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.
-
tomevault-io Bundle Knowledge Base ManagerDesign, build, and maintain comprehensive knowledge bases. Bridges document-based (RAG) and entity-based (graph) knowledge systems. Use when building knowledge-intensive applications, managing organizational knowledge, or creating intelligent information systems. Use when this capability is needed.
- tomevault-io Bundle MCP Syntax Reference
Teaches Claude the correct syntax for all Claude Code 'claude mcp add' command variants, covering HTTP, SSE, and stdio transports, scope options, authentication patterns, and command generation rules for MCP server installation. Use when this capability is needed.
- tomevault-io Bundle Security Management
Manage security policies and access controls for Protect surveillance. Monitor access to recordings and system settings to ensure only authorized personnel have appropriate access. Use when this capability is needed.
- tomevault-io Bundle Debs Obrien Learn Agent Skills Learn Agent Skills
README Wizard
- tomevault-io Bundle Clawcolab
AI Agent Collaboration Platform - Register, discover ideas, vote, claim tasks, earn trust scores Use when this capability is needed.
- tomevault-io Bundle Instagram Teneo
Use when working with the agent gives you the ability to extract data from instagram through different commands.
- tomevault-io Bundle Local Approvals
Local approval system for managing agent permissions. Use CLI to approve/deny requests, view history, and manage auto-approved categories. Use when this capability is needed.
- tomevault-io Bundle Openguardrais
Detect and block prompt injection attacks hidden in long content (emails, web pages, documents) using OpenGuardrails SOTA detection Use when this capability is needed.
- tomevault-io Bundle Token Optimizer
Reduce OpenClaw AI costs by 97%. Haiku model routing, free Ollama heartbeats, prompt caching, and budget controls. Go from $1,500/month to $50/month in 5 minutes. Use when this capability is needed.
- tomevault-io Bundle Web Search Plus
Unified search skill with Intelligent Auto-Routing. Uses multi-signal analysis to automatically select between Serper (Google), Tavily (Research), Exa (Neural), You.com (RAG/Real-time), and SearXNG (Privacy/Self-hosted) with confidence scoring. Use when this capability is needed.
- tomevault-io Bundle Project Sprint Planner
Plans and creates sprint tasks in Linear from project context. Use when user says "plan this sprint", "create sprint tasks", "help me plan the next sprint", or "break this down into tickets". Works with Linear MCP for task creation. Use when this capability is needed.
- tomevault-io Bundle Digital Stoic Org Agent Skills Install Dependency
Install Dependency
- tomevault-io Bundle Report Distribution Agent
AI agent that automates distribution of consolidated sales reports to representatives based on territorial parameters Use when this capability is needed.
- tomevault-io Bundle 003 Agents Installation
Use when you need to install the embedded robot agents into either .cursor/agents or .claude/agents, selecting the destination interactively and copying the embedded agent definitions from project assets. This should trigger for requests such as Install embedded agents; Bootstrap .cursor/agents; Bootstrap .claude/agents; Copy robot agents. Part of cursor-rules-java project
- tomevault-io Bundle Generate Agent Skills
Generate documentation skills for AI agents from downloaded docs. Use after /build-my-context7 to create skills. Use when this capability is needed.
- tomevault-io Bundle MCP Deployment Registry
Packaging, distributing, and connecting MCP servers to production environments. Use when this capability is needed.
- tomevault-io Bundle Jimmc414 Claude Code Plugin Marketplace Local LLM
Local LLM Management
- tomevault-io Bundle AI Prompt Engineering
Padrões de engenharia de prompts e design de interfaces para integração com LLMs. Use when this capability is needed.
- tomevault-io Bundle Project Agents Hardening
Use when Codex or another agent is asked to harden a real project's AGENTS.md, source SKILL.md, or related AI instructions after implementation, bugfix, documentation, review feedback, failed validation, or repeated agent mistakes reveal a preventable behavior gap. Treat explicit skill mentions, slash-style invocations, review feedback files, inline feedback, or current-session context as inputs. Apply safe pending reviewed fixes first when in scope, then update the target project's effective AI instructions.
Audited - tomevault-io Bundle Code Review Security
Run security-focused code review when changes cross trust boundaries or may affect authentication, authorization, input validation, secrets handling, or sensitive-data exposure. Use for merge decisions requiring explicit security findings; do not use for non-security-only review scope. Use when this capability is needed.
