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.
-
julianromli Bundle Hermes Wag Summarizer 2Plug & play guide to set up automatic WhatsApp group summaries with Hermes Agent — pairing, bot behavior config, parser script, wrapper, and cron job in one place.
-
spec-kitty Bundle Spec Kitty Charter Doctrine 2Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter", "sync charter", "use doctrine", "set up governance", "charter status", "extract governance config", "load doctrine", "agent profile", "DoctrineService", "action index". Does NOT handle: generic spec writing not tied to governance, direct runtime loop advancement, setup/repair diagnostics, or editorial glossary maintenance.
-
korchasa Bundle Session History Analyzer 2Analyzes past AI IDE sessions (Claude Code, OpenAI Codex, OpenCode) for LLM behavior errors: hallucinated diagnostics, context decay, format loss, language leakage, and excessive reading. Use when the user asks to inspect session history, find agent errors, or build a session error index.
-
trac3r00 Bundle Domain ModelingBuild and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.
-
codealive-ai Bundle Prompt Engineering 3Universal prompt engineering techniques for any LLM. Use when crafting, optimizing, or reviewing prompts for AI models. Triggers on requests like "improve this prompt", "write a system prompt", "optimize my instructions", "help me prompt engineer", "audit this prompt", "review my prompt", or when building agentic systems that need structured prompts.
-
huangjia2019 Skill Github Trending 4Fetch today's GitHub trending repos filtered by AI/LLM/agent/ML topics. Use when user asks about popular AI projects, what's hot on GitHub today, trending open-source releases, or daily tech radar.
-
tools-only Bundle 584 Writer 1664b873Claude Agent System Instructions
7 - tools-only Bundle 584 Writer D3382e65
Claude Agent System Instructions
7 - tools-only Bundle 124 Model 1b0d2355
Model Validation
7 - tools-only Bundle 030 Model 28e73813
C4 Model Diagrams
7 - tools-only Bundle 280 State A735d97b
<!-- Source: https://github.com/SuperiorByteWorks-LLC/agent-project | License: Apache-2.0 | Author: Clayton Young / Superior Byte Works, LLC (Boreal Bytes) -->
7 - tools-only Bundle 2717 Box 1e5cdfee
Box MCP Server
7 - tools-only Bundle 1639 Spec 7de31a7d
Agent讨论协作机制规范
7 - tools-only Bundle 1639 Spec 8e3cf9db
agent-debug-sidebar Specification
7 - tools-only Bundle 039 Pre 2855d2a3
Forecasting Data Model Template
7 - tools-only Bundle 083 Pre F8af7215
Territory Management Data Model Template
7 -
agentlas-ai Skill Install Verification 3Use when verifying that a generated agent package can be installed, discovered by runtimes, and checked without private dependencies.
- tools-only Bundle Research Agent
Research Agent
7 - tools-only Bundle 2443 V1013 Ce9d8c5b
Release v1.0.13 - Federated Registry, Agent Skills & Audit Logging
7 - tools-only Bundle 2587 V1015 9a8914f3
Release v1.0.15 - Virtual MCP Servers, IAM Settings, Skill Security Scanning & Internal JWT Auth
7 - tools-only Bundle 036 Pre 05297006
Consent Data Model Template
7 - tools-only Bundle 067 RAG 3559546e
LangChain4j RAG Implementation Guide
7 - tools-only Bundle 089 Off De809bae
Prompt Caching Quick Reference
7 - tools-only Bundle 137 MCP Eb4ab38d
Model Context Protocol (MCP) Reference
7 - tools-only Bundle 097 Index 4b90993d
Overview of all benchmarks supported by mcpbr for evaluating MCP servers and AI agent capabilities across software engineering, code generation, math reasoning, knowledge, tool use, and security.
7 - tools-only Bundle 097 Index 817e60d4
🎯 Sample MCP Servers
7 - tools-only Bundle 004 Manage B392d1b1
Agent Skills
7 - tools-only Bundle 1757 V105 1785e6b6
Release v1.0.5 - Supply Chain Security & MCP Registry CLI
7 - tools-only Bundle 2500 Edit 92b57853
Quantitative benchmark of basic LLM code editing skill.
7 - tools-only Bundle 285 Swarm Aaca37a6
Swarm Multi-Agent Pattern
7 - tools-only Bundle 2479 Tasks 3e835521
Tasks: 新增新闻分析师 Agent
7 - tools-only Bundle 2479 Tasks 4c951f08
多Agent对抗策略竞技场 - 实施任务
7 - tools-only Bundle Summary
Demonstrates LLM blocks and extract filter
7 - tools-only Bundle 2567 Pie 94fdb61d
<!-- Source: https://github.com/SuperiorByteWorks-LLC/agent-project | License: Apache-2.0 | Author: Clayton Young / Superior Byte Works, LLC (Boreal Bytes) -->
7 - tools-only Bundle 075 Agents 125bbbb5
Supervertaler - AI Agent Documentation
7 - tools-only Bundle 075 Agents 2114e001
Supervertaler - AI Agent Documentation
7
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 hermes-wag-summarizer, spec-kitty-charter-doctrine, session-history-analyzer. 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.