Total 56,731 skills, AI & Machine Learning has 9436 skills
Showing 12 of 9436 skills
Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.
Use when you need to create new skills or update existing ones, integrate and package domain knowledge, workflows, scripts and tools into reusable Skills; the newly generated skills must be written in Chinese. Trigger words: create new skill, update skill, create new skill package, expand AI capabilities.
Interactively onboard a project to agent-driven development by running a structured interview and generating a complete AGENTS.md (or CLAUDE.md). Use this skill whenever a user mentions "AGENTS.md", "CLAUDE.md", "agent behavior", "agent instructions", "agent config", "set up agent rules", "onboard agent", "configure claude code", "agent guardrails", "agent workflow", or asks how to tell an AI agent how to behave in their project — even if they just say "help me write AGENTS.md" or "what should go in CLAUDE.md". Always prefer this skill over ad-hoc agent instruction generation.
Implement features from a validated RootSpec specification — test-driven and autonomous. Use this when a user wants to build, code, or implement features from their spec, or when they want to make failing tests pass.
Expert knowledge for Microsoft Foundry (aka Azure AI Foundry) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Foundry agents with Azure OpenAI, vector search/RAG, Sora video, realtime audio, or MCP/LangChain APIs, and other Microsoft Foundry related development tasks. Not for Microsoft Foundry Classic (use microsoft-foundry-classic), Microsoft Foundry Local (use microsoft-foundry-local), Microsoft Foundry Tools (use microsoft-foundry-tools).
On-device, real-time multimodal AI voice and vision assistant powered by Gemma 4 E2B and Kokoro TTS, running entirely locally via FastAPI WebSocket server.
Claude Code skill that makes AI agents respond in caveman-speak, cutting ~65-75% of output tokens while preserving full technical accuracy
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn. Use when creating any figure for a conference paper.
ModelScope integration. Manage data, records, and automate workflows. Use when the user wants to interact with ModelScope data.
Configure-Price-Quote (CPQ) vertical skill for the Customware SPA. Defines the section layout, config schema, business rule templates, and deterministic mapping rules for transforming a DOMAIN.md into a CPQ config object. Use this skill when the Builder Agent classifies a customer's domain as a quoting, pricing, or product configuration system. Trigger signals: products with dependencies, price lists, markup/margin calculations, quote generation, proposal workflows, accessory compatibility, product configuration options.
Enforces complete execution, mode-aware delivery, compact sub-agent communication, independent agent-review gating, validation, and reporting for implementation, bugfix, hardening, documentation, specification, architecture, design, review, and post-mortem tasks. Use whenever work must be completed, reviewed, validated, or documented through an explicit execution mode instead of handled ad hoc.
AI Agent Harness Design Patterns - Memory, Permission, Context Engineering, Delegation, Skill, Hook, Bootstrap. Chinese Version.