В каталоге 183 730 навыков в 14 категориях.
MoAI super agent - unified orchestrator for autonomous development. Routes natural language or explicit subcommands (pla...
Agent Factory master skill for intelligent Claude Code agent generation. Includes requirement analysis, domain detection...
Guide Alfred sub-agents to actively invoke AskUserQuestion for ambiguous decisions.
Enterprise Claude Code context window optimization with 2025 best practices: aggressive clearing, memory file management...
Claude Code context window optimization strategies, JIT retrieval, progressive loading, memory file patterns, and cleanu...
Enterprise AI-powered user expertise detection with behavioral analysis, communication pattern recognition, code complex...
Enterprise session state management, token budget optimization, runtime tracking, session handoff protocols, context con...
Claude Code memory management, context persistence, and knowledge retention. Use when managing session memory, persistin...
Enterprise context and session management with token budget optimization and state persistence
Complete guide to MoAI-ADK agents, delegation patterns, and agent orchestration for intelligent task distribution
Enterprise interactive survey orchestrator with AskUserQuestion tool integration, multi-select support, conditional bran...
Adaptive communication patterns and role selection based on user expertise level and request type. Use for personalized...
Production-grade data science specialist with TensorFlow 2.20.0, PyTorch 2.9.0, Scikit-learn 1.7.2 expertise. Master da...
Enterprise Machine Learning specialist with TensorFlow 2.20.0, PyTorch 2.9.0, Scikit-learn 1.7.2 expertise. Master Auto...
Canonical Claude Code authoring kit covering Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandb...
Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. U...
MoAI-ADK's foundational principles - TRUST 5, SPEC-First DDD, delegation patterns, token optimization, progressive discl...
Provides MoAI-ADK foundational principles including TRUST 5 quality framework, SPEC-First DDD methodology, delegation pa...
TAG inventory management, scanning, and orphan detection (Consolidated from moai-alfred-tag-scanning).
TOON Format Specialist - YAML-based token-efficient agent/workflow definitions inspired by BMAD Method patterns
Enterprise LLM Fine-Tuning with LoRA, QLoRA, and PEFT techniques
Retrieval-Augmented Generation systems, vector databases, embedding strategies, and production RAG architectures for ent...
AI/LLM defensive security reference: prompt-injection defense, OWASP LLM Top 10 defensive mapping, MCP and agentic tool-...
End-to-end PC game modding & vertical slice
Serverless GPU cloud for Python with per-second billing on A100/H100/L40S. Use for burst ML training (>13B parameter mod...
Run Python code on cloud GPUs using Modal serverless platform. Use when you need A100/T4/A10G GPU access for training ML...
Use when the user wants to change optimization aggressiveness, switch between aggressive/balanced/thorough modes, or adj...
Use this skill when performing deterministic mode selection for session-start. Reads Phase A STATE.md recommendations +...
Inspect or change Babysitter model-routing policy by phase.
Algorithm/model development and fine-tuning skill. Use for tasks like dataset design/cleaning, supervised fine-tuning (S...
Model selection strategy and routing. Use when choosing between models for different task types, subagent configurations...
Use when validating model downgrades for skills or agents. Runs A/B comparison between current and proposed model, score...
Use when validating or evaluating a trained medical-imaging model. Audits split leakage and validation design, computes...
Model Bias occurs when an AI system produces results that are systematically prejudiced against certain individuals or g...
Identifying, measuring, and mitigating algorithmic bias to ensure equitable outcomes in AI systems.
Creates the model brief: purpose, model class, mechanisms, data, validation level, team, timeline and risks.
Document a deployed ML/AI model so others can use it responsibly. Use when asked to write a model card, document a model...
Document a machine learning model in a structured, transparent format for stakeholders, reviewers, and future maintainer...
When the user needs to evaluate multiple model checkpoints across various benchmarks to identify the best performing mod...
Manage model checkpoint manager operations. Auto-activating skill for ML Training. Triggers on: model checkpoint manager...
Model Checkpoint Manager - Auto-activating skill for ML Training. Triggers on: model checkpoint manager, model checkpoin...
Use this skill when comparing AI or LLM models on benchmarks, capability, cost, latency, context window, or task-specifi...
Use when asked to compare multiple ML models, perform cross-validation, evaluate metrics, or select the best model for a...
AI model configuration patterns for this project. Single source of truth for model definitions. Triggers on "MODEL_CONFI...
MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Cl...
Debug and diagnose model errors in Pollinations services. Analyze logs, find error patterns, identify affected users. Fo...
Generates code that deploys fine-tuned models from SageMaker Serverless Model Customization to SageMaker endpoints or Be...
Deploy trained machine learning models as production-ready services using REST APIs, containers, serverless functions, a...
Deploy a new LLM model via LiteLLM (GitOps) and/or Azure (Terraform + node backend), add it to the ai toolkit, create th...
