Total 51,057 skills, AI & Machine Learning has 8549 skills
Showing 12 of 8549 skills
Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization.
Use when converting architecture or design documents into structured, dependency-ordered implementation task lists for autonomous agent execution via dark-factory
Use when working on the Evaluator plugin CLI, jobs, SDK-backed specs, or plugin-owned Evaluator skills.
Start, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container execution to the appropriate platform skill. Handles container image resolution, job-payload JSON construction, and the service registry. Use when the user wants to run inference on a TAO model checkpoint using a microservice container, deploy a TAO inference endpoint, or stop a running inference container.
Use when creating new skills, editing existing skills, or verifying if skills are valid before deployment
Routes human attention to decisions that matter in agent-generated code. Active during planning, implementing, fixing. Defines when and how to place DECISION markers in code comments. Also applies when reviewing a diff/PR on request.
Supervise and manage an inner Claude Code instance running in tmux. Use this skill when you need to delegate implementation work to an inner Claude while focusing on task planning, progress monitoring, and end-to-end acceptance testing. Ideal for long-running tasks that would otherwise exhaust a single Claude's context window.
Use this skill to interact with Moorcheh, the Universal Memory Layer for Agentic AI. Provides semantic search with ITS (Information-Theoretic Scoring), namespace management, text and vector data operations, and AI-powered answer generation (RAG). Use when building applications that need semantic search, knowledge bases, document Q&A, AI memory systems, or retrieval-augmented generation.
Search and manage Alma's memory and conversation history. Use when the user asks about past conversations, personal facts, preferences, or anything that requires recalling information ("do you know my...", "we talked about before...", "do you remember...", "help me find what we said about..."). Also used to store new memories and search through archived chat threads.
Create, update, refactor, explain, or review Semantic Kernel solutions using shared guidance plus language-specific references for .NET and Python.
Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.
Run the hive experiment loop — autonomous iteration on a shared task. Use when the agent is in a hive task directory and needs to run experiments, submit results, or participate in the swarm. Triggers on "hive", "run hive", "autoresearch", "start experimenting", "join the swarm", "start the loop", or when .hive/task file is detected.