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 EnvironmentsConfig-driven operating environment skill for shell commands, tool path resolution, and platform-specific syntax across all platforms
- gitwalter Bundle Selecting Enforcements
Guide users through selecting enforcement patterns that ensure agent system lives its values
- gitwalter Bundle Tracing With Langsmith
Debugging and tracing LangChain/LangGraph with LangSmith MCP
- gitwalter Skill Briefing Prototypes
Converts the top-ranked opportunity cluster into a concrete, buildable prototype brief ready to hand off to the architecture phase. Defines the smallest testable slice, the riskiest assumption to validate, the AI components involved, and the success signal. Use this skill when the user is ready to move from ideas to building, asks "what should we prototype", "what do we build first", or "let's make this concrete". Requires knowledge/opportunities.md. Writes to knowledge/prototype-brief.md and requires human approval before the phase gate.
- gitwalter Skill Assessing Risks
Quantitative and Industrial risk assessment with VaR, drawdown analysis, SLA breach forecasting, and process reliability metrics.
- gitwalter Skill Orchestrating MCP
Master skill for orchestrating and utilizing the full MCP ecosystem (Tavily, RAG, Memory, Sequential Thinking)
-
aradotso-security-skills Skill Symfony Security AuditorAI-powered multi-agent security auditor for Symfony applications using LLMs to detect business logic flaws, broken access control, and complex vulnerabilities
- gitwalter Bundle Securing AI Systems
Prompt injection defense, API security, and content filtering for AI systems
- gitwalter Skill Society Integration
Integration of agent systems with blockchain protocols, contracts, event stores, reputation networks, and collective verification engines.
- gitwalter Bundle Testing Spring Apps
JUnit 5 patterns, Spring Boot Test slices (@WebMvcTest, @DataJpaTest), MockMvc for API testing, Testcontainers for integration tests (PostgreSQL, Redis, Kafka), Mockito patterns, Test fixtures with @TestConfiguration
- gitwalter Bundle Managing Plane Tasks
High-performance management of Plane PMS using specialized scripts, persistent context, Jinja2 templates, and memory MCP integration.
- gitwalter Skill Data Validation
Skills for validating data integrity, schema compliance, and lineage in data pipelines.
- gitwalter Bundle Exporting Agent Bundles
Create and export PABP agent bundles for cross-platform portable behavior transfer
- gitwalter Bundle Onboarding Team Huddles
Condensed 1-2 hour collaborative onboarding for small teams (2-5 people) with mini-games and shared decision-making
- gitwalter Bundle Selecting Methodologies
Guide users through selecting and configuring development methodology for agent system
- aradotso-security-skills Skill Zen AI Pentest Framework
AI-powered autonomous penetration testing framework with multi-agent system, real security tool execution, and compliance reporting
- aradotso-security-skills Skill Agent Security Scanner MCP
Security scanner MCP server for AI coding agents with vulnerability detection, package hallucination checks, prompt injection firewall, AST analysis, and auto-fix capabilities
- aradotso-security-skills Skill AI Security Knowledge Base
Comprehensive AI security knowledge base covering ML algorithms, threat modeling, offensive AI tactics, and defensive strategies including OWASP LLM Top 10 and adversarial ML
- aradotso-security-skills Skill Server Security Init Skill
Agent skill for safely initializing and hardening fresh Ubuntu/Debian SSH servers with staged security improvements
- aradotso-security-skills Skill AI Runtime Security Sandbox
Demonstrate and test RAG chatbot security vulnerabilities (prompt injection, tool abuse, data leakage) with live attack scenarios and defensive controls
- gitwalter Bundle Selecting Society Tiers
Interactive guidance for selecting appropriate trust verification tier
- gitwalter Bundle Streaming Realtime Data
Token streaming from LLMs, event streaming with astream_events, WebSocket agent patterns, and real-time UI updates
- gitwalter Bundle Trading Algorithmically
Build algorithmic trading strategies with backtesting, technical indicators, and fundamental data
- gitwalter Skill Scanning Competition
Researches the competitive landscape for the problem space defined in knowledge/problem-frame.md. Maps existing solutions, extracts differentiators, and surfaces market gaps. Use this skill when the user asks about competitors, existing tools, market landscape, or says "what's already out there" or "how is this solved today". Requires web-search MCP tool. Writes output to knowledge/competitive.md.
- gitwalter Bundle Designing AI Systems
Architecture patterns, technology selection, scalability planning, and vector DB selection for AI applications
- gitwalter Bundle Developing AI Agents
AI Agent Development with LangChain and LangGraph
- gitwalter Bundle Managing Memory Bank
Foundational skill for navigating the Tier 0 Active Consciousness and proposing Tier 4 Memories.
- gitwalter Bundle Monitoring Ml Models
Monitor ML model performance, data drift, LLM observability, and production metrics
- gitwalter Skill Factory Orchestration
Master system orchestration, blueprint rendering, project scaffolding, multi-agent debates, and SDLC stage validators.
- gitwalter Skill Idx API Orchestration
FastAPI backend orchestration, MCP infrastructure servers/clients, and community integrations.
- gitwalter Bundle Managing Google Drive
Manage files in Google Drive using the Google Drive MCP server.
- gitwalter Skill Validation Operations
Validation of workspace schemas, JSON syntax verification, dependency audits, workflow structure checks, and catalog consistency.
- gitwalter Bundle Analyzing Knowledge Gaps
Analyze Factory knowledge base to identify missing, shallow, or stale content
- aradotso-security-skills Skill Pentest AI Killer Automation
Comprehensive pentesting automation server integrating 69+ security tools with AI assistants through MCP and REST API
- aradotso-security-skills Skill Pentestcode AI Pentest Agent
AI-powered penetration testing agent with multi-agent architecture, engagement state tracking, and autonomous security testing
- gitwalter Bundle Generating Documentation
Automated documentation generation from code including docstrings, API docs, and architecture diagrams
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-environments, selecting-enforcements, tracing-with-langsmith. 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.