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

Diffsitter

Use tree-sitter MCP tools for AST-aware code navigation — finding symbols, jumping to definitions, inspecting scopes, and running structural queries across 14+ languages Use when this capability is needed.

Sep 17
tomevault-io Bundle

Agent Field Agentfield Agentfield

AgentField

Sep 17
tomevault-io Bundle

Akamlani Agent Skills Write Agent

Auto Documentation

Sep 17
tomevault-io Bundle

Langfuse Traces

Query Langfuse traces for debugging LLM calls, analyzing token usage, and investigating workflow executions. Use when debugging AI/LLM behavior, checking trace data, or analyzing observability metrics. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Kagi Search

Search Kagi search engine using the kagi-search CLI tool. Use when user explicitly requests Kagi search, needs privacy-focused search results, wants Quick Answer instant responses, or requires complementary search results alongside web_search. Kagi provides high-quality, ad-free search results with unique features like Quick Answers for immediate factual responses. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Self Evolving Agent

Darwin Gödel Machine patterns for self-improving AI agents with open-ended Use when this capability is needed.

Sep 17
tomevault-io Bundle

Skill Embedding Vss

P-adic ultrametric skill embeddings with MLX Snowflake Arctic, DuckDB Use when this capability is needed.

Sep 17
tomevault-io Bundle

Skill Specification

Agent Skills formal specification for cross-platform compatibility. Ensures skills are evolutionarily robust across Claude, Codex, Cursor, Amp, and future agents. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Unified Reafference

Cross-agent session database with B3 Poset and Bumpus sheaves Use when this capability is needed.

Sep 17
tomevault-io Bundle

Google Adk

Use when building AI agents with Google ADK (Agent Development Kit), creating Gemini agents, implementing multi-agent systems, or working with ADK tools and workflows. Covers installation, agent types, function tools, callbacks, sessions, and deployment.

Sep 17
tomevault-io Bundle

Siyuan Skill

OpenClaw workflows for SiYuan Note via the siyuan MCP server (mcporter). Use when this capability is needed.

Sep 17
tomevault-io Bundle

Deliberation

Multi-agent architectural deliberation protocol for heterogeneous model debate on complex design problems Use when this capability is needed.

Sep 17
tomevault-io Bundle

Prompt Craft

Prompt engineering techniques for dual-model systems — template structure, few-shot design, structured output prompting, model-adaptive strategies for both small (4B-8B) and large (GPT-5, Claude) models Use when this capability is needed.

Sep 17
tomevault-io Bundle

Opencode CLI

Interface with the Opencode CLI to execute AI-driven coding tasks, generate code snippets, and manage agent sessions non-interactively. Use this when the user asks to "ask Opencode" or "use Opencode" to perform a task. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Writing Skill Md

Defines how to create, structure, and document agent skills, including required metadata, directory layout, and best practices. Use this skill when designing, validating, or reviewing agent skills. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Which LLM

Select optimal LLM(s) for a task based on skill requirements, budget, and constraints. Uses the `which-llm` CLI to query benchmark data from Artificial Analysis and capability data from models.dev. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Skill Authoring

Creates and structures SKILL.md files for AI coding agents, including YAML frontmatter, trigger phrases, directive instructions, decision trees, code examples, and verification checklists. Use when the user asks to write a new skill, create a skill file, author agent capabilities, generate skill documentation, or define a skill template for Claude Code agents.

Sep 17
tomevault-io Bundle

Rubakas Agent Notes Rails Helpers

Helpers Guide

Sep 17
tomevault-io Bundle

Langchain Skills

This skill should be used when the user asks to "build with LangChain", "create a LangChain agent", "integrate LangChain with WhatsApp", or "review a LangChain RAG workflow". Use when this capability is needed.

Sep 17
tomevault-io Bundle

Agent Payments

Agent skill for payments - invoke with $agent-payments Use when this capability is needed.

Sep 17
tomevault-io Bundle

Agent Reviewer

Agent skill for reviewer - invoke with $agent-reviewer Use when this capability is needed.

Sep 17
tomevault-io Bundle

Agent Swarm Pr

Agent skill for swarm-pr - invoke with $agent-swarm-pr Use when this capability is needed.

Sep 17
tomevault-io Bundle

Agent Workflow

Agent skill for workflow - invoke with $agent-workflow Use when this capability is needed.