Fetch current model names from AI providers (Anthropic, OpenAI, Gemini, Ollama), classify them into tiers (fast/default/...
Detect model drift detector operations. Auto-activating skill for ML Deployment. Triggers on: model drift detector, mode...
Automatic model switching based on task complexity for OpenClaw agents. Dynamically escalates between Haiku (simple), So...
Generates python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Us...
Automated reproduction of comprehensive model evaluation benchmarks following the Benchmark Suite V3. Auto-activates for...
Model Evaluation Metrics - Auto-activating skill for ML Training. Triggers on: model evaluation metrics, model evaluatio...
Evaluate and compare ML model performance with rigorous testing methodologies
Managing ML experiments, metrics, parameters, and artifacts using MLflow, Weights & Biases, and best practices for repro...
Model interpretability and explainability using SHAP, LIME, feature importance, and partial dependence plots. Activates...
Model Export Helper - Auto-activating skill for ML Deployment. Triggers on: model export helper, model export helper Par...
Assist with model export helper operations. Auto-activating skill for ML Deployment. Triggers on: model export helper, m...
模型自动降级与故障切换。当主模型请求失败、超时、达到速率限制或配额耗尽时，自动切换到备用模型，确保服务连续性。支持多供应商、多优先级的智能模型选择，提供健康监控、自动重试和错误恢复机制。
为 Hermes Agent 配置模型故障转移，自动切换到备用模型。类似于 FreeRide 的"速率限制自动切换"概念，但专为 Hermes Agent 设计。
基于 PyTorch 框架的昇腾 NPU 模型推理 KVCache 优化技能。分析并改造 LLM 推理模型的 KVCache 实现，覆盖 Legacy 连续缓存与分页注意力（Paged Attention）配 FA 融合算子、MLA 压缩缓...
Interpret ML model predictions using SHAP, LIME, attention visualization, and probing techniques. Use when explaining mo...
CLI commands to add, update, list, and deprecate AI models in the database. Triggers on "add model", "new model", "updat...
Test, validate, and add new AI models to the eval suite. Use when user asks to add new models, test model access, check...
Professional Model Monitor Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflo...
Monitor model performance, detect data drift, concept drift, and anomalies in production using Prometheus, Grafana, and...
Run this before anything else.
Configure Claude Code to use alternative AI model providers by setting up custom API endpoints and authentication. Use t...
Model Pruning Helper - Auto-activating skill for ML Deployment. Triggers on: model pruning helper, model pruning helper...
Build model quantization tool operations. Auto-activating skill for ML Deployment. Triggers on: model quantization tool,...
Model Quantization Tool - Auto-activating skill for ML Deployment. Triggers on: model quantization tool, model quantizat...
Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and co...
Centralized management of machine learning models throughout their lifecycle, including versioning, metadata, and produc...
Manage model registry manager operations. Auto-activating skill for ML Deployment. Triggers on: model registry manager,...
Model Risk Management (MRM) is a framework designed to manage the risk of adverse consequences resulting from decisions...
Choose model tier by task complexity. Keep routine work cheap. Escalate only when required.
Use when route AI model requests to the optimal provider based on task, cost, latency, and capability requirements. Mana...
Intelligent model selection - routes tasks to Haiku (fast/cheap), Sonnet (balanced), or Opus (complex/strategic) based o...
Model selection strategy for subagents — haiku for exploration, sonnet for implementation, opus for architecture/securit...
LLM and ML model deployment for inference. Use when serving models in production, building AI APIs, or optimizing infere...
Ship ML models to production: versioning, eval-gated serving, GPU efficiency, monitoring for drift. Use when a model lea...
Deploy and query Databricks Model Serving endpoints. Use when (1) deploying MLflow models or AI agents to endpoints, (2)...
Use when deploying a trained model behind an API. Covers FastAPI inference services, loading artifacts safely, request v...
Model serving is the process of deploying ML models to production and handling inference requests efficiently at scale.
Deploy ML models on Kubernetes with KServe (formerly KFServing) and NVIDIA Triton Inference Server. Includes canary depl...
Writes the model specification: equations, timing, closures, steady state, shocks, observables and known limitations.
Switch the agent's model at runtime and restart. Use when the user asks to change models (e.g., "switch to kimi", "use o...
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Lea...
Model training is the process of teaching machine learning models to make predictions or decisions based on data. This s...
QuantMind 模型训练配置文件生成器：把自然语言需求（市场/周期/模型/因子/超参/时间切分）转成前端『模型训练 → 导入配置』可直接导入的 quantmind-model-training-config 文件（YAML/JSON，....
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent)...
Step-by-step guidance for model usage.
Model versioning is practice of tracking and managing different versions of machine learning models throughout their lif...
Model Versioning Manager - Auto-activating skill for ML Deployment. Triggers on: model versioning manager, model version...