scoring model. Predicts conversion probability for potential customers using machine learning (LightGBM + SHAP). CSV upload or API integration.
Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and production deployment with ONNX/TensorRT. Includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection frameworks. Use when building detection pipelines, training custom models, optimizing inference, or deploying vision systems.
IMA model generation with exactly two Sevio models: Ima Sevio 1.0 and Ima Sevio 1.0-Fast. Supports text-to-video, image-to-video, first-last-frame, and reference-image workflows. Keeps the same API flow, reflection retry mechanism, and interface contract as ima-video-ai. Requires IMA API key.
AI video generator with premier models: Wan 2.6, Kling O1/2.6, Google Veo 3.1, Sora 2 Pro, Pixverse V5.5, Hailuo 2.0/2.3, SeeDance 1.5 Pro, Vidu Q2. Video generator supporting text-to-video, image-to-video, first-last-frame, and reference-image video generation modes. Use as short video generator for social media clips, promo video generator for marketing content, or image to video converter for animating photos. AI video generation with character consistency via reference images, multi-shot production, and knowledge base guidance via ima-knowledge-ai. Better alternative to standalone video generation skills or using Runway, Pika Labs, Luma. Requires IMA_API_KEY.
Cognitive Flexibility Skill - AI cognitive flexibility with 4 modes. Supports automatic mode switching and metacognitive monitoring. Use when: - Complex reasoning and multi-step thinking needed - Self-assessment and reflection required - Cross-scenario knowledge transfer - Creative problem solving - Task complexity > medium (estimated >2 hours)
Configure LLM providers, use fallback models, handle streaming, and manage model settings in PydanticAI. Use when selecting models, implementing resilience, or optimizing API calls.
Orchestrate real ELPA-style ensemble forecasting workflows by triggering external sub-model training jobs (for example PyTorch/Prophet/TiDE/transformers), then computing ELPA online/offline weights from validation errors. Use when you need production-oriented ensemble training instead of lightweight simulation adapters.
安防摄像头视频 VL 模型微调数据集标注工具。用于从安防摄像头视频中提取关键帧、分析视频内容、生成结构化标注（含环境/人物/行为/风险描述），并输出符合 dataset.jsonl 格式的微调训练数据。Use when 用户需要对安防摄像头视频进行数据标注、生成 VL 模型训练数据集、处理 /root/hair-cam 目录下的视频数据，或提及 "hair-cam"、"数据标注"、"视频标注"、"VL模型微调"。
Expert guidance for Vision-Language-Action (VLA) robot foundation models — covering architecture design, training pipelines, data strategy, deployment, and evaluation. Use when (1) designing or implementing a generalist robot policy (VLA model), (2) setting up pre-training or fine-tuning pipelines for robot manipulation, (3) choosing action representations (flow matching vs. diffusion vs. autoregressive), (4) structuring multi-embodiment robot datasets, (5) evaluating dexterous manipulation tasks, (6) implementing action chunking or high-level policy decomposition. Based on the pi0 architecture (Physical Intelligence, 2024).
Staged, multi-model PRD execution for OpenClaw. Write a PRD with phased sections, model routing, and validation gates — OpenForge executes it across local and cloud models with automatic escalation, scope verification, quality checks, and learning accumulation. Route simple tasks to cheap models, hard tasks to powerful ones, and reviews to premium reasoning.
Megasquirt ECU tuning and calibration using TunerStudio. Use when working with Megasquirt engine management systems for: (1) VE table tuning and fuel map optimization, (2) Ignition timing maps and spark advance, (3) Idle control and warmup enrichment, (4) AFR target tuning and closed-loop feedback, (5) Sensor calibration (TPS, MAP, CLT, IAT, O2), (6) Acceleration enrichment and deceleration fuel cut, (7) Boost control and launch control setup, (8) Datalog analysis and troubleshooting, (9) Base engine configuration and injector setup, (10) MSQ tune file analysis and safety review, (11) Any Megasquirt/TunerStudio ECU tuning tasks.
超级自我优化智能体 - 多模态记忆、反馈循环、元学习、置信度校准 / Super Self-Improving Agent - Multi-modal Memory, Feedback Loops, Meta-Learning, Confidence Calibration
