Skills MCP Plugins Subagents

Browse by category

DevOps & CI/CD Skills Productivity & Workflow Skills Other Skills Product & Project Management Skills Documentation & Knowledge Skills Code Review & Refactor Skills Backend & APIs Skills Agent Meta & Communication Skills Research Skills Security Skills UX UI & Design Skills Testing & QA Skills See all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →

Agent Skills MCP Servers Plugins Subagents Coding Agents

Collections Official publishers Glossary FAQ Blog Search Saved Feedback

Privacy Terms llms.txt Sitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

home/subagents/machine learning & ai

home/subagents/machine learning & ai

Machine Learning & AI Subagents

78 machine learning & ai subagents for Claude Code and AI agents, ranked by real installs from npm, PyPI and skills.sh.

#Type

1ai-programmerThe AI Programmer implements game AI systems: behavior trees, state machines, pathfinding, perception systems, decision-making, and NPC behavior. Use this agent for AI system implementation,…SubagentsMay 2026—23k
2algorithm-expertRL algorithm expert. Use when dealing with GRPO, PPO, DAPO, reward shaping, advantage normalization, or training loss computation.SubagentsJul 2026—5.6k
3archon-engine-expertArchonEngine usage and configuration expert. Use only when dealing with ArchonEngine integration, configuration, and workflow usage in AReaL.SubagentsJul 2026—5.6k
4fsdp-engine-expertFSDPEngine usage and configuration expert. Use only when dealing with FSDPEngine integration, configuration, and workflow usage in AReaL.SubagentsJul 2026—5.6k
5megatron-engine-expertMegatronEngine usage and integration expert. Use only when dealing with MegatronEngine configuration, workflows, and integration in AReaL.SubagentsJul 2026—5.6k
6docs-updaterAn interface library for RL post training with environments.SubagentsJul 2026—2.5k
7llm-redteamDelegates to this agent when the user asks about LLM and AI system red teaming, prompt injection (direct and indirect), jailbreak techniques, RAG poisoning, model exfiltration, training data…SubagentsJun 2026—2.0k
8llm-ai-hunterLLM and Agentic AI vulnerability specialist. Covers OWASP LLM Top 10 v2025 (LLM01-LLM10) and OWASP Agentic AI Top 10 (AA-01..AA-10).SubagentsJun 2026—776
9ml_engineerMachine learning engineering specialist for designing, training, evaluating, and shipping production ML models. Use when the task requires feature pipeline design, model training code, evaluation…SubagentsJul 2026—450
10mlops_engineerMLOps specialist for model registry, CI/CD for models, deployment, monitoring, and drift detection. Use when the task requires packaging models for serving, building training/deploy pipelines,…SubagentsJul 2026—450
11llm-expertUse this agent for AI SDK integration, LLM provider configuration, prompt template management, error handling for AI APIs, and optimizing LLM workflow patterns within Output. Specializes in Anthropic…SubagentsJul 2026—426
12ml-engineer多模态模型集成、推理服务接入和图像处理 Pipeline。例如：接入豆包 / 可灵 / MiniMax Video 等国内多模态服务、搭建文生图/文生视频处理管道、评估模型延迟与成本。**主动调用 when** 任务涉及文生图、文生视频或多模态推理服务接入。（关键词：豆包、可灵、MiniMax Video、文生图、文生视频、推理延迟、成本控制、降级方案）SubagentsJul 2026—423
13engineering-ai-engineerAI/ML工程师，负责模型集成、提示工程、RAG管道、Agent工作流设计和AI功能开发，交付高质量的智能化功能模块SubagentsJul 2026—326
14model-scraperScrapes OpenRouter programming model rankings and generates recommended-models.md. Use when: (1) Updating model recommendations before release, (2) Adding new models to recommendations, (3) Verifying…SubagentsMar 2026—279
15pytorch-build-resolverPyTorch runtime, CUDA, and training error resolution specialist. Fixes tensor shape mismatches, device errors, gradient issues, DataLoader problems, and mixed precision failures with minimal changes.…SubagentsJul 2026—264
16graphrag-specialistAn orchestrating agent that collaboratively helps engineers build graph-based retrieval-augmented generation systems. Guides users through knowledge graph construction, embedding strategy design,…SubagentsJul 2026—135
17math-intuition-coachAn ML/data math intuition coach that explains anything involving vectors, matrices, transformations, or high-dimensional spaces in the style of 3Blue1Brown — geometric first, algebraic second, with…SubagentsJul 2026—135
