AI & ML
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
-
gitwalter Bundle Operating Ml EngineeringTactical Blueprint for ML Training, Deployment, and Monitoring. Focuses on production-grade PyTorch loops, distributed training, and MLOps observability.
-
magnus919 Bundle CrewaiBuild role-based multi-agent systems with CrewAI. Agents with Role/Goal/Backstory, task design, crew composition (sequential or hierarchical), tool integration, callbacks, and production deployment. Use when orchestrating multi-agent teams or comparing agent frameworks. Do not use this skill for unrelated requests; route to the nearest named specialist.
- magnus919 Bundle Linear
Manage Linear teams, projects, cycles, issues, comments, workflow state, and documents from a terminal through Linear's public GraphQL API. Use when a user asks to list, search, inspect, create, update, move, or comment on Linear work, or to find Linear documents. Do not use to embed a live agent inside Linear or to build an MCP integration.
- magnus919 Bundle Notion
Operate Notion from a terminal or agent: retrieve pages, query databases, search pages and databases, and update page properties — with a bundled notion-cli script that is read-only by default and gates every create or update behind a --dry-run/--yes confirmation. Use when an agent needs to read Notion content, answer questions from a team wiki or database, or make a confirmed edit. Do not use for building Notion integrations or block-level page composition beyond property updates (that is Notion API application development), or for other knowledge bases (that is their own tooling).
- magnus919 Bundle Stripe
Read Stripe account state from a terminal or agent: balance, payment intents, and subscriptions — and perform guarded mutations like canceling a subscription — backed by a bundled stripe-cli script that is read-only first and gates every state-changing command behind a --dry-run/--yes confirmation. Use when an agent needs to answer questions about account balance, recent payments, active subscriptions, or apply a confirmed subscription cancellation. Do not use for building Stripe payments into an application (that is Stripe integration development), managing Stripe dashboard settings, or other payment processors (that is their own tooling).
- magnus919 Bundle Autogen
Build conversational multi-agent systems with Microsoft AutoGen. AssistantAgent, UserProxyAgent, GroupChat, code execution, nested chats, cancellation tokens, tool integration, and MCP support. Use when building conversation-driven multi-agent systems or comparing agent frameworks. Do not use this skill for unrelated requests; route to the nearest named specialist.
- gitwalter Bundle Programming Python Async
Tactical Blueprint for high-performance Python Asyncio. Focuses on structured concurrency, resource safety, and resilient background processing.
- gitwalter Bundle Managing Google Workspace
Tactical Blueprint for managing Google Workspace (Drive, Gmail, Calendar). Focuses on prescriptive search, organization, and high-fidelity communication.
- gitwalter Skill Pre Completion Check
Use when about to claim work is complete, fixed, or passing, before committing or closing tasks - requires running verification commands and confirming output before making any success claims.
- gitwalter Skill Smart Contract Audit
Skills for performing security audits and gas optimization checks on smart contracts.
- gitwalter Skill Systematic Debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
- gitwalter Bundle Mastering Project Management
Procedural truth for orchestrating high-fidelity software delivery via Plane MCP server.
- gitwalter Bundle Optimizing Langsmith Prompts
Prompt management with LangSmith Hub - versioning, testing, and evaluation
- gitwalter Bundle Developing Trading Strategies
Design and implement algorithmic trading strategies with entry/exit rules, position sizing, and risk parameters
- gitwalter Bundle Evaluating Llms
RAGAS evaluation setup, DeepEval integration, LangSmith evaluation runs, custom metrics, retrieval quality metrics, regression testing for LLM outputs
- gitwalter Skill Synthesizing Knowledge
Structured knowledge capture to extract team wisdom, lessons learned, and best practices for embedding in agent systems
- gitwalter Skill Documentation Generation
Global documentation skill for generating code references, SDLC gate artifacts, and repository management files (README, Changelog, ADRs).
- gitwalter Bundle Building Spring Enterprise
Tactical Blueprint for production-grade Spring Boot 3+ applications. Focuses on procedural execution, tool-calling sequences, and idiomatic excellence.
- gitwalter Skill Retrieving RAG Context Adv
Patterns for using FAISS MCP tools to ingest documents and perform semantic retrieval.
- gitwalter Bundle Building Fastapi Enterprise
Tactical Blueprint for production-grade FastAPI applications. Focuses on procedural execution, tool-calling sequences, and idiomatic excellence.
- gitwalter Skill Dispatching Parallel Agents
Use when facing 2+ independent tasks or failures that can be worked on without shared state or sequential dependencies.
- gitwalter Bundle Orchestrating Crewai Agents
Detailed CrewAI agent design patterns - role design, backstories, collaboration, hierarchical vs sequential processes, tool integration
- gitwalter Skill Subagent Driven Development
Execute plan by dispatching specialized subagents per task. Ensures isolated context and high precision.
- gitwalter Bundle Applying Sqlalchemy Patterns
SQLAlchemy 2.0 patterns (mapped_column, Mapped types), Async engine and sessions, Relationship patterns, Alembic migrations, Repository pattern, Query optimization, Connection pooling
- gitwalter Bundle Checking Alignment
Verify understanding and alignment before major implementations
- gitwalter Bundle Building Dotnet Microservices
Service decomposition, API Gateway with YARP, inter-service communication (gRPC, REST, message bus), distributed caching, health checks, circuit breakers
- gitwalter Bundle Verifying Grounding
Universal two-pass verification for LLM grounding using confidence delta comparison
- gitwalter Bundle Orchestrating Crewai Workflows
Build multi-agent workflows using CrewAI patterns
- gitwalter Bundle Reviewing Clean Code
Systematic code quality review using SOLID principles, code smell detection, and refactoring patterns
- gitwalter Skill Subagent Driven Dev
Use when executing implementation plans with independent tasks in the current session. Subagents follow a two-stage review loop.
- magnus919 Bundle Langchain
Build LLM applications with LangChain. Use when working with LangChain or comparing LLM application frameworks. Do not use this skill for unrelated requests; route to the nearest named specialist.
- magnus919 Bundle Langgraph
Build multi-agent AI systems with LangGraph — the low-level orchestration framework for stateful, graph-based agent workflows. Covers supervisor, swarm, and hierarchical multi-agent patterns; subgraph composition; state management (checkpointers/stores); persistence; evals; and production debugging. Reach for this when designing agent architectures that need cycles, conditional branching, parallel execution, or human-in-the-loop patterns. Do not use this skill for unrelated requests; route to the nearest named specialist.
- magnus919 Bundle Llama Cpp
Operate, configure, benchmark, and troubleshoot llama.cpp across CPU, Metal, CUDA, HIP/ROCm, Vulkan, SYCL, and hybrid or multi-GPU systems. Use when installing or building llama.cpp, selecting or inspecting GGUF models, running llama-cli, serving an OpenAI-compatible API with llama-server, tuning memory and performance, or diagnosing backend, context, template, and API failures. Do not use for model training or fine-tuning, general inference-framework selection, llama-cpp-python or other bindings, LlamaIndex, Ollama, or LM Studio operation.
- gitwalter Skill Requesting Code Review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements. Dispatches the code-reviewer agent.
- gitwalter Skill Verifying Artifact Structures
Verifying the structural integrity of knowledge JSON and workflow markdown files.
- gitwalter Skill Verification Before Completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs. Requires running verification commands and confirming output before making any success claims; evidence before assertions always.
Frequently asked questions
What are AI & ML agent skills?
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
Which AI & ML skills are most installed?
Popular AI & ML skills on SkillMD right now include operating-ml-engineering, crewai, linear. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do AI & ML skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.