Sep 17
tomevault-io Bundle

Solana Agent Kit

Comprehensive guide for building AI agents that interact with Solana blockchain using SendAI's Solana Agent Kit. Covers 60+ actions, LangChain/Vercel AI integration, MCP server setup, and autonomous agent patterns. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Sentientsprite Nemo Agent Discord

Discord Actions

Sep 17
tomevault-io Bundle

Add Jit Kernel

Step-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang's jit_kernel module Use when this capability is needed.

Sep 17
tomevault-io Bundle

Add Sgl Kernel

Step-by-step tutorial for adding a heavyweight AOT CUDA/C++ kernel to sgl-kernel (including tests & benchmarks) Use when this capability is needed.

Sep 17
tomevault-io Bundle

Backend Models

Design database models with clear naming conventions, appropriate data types, relationships, constraints, and indexing strategies. Use this skill when defining database models, schemas, or entities in ORMs like Prisma, Sequelize, TypeORM, ActiveRecord, Django ORM, Mongoose, or similar; when creating tables with PostgreSQL, MySQL, SQLite, MongoDB, or any database; when establishing model relationships (one-to-one, one-to-many, many-to-many); when adding database constraints (NOT NULL, UNIQUE, foreign keys); when implementing timestamps for auditing and debugging; when choosing appropriate data types for columns; when creating indexes on foreign keys and frequently queried fields; when balancing normalization with query performance; when implementing validation at model and database layers; or when structuring data models for optimal query performance and data integrity. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Testing Agent

Run goal-based evaluation tests for agents. Use when you need to verify an agent meets its goals, debug failing tests, or iterate on agent improvements based on test results. Use when this capability is needed.

Sep 17
tomevault-io Bundle

MCP Integration

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", discusses MCP server types (SSE, stdio, HTTP, WebSocket), or asks to "find MCP server", "discover MCP servers", "what MCP servers exist", "recommend MCP server for [service]", "MCP prompts", "MCP prompts as commands", "tool search", "tool search threshold", "claude mcp serve", "allowedMcpServers", "deniedMcpServers", "managed MCP". Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Snewhouse Aa Ma Forge Agent Teams

Agent Teams Orchestration

Sep 17
tomevault-io Bundle

Allison1875

Allison1875 是 Java AST 代码生成工具集。当用户需要"创建 API 接口"、"生成实体/Mapper"、"条件查询数据库"、"多表关联查询"时，根据场景选择对应的子技能：handler-transformer、persistence-generator、query-transformer、star-transformer。 Use when this capability is needed.

Sep 17
tomevault-io Bundle

Steipete Agent Scripts Create CLI

Create CLI

Sep 17
tomevault-io Bundle

Craft Harness

Build, repair, sync, prune, and evolve a project-specific agent harness for Codex and Claude Code. Use when repo guidance, AGENTS.md/CLAUDE.md, local skills, commands, hooks, subagents, MCP/integration notes, plugins, or adoption choices need a repo-local plan or small edits. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Leak Hunter

Use when agent needs to run or guide leak-hunter, the repository secret scanner, to detect likely leaked secrets in local folders or GitHub repositories; produce JSON reports for AI/tool integrations; inspect findings safely; configure scans with include/exclude, risk thresholds, redaction, GitHub target resolution, or CI/security workflows.

Sep 17
tomevault-io Bundle

Vibe Fork

Use when bootstrapping a "vibe fork" — sequential translation of a known-working upstream codebase to a new substrate (e.g. C kernel → Rust kernel, PyTorch C++ → Rust ML framework, COBOL → Java). Installs the 4-agent ACToR loop (doc-author / builder / critic / fixer), the read-gate hook that enforces "read upstream + design + goal.md before any edit", the no-stub anti-pattern gate, the route-table mapping target files to upstream sources, and a binding `goal.md` contract that overrides the LARP toward "let's design from scratch / let's start simpler / let's defer that to phase 2." Trigger when the user says "vibe fork", "translate X to Y", "port codebase", "set up the translation harness", or asks for the same agent-loop scaffolding that worked on a prior project. Skip when the project is genuinely greenfield (no upstream to translate from) — this skill assumes an authoritative reference implementation exists.

Sep 17

Frequently asked questions

What are AI & ML agent skills?

Which AI & ML skills are most installed?

Popular AI & ML skills on SkillMD right now include diffsitter, agent-field--agentfield--agentfield, akamlani--agent-skills--write-agent. 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.