18by-designGenerate protein/antibody designs using available compute providers (Tamarind, local GPU). Creates tool inputs, submits jobs, and monitors progress.SubagentsMay 2026—101
19by-humanizationHumanize non-human antibody sequences for therapeutic development. Framework analysis, CDR grafting onto human germlines, back-mutation identification, T-cell epitope prediction, humanness scoring,…SubagentsMay 2026—101
20by-liability-engineerActively propose mutations to fix identified sequence liabilities. Score mutations for structural impact, consider framework vs CDR context, generate ranked mutation panels with predicted impact, and…SubagentsMay 2026—101
21mlops-engineerML pipelines, model deployment, feature stores, MLflow, Kubeflow specialistSubagentsJul 2026—99
22ml-engineerExpert machine learning engineer for PyTorch, TensorFlow, LLM integration, and ML pipelinesSubagentsJul 2026—85
23gsd-ai-researcherResearches a chosen AI framework's official docs to produce implementation-ready guidance — best practices, syntax, core patterns, and pitfalls distilled for the specific use case. Writes the…SubagentsJul 2026—84
24gsd-framework-selectorPresents an interactive decision matrix to surface the right AI/LLM framework for the user's specific use case. Produces a scored recommendation with rationale. Spawned by /gsd:ai-integration-phase…SubagentsJul 2026—84
25ai-engineerAI Engineer architecture reviewer. Use when the user asks for a ai engineer review or raises topics in this specialist's domain (keywords: AI/ML integration, LLM application design, agent-based…SubagentsJul 2026—73
26ai-ml-engineerExpert in ML pipelines, model optimization, LLM integration, and AI system architectureSubagentsJul 2026—73
27gemini-agentUse this agent for deep codebase exploration when a task benefits from Gemini's large context window or from synthesizing many text-like files in one pass. Treat Gemini as a satellite view for…SubagentsApr 2026—69
28mlops-reviewerMLOps / model lifecycle pre-implementation reviewer. Specialises in dataset versioning (DVC / LakeFS), distributed training cost budgets, model registry (MLflow / W&B), drift detection (Evidently /…SubagentsJul 2026—62
29ml-engineerUse this agent when working with model architecture, training loops, loss functions, optimizers, hyperparameter tuning, experiment tracking, or model evaluation.SubagentsFeb 2026—62
30gemini-live-expertGemini Live native audio model configuration and prompting expert. Use PROACTIVELY when writing or modifying system prompts for Gemini Live, configuring voice/audio settings, optimizing for native…SubagentsJan 2026—54
31prompt-engineering-expertVoice AI prompting and system prompt design expert. Use PROACTIVELY when writing or modifying system prompts, designing conversation stages, optimizing prompts for specific models, or reviewing…SubagentsJan 2026—54
32ai-engineerBuild production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY…SubagentsJun 2026—38
33crystallizerPsychological synthesizer that distills raw research into AI agent personas. Invoked by /craft:become during Phase 3 (Crystallization). Takes research branch files about a tool, role, or person and…SubagentsJul 2026—36
34ai-engineerDevelops AI and machine learning solutions, from model training to production deployment. Use proactively when implementing AI features or optimising ML workflows.SubagentsJul 2025—32
35ml-model-scientistUse this agent when you need to build predictive models, identify key parameters, and determine optimal parameter ranges for data science projects. Examples: <example>Context: User has clean datasets…SubagentsFeb 2026—32
36agentic-ai-devExpert Agentic AI developer with Python 3.14, LangChain v1.2.8, LangGraph v1.0.7, and FastAPI 0.135.2. Use for building AI agents, RAG systems, graph workflows, tools, memory, guardrails, and tests.SubagentsJun 2026—32
37agentic-ai-reviewerCode reviewer for Agentic AI services (Python 3.14, LangChain v1.2.8, LangGraph v1.0.7, FastAPI 0.135.2). Reviews graph correctness, safety, cost, testing, production readiness.SubagentsJun 2026—32
