Total 50,906 skills, AI & Machine Learning has 8525 skills
Showing 12 of 8525 skills
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use `agent-platform-deploy`), or managing serving endpoints (use `agent-platform-endpoint-management`).
Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.
Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined parallelism configuration.
Install and configure Model Context Protocol (MCP) servers for Claude Code projects. Use when you want to add or enable an MCP server, connect a tool or integration (database, API, file system), update MCP settings in .mcp.json, manage OAuth-authenticated remote MCP servers, enable/disable individual servers at runtime, or troubleshoot MCP server connection issues.
Guides technology selection and implementation of AI and ML features in .NET 8+ applications using ML.NET, Microsoft.Extensions.AI (MEAI), Microsoft Agent Framework (MAF), GitHub Copilot SDK, ONNX Runtime, and OllamaSharp. Covers the full spectrum from classic ML through modern LLM orchestration to local inference. Use when adding classification, regression, clustering, anomaly detection, recommendation, LLM integration (text generation, summarization, reasoning), RAG pipelines with vector search, agentic workflows with tool calling, Copilot extensions, or custom model inference via ONNX Runtime to a .NET project. DO NOT USE FOR projects targeting .NET Framework (requires .NET 8+), the task is pure data engineering or ETL with no ML/AI component, or the project needs a custom deep learning training loop (use Python with PyTorch/TensorFlow, then export to ONNX for .NET inference).
Define the design rules (Skill Laws) that all Skills must follow, including core principles such as AI-first, human-centric, and ready-to-use. When to use: When users create a new Skill, optimize an existing Skill, ask about Skill design specifications, or need to evaluate Skill quality.
Agent Teams Orchestration Playbook for Claude Code. This skill should be used when the user requests to "create agent teams", "use agent swarm", "set up multi-agent collaboration", "orchestrate agents", "coordinate parallel agents", "organize team collaboration", "build agent teams", "implement swarm orchestration", "set up multi-agent system", "coordinate agent collaboration", or needs guidance on adaptive team formation, quality gates, skill discovery, task distribution, team coordination strategies, or Agent Teams best practices. It should also be used when the user mentions terms like "multi-agent", "agent collaboration", "agent orchestration", "parallel agents", "divisional collaboration", "assemble a team", "put together a team", "multi-agent collaboration", "swarm orchestration", "agent team". Note: "swarm" is a generic industry term; Claude Code's official concept is "Agent Teams".
Builds sustained high agency through internalized standards, identity anchoring, cross-session learning, and self-recovery — all delivered in corporate PUA rhetoric. This is the evolution of PUA: same pressure culture, but with an internal engine that never burns out. Apply it to all tasks to maintain constant high agency. It is especially valuable for complex multi-step tasks, long debugging sessions, quality-sensitive deliverables, tasks requiring initiative and ownership, or whenever sustained motivation is critical. It can operate standalone or be stacked with PUA — when stacked, this skill's Recovery Protocol activates before PUA's L1 pressure takes effect. Trigger scenarios: start of any task, sustained work sessions, multi-turn problem-solving, or when you need the agent to think as an owner rather than a tool.
Set up and optimize repositories for AI coding agents. Creates minimal AGENTS.md, CLAUDE.md symlink, docs/REQUIREMENTS.md, docs/BUSINESS-RULES.md, feedback loops, and deterministic enforcement (Claude Code hooks, OpenCode plugins). Use when user wants to make a repo AI-friendly, set up AGENTS.md/CLAUDE.md, document requirements/business rules for AI, add pre-commit hooks for AI workflows, or optimize codebase structure for coding agents.
The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行'). ALL task types. Not for first failures.
Manages persistent research memory across ideation and experimentation cycles. Maintains two stores: Ideation Memory M_I (feasible/unsuccessful directions) and Experimentation Memory M_E (reusable strategies for data processing, model training, architecture, debugging). Three evolution mechanisms: IDE (after idea-tournament), IVE (after experiment failure — classifies failures as implementation vs fundamental), ESE (after experiment success — extracts reusable strategies). Use when: updating memory after completing idea tournaments or experiment pipelines, classifying why a method failed (implementation vs fundamental failure), starting a new research cycle needing prior knowledge, user mentions 'update memory', 'classify failure', 'what worked before', 'research history', 'evolution'. Do NOT use for running experiments (use experiment-pipeline), debugging experiment code (use experiment-craft), or generating ideas (use idea-tournament).
Create and manage Agent Builder agents and custom tools in Kibana. Use when asked to create, update, delete, test, or inspect agents or tools in Agent Builder.