Back to the catalog
published by aitmpl
50 tools
- agent-managementCreate, manage, and orchestrate AI agents using the AI Maestro CLI. Use when the user asks to "create agent", "list agents", "delete agent",33,599 stars
- agent-messagingSend and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "se33,599 stars
- docs-searchSearch auto-generated codebase documentation for function signatures, API docs, class definitions, and code comments. Use when the user asks33,599 stars
- graph-queryQuery the code graph database to understand component relationships, dependencies, and change impact. Use when the user asks to "find caller33,599 stars
- memory-searchSearch conversation history and semantic memory to recall previous discussions, decisions, and context. Use when the user asks to "search me33,599 stars
- planningCreate and manage persistent markdown planning files for structured task execution. Use when the user asks to "create a plan", "track progre33,599 stars
- agent-evaluationTesting and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—wher33,599 stars
- agent-manager-skillManage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.33,599 stars
- agent-memory-mcpA hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).33,599 stars
- agent-memory-systemsMemory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent33,599 stars
- agent-tool-builderTools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinate33,599 stars
- agents-autogptAutonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent au33,599 stars
- agents-crewaiMulti-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on compl33,599 stars
- agents-langchainFramework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ 33,599 stars
- agents-llamaindexData framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features33,599 stars
- ai-agents-architectExpert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.33,599 stars
- ai-release-hunterDaily digest of AI releases from Anthropic, Meta, Vercel Labs, OpenAI and Google GitHub repos, the Claude Cowork changelog, the claude.dev b33,599 stars
- autonomous-agent-patternsDesign patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loo33,599 stars
- autonomous-agentsAutonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant huma33,599 stars
- behavioral-modesAI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.33,599 stars
- claude-code-guideMaster guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techni33,599 stars
- computer-use-agentsBuild AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Ant33,599 stars
- context7-auto-researchAutomatically fetch latest library/framework documentation for Claude Code via Context7 API33,599 stars
- context-window-managementStrategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, t33,599 stars
- conversation-memoryPersistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, reme33,599 stars
- crewaiExpert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goa33,599 stars
- data-engineerBuild scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and clo33,599 stars
- data-processing-nemo-curatorGPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filterin33,599 stars
- data-processing-ray-dataScalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, 33,599 stars
- data-scientistExpert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling33,599 stars
- datadog-cliDatadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use this when debugging production issues or wo33,599 stars
- deep-researchRun autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.33,599 stars
- deep-research-notebooklmDeep research skill powered by NotebookLM MCP. Conducts structured multi-source research (market analysis, competitive intel, trend analysis33,599 stars
- dispatching-parallel-agentsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies33,599 stars
- distributed-training-pytorch-fsdpExpert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP233,599 stars
- distributed-training-megatron-coreTrains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models 33,599 stars
- distributed-training-pytorch-lightningHigh-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerpl33,599 stars
- distributed-training-accelerateSimplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Au33,599 stars
- distributed-training-ray-trainDistributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparam33,599 stars
- distributed-training-deepspeedExpert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse 33,599 stars
- emerging-techniques-knowledge-distillationCompress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained 33,599 stars
- emerging-techniques-long-contextExtend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long docume33,599 stars
- emerging-techniques-moe-trainingTrain Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost red33,599 stars
- emerging-techniques-model-mergingMerge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending33,599 stars
- emerging-techniques-model-pruningReduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, 33,599 stars
- emerging-techniques-speculative-decodingAccelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference33,599 stars
- evaluation-bigcode-evaluation-harnessEvaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code model33,599 stars
- evaluation-lm-evaluation-harnessEvaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparin33,599 stars
- evaluation-nemo-evaluatorEvaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needin33,599 stars
- fine-tuning-axolotlExpert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support33,599 stars
Looking for something else?QuestionsContact