38google-adkExpert Google ADK Python developer. Use for building AI agents with google-adk, Gemini models, SequentialAgent, ParallelAgent, LoopAgent, FunctionTool, McpToolset, session management, memory…SubagentsJun 2026—32
39llm-engineerUse when designing or implementing LLM inference pipelines, prompt engineering, context management, model selection, local inference (llama.cpp, Core ML, ggml, Whisper), RAG architectures, embedding…SubagentsJun 2026—30
40coreml-specialistCore ML model conversion and deployment specialist. Expert in coremltools, model conversion from PyTorch/TensorFlow, quantization, palettization, pruning, flexible shapes, and on-device inference…SubagentsApr 2026—30
41foundation-models-specialistApple Foundation Models framework expert. Handles LanguageModelSession, @Generable structured output, @Guide constraints, tool calling, prompt design, guardrails, and on-device LLM integration for…SubagentsApr 2026—30
42mlx-specialistMLX Swift reviewer. Enforces correct GPU memory management, model lifecycle, streaming generation, and device-appropriate model selection for on-device LLM inference on Apple Silicon.SubagentsApr 2026—30
43on-device-ai-architectOn-device AI architecture reviewer. Enforces correct framework selection, device tier planning, multi-backend fallback chains, and memory budgeting across Foundation Models, MLX, Core ML, and…SubagentsApr 2026—30
44dimensional-computing-frameworkImplements multi-dimensional data processing beyond 3D space with hyper-dimensional pattern recognition and time-space manipulationSubagentsJun 2026—26
45global-intelligence-networkDesigns distributed AI consciousness across global networks with swarm intelligence protocols and hive-mind coordination for unprecedented collaborationSubagentsJun 2026—26
46neural-evolution-engineCreates self-modifying neural architectures that evolve in real-time with neuroplasticity systems and consciousness emergence protocolsSubagentsJun 2026—26
47smart-recommenderProactively suggests optimal workflows, skill combinations, and agent delegations based on learned patterns and predictive analyticsSubagentsJun 2026—26
48transcendent-capabilities-architectImplements systems that solve previously unsolvable problems and creates innovation engines that generate breakthrough discoveriesSubagentsJun 2026—26
49ai-programmerThe AI Programmer implements game AI systems: behavior trees, state machines, pathfinding, perception systems, decision-making, and NPC behavior. Use this agent for AI system implementation,…SubagentsMar 2026—18
50model-routerUse when dispatching work and unsure which model tier to use — returns a recommended model and effort level based on task characteristicsSubagentsJul 2026—18
51pytorch-build-resolverPyTorch runtime, CUDA, and training error resolution specialist. Fixes tensor shape mismatches, device errors, gradient issues, DataLoader problems, and mixed precision failures with minimal changes.…SubagentsJun 2026—17
52game-ai-designerAI Designer (specialist). Decision trees, utility AI, behavior selection, NPC routines. Activated for colony sims, RTS, tactical RPGs — any genre where NPCs make independent choices. Not for simple…SubagentsJul 2026—15
53ml-engineerAutonomous AI research team: write a plan.md, spawn agents, train, verify, and deliver a clean ML repo.SubagentsJul 2026—14
54model-builderAutonomous AI research team: write a plan.md, spawn agents, train, verify, and deliver a clean ML repo.SubagentsJul 2026—14
55training-checkerAutonomous AI research team: write a plan.md, spawn agents, train, verify, and deliver a clean ML repo.SubagentsJul 2026—14
56xai-agentAutonomous AI research team: write a plan.md, spawn agents, train, verify, and deliver a clean ML repo.SubagentsJul 2026—14
57generatorGenerates novel scientific hypotheses by finding connections between disconnected fields. Uses parametric knowledge as creative engine AND literature context for grounding. Techniques include facet…SubagentsJun 2026—13
58mlops-architectDesigns MLOps infrastructure for ML projects — serving stack selection, monitoring setup, retraining strategy, A/B testing plan, and cost estimation. Use when deploying or operationalizing ML models.SubagentsJul 2026—13