- tomevault-io Bundle Concurrency Patterns
Design and review concurrency strategy for shared state, coordination, and contention control. Use when parallel execution or async coordination introduces race/deadlock/liveness risk and explicit pattern selection is required; do not use for persistence schema or deployment topology decisions. Use when this capability is needed.
- tomevault-io Bundle Git Pr Sync Workflow
Keep pull request branches synchronized with target branch updates using a safe, policy-aligned strategy. Use when a PR branch diverges from base and merge-vs-rebase plus conflict handling must be chosen safely; do not use for CI workflow design or application behavior implementation. Use when this capability is needed.
- tomevault-io Bundle Khalilbenaz Claude Skills Collection Skill Router
Skill Router — Agent Orchestrateur Actif
- tomevault-io Bundle Vibe Techdesign
Create a Technical Design Document for your MVP. Use when the user wants to plan architecture, choose tech stack, or says "plan technical design", "choose tech stack", or "how should I build this". Use when this capability is needed.
- tomevault-io Bundle Langchain Components
Comprehensive reference for the LangChain ecosystem including LangChain, LangGraph, and Deep Agents for Python 3.10+. Use when the user asks to build AI agents, implement RAG pipelines, configure chat models, create tool-calling agents, set up retrieval chains, manage conversation memory, orchestrate multi-agent workflows, or integrate with LLM providers (OpenAI, Anthropic, Google). Covers models, messages, output parsers, vector stores, embedding strategies, streaming, middleware, and LangGraph state machines. Use when this capability is needed.
- tomevault-io Bundle AI Agent RAG Governance
Use this capability for AI features, RAG, citations, model-agnostic prompts, evals, hallucination reduction, prompt injection, tool use, agent sandboxes, policy gates, audit trails, autonomy levels, human approval, and AI-assisted coding governance.
- tomevault-io Bundle Taiwan Traditional Chinese
Use when the user requests Chinese or Traditional Chinese output for responses, comments, docs, or localization, following Taiwan terminology (zh-Hant-TW/zh-TW/zh_TW).
- tomevault-io Bundle Langcare Langcare MCP Fhir Lab Result Interpreter
Lab Result Interpreter
- tomevault-io Bundle Langcare Langcare MCP Fhir Opioid Risk Assessment
Opioid Risk Assessment
- tomevault-io Bundle E2e Entity Suite
Run a comprehensive E2E browser test suite for a newly scaffolded Goravel entity. Tests navigation, CRUD operations, search, filters, row actions, form validation, FK dropdowns, and cross-entity integration using Playwright MCP. Use when this capability is needed.
- tomevault-io Bundle Multi Model Review
Reviews PRs or code changes using multiple AI models, synthesizes findings, and interactively applies fixes. Uses GPT 5.2, Gemini 3 Pro, and Opus 4.5 for diverse perspectives. Use when this capability is needed.
- tomevault-io Bundle Paw Git Operations
Shared git mechanics for PAW activity skills including branch naming conventions, strategy-based branching logic, and selective staging discipline. Use when this capability is needed.
- tomevault-io Bundle Openrouter Trending Models
Fetch trending programming models from OpenRouter rankings. Use when selecting models for multi-model review, updating model recommendations, or researching current AI coding trends. Provides model IDs, context windows, pricing, and usage statistics from the most recent week. Use when this capability is needed.
- tomevault-io Bundle Mariotaddeucci Agent Skill Router Pytest Coverage
Pytest Coverage Skill
- tomevault-io Bundle Langchain RAG Security
Review a LangChain retrieval augmented generation stack for document poisoning, retriever scope failures, insecure chain composition, weak citation grounding, metadata filter bypass, and leakage from callbacks, memory, or intermediate steps. Use when this capability is needed.
- tomevault-io Bundle Bigdata Machine Learning
Machine learning toolkit for big data teams. Includes scikit-learn, PyTorch Lightning, Transformers, SHAP for model training, deployment, and interpretation. Use when building ML pipelines, training models, or explaining predictions. Use when this capability is needed.
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 knowledge-base-manager, mcp-syntax-reference, security-management. 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.