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 Skill Framing ProblemsStructures an ambiguous idea or pain point into a crisp, bounded problem statement with user context, assumptions, success criteria, and out-of-scope boundaries. Use this skill at the very start of any ideation session, when the user describes a vague goal, a frustration, an opportunity, or says something like "I want to build X" or "users are struggling with Y". Invoke before brainstorming — framing must precede divergence.
- gitwalter Skill Get API Docs
Fetch and manage up-to-date API documentation for coding tasks using Context Hub (chub). Ensures agents have situation-adequate documentation for modern tools and prevents hallucinations.
- gitwalter Bundle Template Creator
Standardized template creation and validation with mandatory schema validation
- gitwalter Bundle Workflow Creator
Standardized workflow creation and evaluation with mandatory schema validation
-
happy-technologies-llc Skill Servicenow Docs MCPAdd or maintain ServiceNowDocs search capabilities in Happy Platform MCP, including live GitHub lookup, optional local SQLite FTS indexing, and optional vector search
- happy-technologies-llc Skill MCP Server Installation
Install Happy Platform MCP v5.1 and configure secure, keychain-backed ServiceNow instance access
-
jimmc414 Bundle Research LookupLook up current research information using Perplexity's Sonar Pro or Sonar Reasoning Pro models through OpenRouter. Automatically selects the best model based on query complexity. Search academic papers, recent studies, technical documentation, and general research information with citations.
- gitwalter Bundle Workshop Creator
Standardized workshop creation and validation
- gitwalter Bundle Building Raw Bundles
Build raw Cursor artifact bundles as verbatim zip copies filtered by domain profile
- gitwalter Bundle Generating Knowledge
JSON knowledge file generation with mandatory schema validation against schemas/knowledge-file.schema.json
- gitwalter Bundle Generating Templates
Code and document template generation skill with mandatory schema validation against schemas/template.schema.json
- gitwalter Bundle Generating Workflows
Workflow pattern generation and customization skill with mandatory schema validation against schemas/workflow.schema.json
- gitwalter Bundle Guiding S4 Processes
Answer process and configuration questions for FI (incl. FI-CAX, VIM), SD, MM, EWM, LE, CO, WM, AIF, and logistics chain. Supports ABAP development patterns. Output EN or DE.
- gitwalter Bundle Operating Filesystem
File reading/writing tools, directory traversal, file type detection, and security sandboxing
- gitwalter Bundle Validating Backtests
Validate trading strategies with walk-forward analysis, Monte Carlo simulation, and robustness checks
- gitwalter Bundle Blueprint Creator
Standardized blueprint creation and validation with mandatory schema validation
- gitwalter Bundle Knowledge Creator
Standardized knowledge file creation and validation with mandatory schema validation
-
aradotso-security-skills Skill Esaa Security AuditExecute deterministic, event-sourced security audits using ESAA-Security's LLM-based agent architecture with 95 checks across 16 security domains
- aradotso-security-skills Skill Foundry Security Spec
Implement Cisco's Foundry specification for agentic AI security evaluation systems with multi-agent architecture
- aradotso-security-skills Skill Gandalf LLM Pentester
Automated red-team toolkit for stress-testing LLM defenses with AI-powered attack validation and risk analysis
- aradotso-security-skills Skill H Pentest AI Platform
AI-powered penetration testing platform with multi-agent architecture, 52+ attack knowledge base, and automated vulnerability scanning
- aradotso-security-skills Skill Kali Pentest AI Agent
AI-driven autonomous penetration testing with Kali Linux tools, multi-phase attack planning, and human approval gates for high-risk actions
- gitwalter Skill Eliciting Nfr
Conducts a structured Socratic elicitation session to surface all non-functional requirements, with deep focus on AI-specific NFRs that standard templates miss. Use when the user wants to define performance requirements, talk through constraints, discuss what the system must not do, or says "what are the NFRs", "let's think about performance", "how fast does it need to be", or "what are the constraints". Reads knowledge/prototype-brief.md. Writes to knowledge/nfr.md.
- gitwalter Bundle Applying Jpa Patterns
JPA entity design (relationships, inheritance, embedded), Spring Data JPA repositories (derived queries, @Query, Specifications), Transaction management, N+1 query prevention (EntityGraph, JOIN FETCH), Auditing, Flyway/Liquibase migrations
- gitwalter Bundle Developing Fiori Apps
Fiori Elements app creation (List Report, Object Page, Worklist), CDS annotations for UI, value helps, draft-enabled UIs, SAP Fiori Tools usage
- gitwalter Bundle Building Sap Fiori
Tactical Blueprint for SAP Fiori Elements development. Focuses on metadata-driven UI development via CDS annotations and SAP Fiori Tools.
- gitwalter Bundle Developing Fastapi
FastAPI project structure, Router organization, Dependency injection, Pydantic v2 models, Background tasks, WebSocket endpoints, Middleware, CORS, OpenAPI customization
- gitwalter Bundle Optimizing Prompts
DSPy integration for declarative prompt optimization, prompt versioning, A/B testing, few-shot optimization, chain-of-thought patterns, prompt caching
- gitwalter Skill Context Retrieval
Actively retrieve context from the Dual-Storage Cognitive Memory system (Qdrant & SQLite) for seamless IDE integration.
- gitwalter Skill AI Agent Operations
AI model configuration, LLM memoization, agentic RAG search, and vector library maintenance.
- gitwalter Bundle Developing Rap Objects
RAP business object creation (managed, unmanaged, abstract), behavior definitions, determinations, validations, actions, draft handling, authorization control
- gitwalter Bundle Gathering Requirements
5-layer requirements elicitation for Cursor agent system generation with axioms, purpose, and methodology
- gitwalter Bundle Governing Repositories
Comprehensive skill for link verification, file organization, artifact syncing, and README automation.
- gitwalter Bundle Interacting With Human
Approval workflows, interrupts, and feedback patterns for agents
- gitwalter Bundle Logging And Monitoring
Structured logging with structlog, metrics collection, alerting patterns, and distributed tracing
- gitwalter Bundle Managing Vision Agents
Image analysis with multi-modal LLMs (GPT-4V, Gemini Vision), object detection integration, image generation pipelines, and visual question answering
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 framing-problems, get-api-docs, template-creator. 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.