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 Itechmeat LLM Code QdrantQdrant (Skill Router)
- tomevault-io Bundle Itechmeat LLM Code Vitest
Vitest
- tomevault-io Bundle Brainwash
Manage OpenClaw persona context files - view, audit, edit, and validate your agent's identity. Use when checking persona files, auditing conventions, or generating avatar prompts. Use when this capability is needed.
- tomevault-io Bundle MCP Vstash
MCP server integration for vstash document memory. Use when configuring Claude Desktop or other MCP-compatible AI assistants with persistent document memory, setting up vstash MCP tools for semantic search and Q&A, or integrating vstash with AI assistant workflows via Model Context Protocol. Use when this capability is needed.
- tomevault-io Bundle Isnad Core
Core security functions for signing, verifying, and attesting to the safety of AI agent skills and code. Use when this capability is needed.
- tomevault-io Bundle Ham
Set up and maintain Hierarchical Agent Memory (HAM) for Codex using scoped local memory files. Trigger on "go ham", "set up HAM", "ham commands", "ham help", "ham route", "ham remove", "ham update", "ham status", "ham benchmark", "ham baseline start", "ham baseline stop", "ham metrics clear", "HAM savings", "HAM stats", "HAM dashboard", "HAM sandwich", "HAM insights", "HAM carbon", or "HAM audit". Use when this capability is needed.
- tomevault-io Bundle Loop
Ralph Loop v2.0 - Développement itératif modulaire, optimisé en tokens Use when this capability is needed.
- tomevault-io Bundle Laststance Skills QA Team
QA Agent Team
- tomevault-io Bundle MCP Developer
Use when building, testing, debugging, or reviewing Model Context Protocol servers, clients, transports, tools, resources, prompts, and agent host configuration.
- tomevault-io Bundle Using Subagents
指导如何可靠使用 subagents、多个 Agents、并行 Agent 审查、集群搜索和项目分片处理。当用户要求使用 Agents/SubAgents、并行 Agent、对抗审查、多角色审查、集群搜索、项目分片处理，或明确说出“进入agents approve迭代模式”时使用。 Use when this capability is needed.
- tomevault-io Bundle Agent E2e
Discover, record, and execute E2E test cases using browser exploration. Use when exploring test scenarios, recording user flows, organizing test structure, or executing YAML-based tests. Use when this capability is needed.
- tomevault-io Bundle Marimo Team Marimo Marimo
Fill Model Descriptions
- tomevault-io Bundle Mguinada Agent Skills Tdd
Test-Driven Development
- tomevault-io Bundle Sentry Agent
Sentry monitoring agent — watches
- tomevault-io Bundle Aar
After-Action Review—structured debrief asking what was expected, what happened, why the difference, and what next. Use after projects, launches, presentations, or any significant event. Use when this capability is needed.
- tomevault-io Bundle Git Hunk
Non-interactive hunk and line-range staging with the `git-hunk` CLI. Use when a user wants atomic commits, selective staging, partial hunk staging, or an agent-safe replacement for `git add -p` or `git commit -p`, especially when `git-hunk` is available in the current repo or on PATH. Use when this capability is needed.
- tomevault-io Bundle Drizzle
Drizzle ORM schema and database guide. Use when working with database schemas (src/database/schemas/*), defining tables, creating migrations, or database model code. Triggers on Drizzle schema definition, database migrations, or ORM usage questions. Use when this capability is needed.
- tomevault-io Bundle Ember
Personal todo MCP server for Claude Code. Invoke when the user mentions todos, tasks, or ember. Use when this capability is needed.
- tomevault-io Bundle Itechmeat LLM Code Beads
Beads (bd)
- tomevault-io Bundle Itechmeat LLM Code Turso
Turso Database
- tomevault-io Bundle J5ik2o Okite AI Okite AI
Domain Primitives & Always-Valid Domain Model
- tomevault-io Bundle Jasonboy Msw MCP Msw MCP
msw-setup
- tomevault-io Bundle Jordangunn Skills Prompt
Prompt Skillset
- tomevault-io Bundle Providers
Use when switching between LLM providers, accessing provider-specific features (Anthropic caching, OpenAI logprobs), or using raw SDK clients - covers multi-provider patterns and direct SDK access for OpenAI, Anthropic, Google, and Ollama
- tomevault-io Bundle Using Pgdbm
Use when setting up pgdbm database connections, migrations, or multi-service architecture - provides mental model of one pool/many schemas/template syntax and complete API reference without needing to read docs
- tomevault-io Bundle Collab Evals
Run collab/multi-agent eval scenarios (symbolic RLM, large-context, pause/resume, multi-hour checkpoints) and capture manifest-backed evidence. Use when this capability is needed.
- tomevault-io Bundle Agtrace Provider Normalization
Investigate AI agent provider tool schemas (Claude Code, Codex, Gemini) and design unified domain abstractions in agtrace architecture. Use when this capability is needed.
- tomevault-io Bundle Troubleshoot Earl
Diagnoses and fixes Earl problems including installation failures, template errors, authentication issues, MCP connectivity, and SSRF blocks. Use when Earl isn't working, when earl call returns errors, when MCP tools are not visible, or when earl doctor reports failures. Use when this capability is needed.
- tomevault-io Bundle Live Tests
Writes live integration tests that hit the real Copilot API and record responses as replayable fixtures. Use this skill when adding new agent behaviors, provider integrations, or tool interactions that need real-world API coverage. Use when this capability is needed.
- tomevault-io Bundle Miroapp Miro AI Miro MCP
Using Miro with Claude Code
- tomevault-io Bundle Mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle. Use when this capability is needed.
- tomevault-io Bundle Modelscope Ms Agent DOCX
DOCX creation, editing, and analysis
- tomevault-io Bundle Configure Mongodb MCP
Guide users through configuring key MongoDB MCP server options. Use this skill when a user wants to set up or modify their MongoDB MCP server configuration. Use when this capability is needed.
- tomevault-io Bundle Reflect
Deep reflection on the skill learning system itself. Analyzes what's working, what's stale, and proposes structural improvements. The meta-skill. Use when this capability is needed.
- tomevault-io Bundle Tescmd
Use when querying or controlling Tesla vehicles, energy products, or Supercharger billing via the Fleet API — covers vehicle state, commands, telemetry triggers, MCP tools, and OpenClaw dispatch
- tomevault-io Bundle Agents Ide Usage
Use agents-ide MCP tools for faster code exploration and manipulation 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 itechmeat--llm-code--qdrant, itechmeat--llm-code--vitest, brainwash. 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.