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 Managing Memory BankFoundational 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 AutomationComprehensive 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
- gitwalter Bundle Verifying Communications
Enable verified, axiom-compliant communication between Factory agents
- gitwalter Skill Optimizing Models
LoRA/QLoRA/PEFT fine-tuning workflows with Hugging Face transformers
- gitwalter Skill Using Git Worktrees
Use when starting feature work that needs isolation from the current workspace - creates isolated git worktrees. Good for @Operator (PROPS).
- gitwalter Bundle Applying RAG Patterns
Document chunking strategies, hybrid retrieval (semantic + keyword), reranking patterns, and citation/attribution
- gitwalter Bundle Authenticating Dotnet
ASP.NET Core authentication and authorization patterns
- gitwalter Bundle Observing Spring Apps
Micrometer metrics (counters, gauges, timers), Distributed tracing with Micrometer Tracing + Zipkin/Jaeger, Structured logging (Logback + JSON), Spring Boot Actuator endpoints, Prometheus + Grafana setup, Custom health indicators
- gitwalter Bundle Using Prisma Database
Prisma schema design patterns, relations (1:1, 1:N, M:N), migrations workflow, Prisma Client queries (findMany, create, update, transactions), seeding, type-safe queries, and performance optimization.
- gitwalter Bundle Managing Stack Context
Tools for managing the execution environment active SDLC stack (e.g., Python_FastAPI, DotNet_CSharp) to ensure correct workflow routing.
- aradotso-security-skills Skill Awesome AI Security Tools Guide
Navigate and recommend tools from the curated Awesome AI Security Tools list covering autotriage, agent security, AI/ML supply chain, pentest agents, LLM red-teaming, and more.
- aradotso-security-skills Skill Security Investigator Automation
Automated security investigations using Microsoft Sentinel, Defender XDR, GitHub Copilot Agent Skills, and MCP servers for natural language threat hunting
- aradotso-security-skills Skill Vibe Pentest AI Security Testing
AI-powered automated penetration testing tool using multi-agent architecture for web applications, APIs, and admin panels
-
magnus919 Bundle SlackOperate Slack workspaces from a terminal or agent: list channels, read messages, follow threads, search message history, list files, and verify inbound webhook signatures — with a bundled slack-cli script that is read-only by default and gates every send behind a --dry-run/--yes confirmation. Use when an agent needs to read or post Slack data, triage incidents, or answer questions about what was said in a workspace. Do not use for building Slack apps or bots (that is application development) or workspace administration like user provisioning and org settings (that is the Slack admin console).
- gitwalter Skill Repository Maintenance
Systematic maintenance, debugging, updating, and health reporting for the agent factory codebase.
- gitwalter Bundle Applying Ef Core Patterns
Entity Framework Core patterns for data access, migrations, and query optimization
- gitwalter Bundle Managing Knowledge Graphs
Graph RAG patterns, entity extraction with LLMs, relationship mapping, and Neo4j integration
- gitwalter Bundle Onboarding Configurations
Skill for migrating hardcoded environment parameters to the Single Point of Truth configuration
- gitwalter Bundle Onboarding Team Workshops
Collaborative team workshop series for designing customized Cursor agent systems grounded in love, truth, and beauty
- gitwalter Bundle Operating Shell Platforms
Platform-specific shell command considerations for Windows PowerShell and Unix shells
- gitwalter Bundle Processing Data Pipelines
Dataset preparation for ML, HuggingFace datasets, custom loaders, data validation with Great Expectations, feature engineering, data versioning with DVC, preprocessing pipelines
- gitwalter Bundle Verifying With Strawberry
Factual claim verification - the canonical profile of grounding-verification
- gitwalter Bundle Developing Spring Boot
Spring Boot 3+ project setup (Initializr), REST controllers, Service layer patterns, Exception handling (@ControllerAdvice), Profiles and configuration, Bean validation, Async operations
- gitwalter Bundle Ingesting RAG Content
Specialized skill for ingesting rag content
- gitwalter Skill Test Driven Development
Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR.
- gitwalter Bundle Providing Pattern Feedback
Implement inductive learning by observing patterns and proposing improvements to axioms, principles, and methodologies
- gitwalter Bundle Applying LLM Guardrails
NeMo Guardrails setup, Guardrails AI integration, prompt injection prevention, PII detection, content safety, topic control
- gitwalter Bundle Building Dotnet Backend
ASP.NET Core Minimal APIs, Controllers, dependency injection, middleware, background services, options pattern, health checks
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 managing-memory-bank, monitoring-ml-models, factory-orchestration. 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.