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 BrainstormingYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
- gitwalter Bundle Agent Creator
Standardized agent creation and evaluation with mandatory schema validation
- gitwalter Bundle Skill Creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
- gitwalter Skill Pabp Packaging
Platform Application Bundle Protocol (PABP) management, MCP config generators, bundle importers, and compliance verifiers.
- gitwalter Bundle Sending Emails
Send emails using the cached Google Workspace credentials.
- gitwalter Skill Tdd Rigor
Use when implementing any feature or bugfix, before writing implementation code. Enforces the Iron Law of TDD.
- gitwalter Bundle Checking Versions
On-demand version audits using version-registry.json as source of truth
- gitwalter Bundle Generating Agents
Agent definition file generation with mandatory schema validation against schemas/agent.schema.json
- gitwalter Bundle Receiving Updates
Receive and apply updates from the Antigravity Agent Factory including skills, knowledge, and agents
- gitwalter Bundle Researching First
Research existing solutions before building to create multiplied value
- gitwalter Bundle Translating Tests
Convert tests between frameworks (pytest, unittest, behave) and translate test patterns across languages
-
happy-technologies-llc Skill Multi Turn OrderingConfigure multi-turn catalog ordering for conversational item selection, variable collection, and order placement via Virtual Agent
- happy-technologies-llc Skill Chat Summarization Va
Summarize virtual agent chat sessions with topic classification, resolution status, handoff context, and actionable insights for agent productivity
- happy-technologies-llc Skill Conversation Evaluator
Evaluate virtual agent conversations for quality including coherence, accuracy, slot filling, intent matching, and hallucination detection
- gitwalter Bundle Designing Apis
REST API design (resource naming, HTTP methods, status codes), OpenAPI/Swagger documentation, API versioning strategies (URL, header, query), GraphQL schema design, gRPC proto definitions, Pagination patterns, Error response format, Rate limiting headers
- gitwalter Bundle Configuring Stacks
Technology stack selection and configuration skill
- gitwalter Bundle Onboarding Express
Fast-track 10-15 minute onboarding for individual developers with guided prompts and celebrations
- gitwalter Bundle Optimizing Caching
LLM response caching, semantic caching, memoization, cache invalidation
- gitwalter Bundle Updating Knowledge
Interactive skill for reviewing, applying, and managing knowledge updates
- gitwalter Bundle Validating Readmes
Validates that project structure documented in README.md accurately reflects the actual filesystem structure
- gitwalter Bundle Pattern Creator
Standardized agent pattern creation and validation
- gitwalter Bundle Securing Agents
Tactical Blueprint for AI Security and Guardrails. Focuses on prompt injection defense, PII detection, and content safety for agentic systems.
- gitwalter Bundle Training Models
PyTorch training loops, distributed training with DeepSpeed/FSDP, hyperparameter tuning with Optuna, experiment tracking, mixed precision training, checkpointing
- gitwalter Bundle Using Langchain
LangChain 1.x patterns for chains, tools, memory, and structured outputs
- gitwalter Bundle Operating Github
GitHub operations and repository management using the GitHub MCP Server
- happy-technologies-llc Skill Natural Language Queries
Use parser-verified Happy Platform MCP 5.1 natural-language search phrases and fall back to precise encoded table queries
- gitwalter Bundle Committing Releases
Safe commit and release workflow with auto-sync, changelog updates, and learning from failures
- gitwalter Bundle Configuring Systems
Interactive configuration and onboarding skill for Antigravity Agent Factory settings
- gitwalter Bundle Exporting Workshops
Export learning workshops to standalone projects with all necessary artifacts for maximum AI-assisted learning
- gitwalter Bundle Extending Knowledge
Extend Factory knowledge, skills, and templates via research, documents, or user links
- gitwalter Bundle Extending Workflows
Create and extend workflow definitions using the workflow system architecture
- gitwalter Skill Managing Guardrails
Enforcement of safety guardrails, axiom verification, secret scanning, and mutability protections.
- gitwalter Bundle Registering Systems
Precise skill for updating JSON registries, dependency graphs, and manifests.
- gitwalter Bundle Retrieving Advanced
Multi-index RAG, query decomposition, contextual compression, and self-querying retrievers
- gitwalter Bundle Sandboxing Security
Input validation and sanitization, output filtering, code execution safety, and permission management
- gitwalter Bundle Selecting Practices
Guide users through selecting practices that maintain excellence, alignment, and continuous improvement
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 brainstorming, agent-creator, skill-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.