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.
-
comeonoliver Skill Bigcode Evaluation HarnessBigCode Evaluation Harness - Code Model Benchmarking
61 - comeonoliver Skill Hosted Agents
Hosted Agent Infrastructure
61 - comeonoliver Skill LLM Application Dev Langchain Agent
LangChain/LangGraph Agent Development Expert
61 - comeonoliver Skill LLM Application Dev Prompt Optimize
Prompt Optimization
61 - comeonoliver Skill Splitting Datasets
Process split datasets into training, validation, and testing sets for ML model development. Use when requesting "split dataset", "train-test split", or "data partitioning". Trigger with relevant phrases based on skill purpose.
61 - comeonoliver Skill Memory Systems 3
Memory System Design
61 - comeonoliver Skill Android Emulator Skill
Android Emulator Skill
61 - comeonoliver Skill Security Scanning Security Hardening
Implement comprehensive security hardening with defense-in-depth strategy through coordinated multi-agent orchestration:
61 - comeonoliver Skill Auto Review Loop LLM
Auto Review Loop (Generic LLM): Autonomous Research Improvement
61 - comeonoliver Skill Gradle Build Performance
Gradle Build Performance
61 - comeonoliver Skill XML To Compose Migration
XML to Compose Migration
61 - comeonoliver Skill Bdi Mental States
BDI Mental State Modeling
61 - comeonoliver Skill Compose Performance Audit
Compose Performance Audit
61 - comeonoliver Skill Kotlin Concurrency Expert
Kotlin Concurrency Expert
61 - comeonoliver Skill Optimizing Prompts
This skill optimizes prompts for Large Language Models (LLMs) to reduce token usage, lower costs, and improve performance. It analyzes the prompt, identifies areas for simplification and redundancy removal, and rewrites the prompt to be more concise and effective. It is used when the user wants to reduce LLM costs, improve response speed, or enhance the quality of LLM outputs by optimizing the prompt. Trigger terms include "optimize prompt", "reduce LLM cost", "improve prompt performance", "rewrite prompt", "prompt optimization".
61 - comeonoliver Skill Filesystem Context
Filesystem-Based Context Engineering
61 - comeonoliver Skill Agent Orchestration Multi Agent Optimize
Multi-Agent Optimization Toolkit
61 - comeonoliver Skill Advanced Evaluation
Advanced Evaluation
61 - comeonoliver Skill Context Compression
Context Compression Strategies
61 - comeonoliver Skill Context Degradation
Context Degradation Patterns
61 - comeonoliver Skill Digital Brain Skill
Digital Brain
61 - comeonoliver Skill Project Development
Project Development Methodology
61 - comeonoliver Skill Coding Standards 2
Coding Standards
61 - comeonoliver Skill Context Fundamentals
Context Engineering Fundamentals
61 - comeonoliver Skill Context Optimization
Context Optimization Techniques
61 - comeonoliver Skill Interleaved Thinking
Reasoning Trace Optimizer
61 - comeonoliver Skill Multi Agent Patterns
Multi-Agent Architecture Patterns
61 - comeonoliver Skill Generating Practice Questions
Generate educational practice questions from lecture notes to test student understanding. Use when users request practice questions, exam preparation materials, study guides, or assessment items based on lecture content.
61 - comeonoliver Skill Rxjava To Coroutines Migration
RxJava to Kotlin Coroutines Migration Skill
61 -
kscz0000 Bundle Claude API使用 Claude API 或 Anthropic SDK 构建应用。触发条件：代码导入 `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`，或用户请求使用 Claude API、Anthropic SDK 或 Agent SDK。不触发：代码导入 `openai`/其他 AI SDK、通用编程或 ML/数据科学任务。
- kscz0000 Bundle LLM Council
运行 Fireworks 托管的开源权重模型委员会，比较多个模型的响应并综合出最终答案。触发词：LLM委员会、模型委员会、多模型审议、Fireworks AI委员会、council、多模型对比、模型协商
- kscz0000 Skill Agent Memory
为 AI 智能体提供持久化、可检索的知识管理的混合记忆系统。
- kscz0000 Skill Earllm Build
构建、维护和扩展 EarLLM One Android 项目——一个通过语音管道将蓝牙耳机连接到 LLM 的 Kotlin/Compose 应用。
- kscz0000 Skill RAG Engineer
检索增强生成（RAG）系统构建专家。精通 embedding 模型、向量数据库、分块策略及 LLM 应用的检索优化。触发词：RAG、检索增强生成、向量搜索、embedding、语义搜索、文档检索、上下文检索、知识库、分块策略、pinecone、weaviate、chromadb、pgvector
- kscz0000 Skill Mesh Memory
通过 MCP 为 AI 智能体提供自托管的语义记忆服务。保存工作日志、决策和笔记，跨会话按语义而非关键词召回。基于 Postgres + pgvector，支持自动标签。
- kscz0000 Skill Clarity Gate
RAG 系统的认知质量预检验证。 确保文档在进入知识库前经过适当认证。 生成 CGD（Clarity-Gated Documents）并验证 SOT（Source of Truth）文件。
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 bigcode-evaluation-harness, hosted-agents, llm-application-dev-langchain-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.