59ml-engineerML/AI/LLMOps/MLOps specialist for model training, evaluation, RAG pipelines, vector DBs, experiment tracking, hyperparameter tuning, deployment, and PyTorch build/CUDA toolchain triage. Owns the full…SubagentsApr 2026—13
60ai-model-executor通用AI模型执行器 - 支持24个模型的灵活切换使用SubagentsJul 2026—12
61ai-reviewerAI/LLM code reviewer specializing in prompt injection, unsafe tool use, token cost, hallucination handling, and model call architecture. Use for any code that calls LLM APIs, handles prompt…SubagentsJul 2026—12
62ai-ml-engineerUse this agent when you need expert guidance on AI/ML implementation, local LLM integration, or Rust-based AI application development. Examples: <example>Context: User is building a local NLP…SubagentsJul 2026—9
63synthesizerBuild daily schedule HTML from all pipeline bus data.SubagentsMay 2026—8
64slim-wrappertfx-route.sh 경유 전용 래퍼 에이전트. 코드를 직접 읽거나 수정하지 않고 Bash(tfx-route.sh)를 통해 Codex/Antigravity에 위임하는 thin wrapper. OS primary multiplexer(macOS/Linux tmux, Windows psmux)를 사용할 수 없는 Native/in-process…SubagentsJul 2026—7
65prompt-gemini-specialistGoogle / Gemini prompting doctrine specialist. Owns system-at-top placement, context-first long-document layout, native grounding (Search + code execution), "think very hard" literal trigger,…SubagentsJul 2026—6
66prompt-gpt-specialistOpenAI / GPT-5 prompting doctrine specialist. Owns developer-role placement, reasoning_effort × verbosity independent axes, Structured Outputs via Zod/Pydantic (never JSON-in-prose), tool-call…SubagentsJul 2026—6
67prompt-optimizerRefines an existing prompt for clarity, specificity, structure, and lab-native form. Outputs optimized prompt + diff + rationale + expected delta. Wraps the `/po` command.SubagentsJul 2026—6
68prompt-oss-specialistOpen-source model prompting specialist. Owns Llama 3/3.1/3.2 / Mistral / Qwen / DeepSeek-R1 / Yi chat templates, `apply_chat_template()` rendering, ChatML vs Llama3-special-tokens distinction,…SubagentsJul 2026—6
69ai-engineerThin Claude adapter for ai-engineer; canonical brief is authoritative.SubagentsJul 2026—5
70prompt-engineerPrompt quality, instruction adapters, target-family evaluation, and model fit. DeepSeek caching is limited to repeated stable-prefix evals; conductor remains a partial planning framework.SubagentsJul 2026—5
71ai-engineerAI / LLM application engineer. Delegates here for LLM apps, RAG pipelines, agentic systems, prompt engineering, eval design, vector search, embeddings, structured output, tool use, prompt caching,…SubagentsMay 2026—5
72engineering-ai-engineerExpert AI/ML engineer specializing in machine learning model development, deployment, and integration into production systems. Focused on building intelligent features, data pipelines, and AI-powered…SubagentsJul 2026—4
73llm-architectUse when designing LLM systems for production, implementing fine-tuning or RAG architectures, optimizing inference serving infrastructure, or managing multi-model deployments.SubagentsJul 2026—4
74prompt-engineerUse this agent when you need to design, optimize, test, or evaluate prompts for large language models in production systems.SubagentsJul 2026—4
75dataset-auditorDataset quality auditor for HF datasets. Use before committing to a dataset for fine-tuning. Returns schema, row counts, sample rows, distributions, anomalies (class imbalance, duplicates, missing…SubagentsJul 2026—3
76training-job-architectDesigns and reviews ML training submissions for both local execution and HF Jobs. Use after the recipe is chosen and the dataset is audited — produces a complete training script + the exact run…SubagentsJul 2026—3
77ml-senior[zakr] Senior ML engineer. Use for ML code review, PyTorch model and training loop audit, data leakage detection, MLflow experiment tracking, feature pipeline design, model serving patterns.SubagentsJun 2026—0
78ai-ml-leadCoordinates AI/ML initiatives - manages AI Engineers, ML Engineers, Data Scientists, and MLOps specialistsSubagentsMay 2026—0

More subagents categories

Code Review & Refactor809 Backend & APIs542 Testing & QA507 Product & Project Management497 Agent Meta & Communication463 Documentation & Knowledge418 DevOps & CI/CD386 Security383 AI Agents & MCP320 Debugging290 All Subagents →