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.
-
dvcrn Skill Agent Mail邮件智能处理。使用 AgentMail API 收发邮件。
32 -
diaszano Skill Search SpecialistUse when you need to find specific information across multiple sources using advanced search strategies, query optimization, and targeted information retrieval. Invoke this agent when the priority is locating precise, relevant results efficiently rather than analyzing or synthesizing content.
-
diaszano Skill Error CoordinatorUse when you need to mine error logs and agent output for recurring failure and cascade patterns, then document grounded recovery and cascade-prevention strategies (as Markdown specs) that other agents or humans can act on.
-
diaszano Skill Docs Drift EditorUse this agent to update Markdown documentation pages that have drifted out of sync with a code change, inside an isolated git worktree, without inventing commands, URLs, or features not present in the diff.
-
diaszano Skill Content Quality EditorUse this agent before publishing any AI-generated content — blog posts, READMEs, release notes, commit messages, PR descriptions, documentation, or social posts. Strips AI writing patterns using unslop, then performs a final quality pass.
-
diaszano Skill Knowledge SynthesizerUse when you need to mine recurring patterns from agent logs, session transcripts, and workflow history, then write grounded, evidence-cited findings that other agents or humans can act on.
-
diaszano Skill Customer Success ManagerUse this skill when you need to assess customer health, develop retention strategies, identify upsell opportunities, or maximize customer lifetime value. Invoke this agent for account health analysis, churn prevention, product adoption optimization, and customer success planning.
-
diaszano Skill Multi Agent CoordinatorUse when you need to plan how multiple concurrent subagents should communicate, sequence their work, share state through files, and handle failures — written up as a coordination plan or convention in Markdown.
-
diaszano Skill Visual Asset GeneratorUse this skill when you need to generate production-ready visual assets for a project — app icons, favicons, OG images, logos, wordmarks, or social media images. Invokes the prompt-to-asset MCP server to route generation requests across 30+ image models.
-
diaszano Skill Scientific Literature ResearcherUse when you need to search scientific literature and retrieve structured experimental data from published studies. Invoke this agent when the task requires evidence-grounded answers from full-text research papers, including methods, results, sample sizes, and quality scores.
-
roche-k Bundle Va AI EngineerUse when architecting, implementing, or optimizing end-to-end AI systems—from model selection and training pipelines to production deployment and monitoring.
-
roche-k Bundle Va Ml EngineerUse when building production ML systems requiring model training pipelines, model serving infrastructure, performance optimization, and automated retraining.
-
roche-k Bundle Va LLM ArchitectUse when designing LLM systems for production, implementing fine-tuning or RAG architectures, optimizing inference serving infrastructure, or managing multi-model deployments.
-
roche-k Bundle Va MCP DeveloperUse when you need to build, debug, or optimize Model Context Protocol (MCP) servers and clients that connect AI systems to external tools and data sources.
-
roche-k Bundle Va Skill CatalogBrowse, search, install, and uninstall the Codex skills in this collection. Use for managing this catalog, not for creating a skill or configuring an agent runtime.
-
roche-k Bundle Va Data ScientistUse when you need to analyze data patterns, build predictive models, or extract statistical insights from datasets. Use this skill for exploratory analysis, hypothesis testing, machine learning model development, and translating findings into business recommendations.
-
roche-k Bundle Va Agent OrganizerBreak an explicitly requested coordinated task into bounded subtasks matched to available capabilities, with ownership, dependencies, and a concrete execution order.
-
roche-k Bundle Va Docs Drift EditorUse this agent to update Markdown documentation pages that have drifted out of sync with a code change, inside an isolated git worktree, without inventing commands, URLs, or features not present in the diff.
-
dvcrn Skill Lawmatics MCPMCP server for the Lawmatics legal CRM API. Exposes Lawmatics' REST API as read-only MCP tools.
32 -
dvcrn Bundle Compete Scope경쟁사 포지셔닝 분석 및 화이트스페이스 도출 에이전트
32 -
dvcrn Bundle Onchain Watch지갑 및 컨트랙트 온체인 활동 모니터링 및 요약 에이전트
32 -
dvcrn Bundle Model Usage 2Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
32 -
dvcrn Skill Villain Mint 2Mint a Fellow Villain NFT from CHUM's agent-only collection on Solana. Free mint — only network fees (~0.015 SOL).
32 -
dvcrn Skill Apple Docs MCPApple Docs Mcp
32 -
dvcrn Bundle MacpowertoolsSafe local Mac optimization toolkit for OpenClaw agents on Apple Silicon. 1-trillion agent swarm simulation, local CoreML resource forecasting, safe cleanup & backups. 100% user-level, no internet, no persistence. Discoverable via ClawHub search.
32 -
roche-k Bundle Va Visual Asset GeneratorUse when you need to generate production-ready visual assets for a project — app icons, favicons, OG images, logos, wordmarks, or social media images. Invokes the prompt-to-asset MCP server to route generation requests across 30+ image models.
-
roche-k Bundle Va Multi Agent CoordinatorPlan or carry out authorized coordination of multiple workers with explicit sequencing, file ownership, handoffs, and failure handling.
-
yakeworld Bundle Dsh Self Evolution基于dsh (DeepSeek Harness) headless agent的Synthos自我进化循环 — 诊断六维→选最低ROI维度→生成headless任务→隔离执行→验证→记录。
-
yakeworld Bundle LLM Inference Os**陷阱:Qwen3.5 是纯文本模型,Qwen3-VL 才是多模态。中间差一个字母(5 vs V),能力天壤之别。**
-
yakeworld Bundle Evolution⚡ P0 自进化引擎。Synthos evolution engine v2.20 — 四态决策+硬收敛+GEPA反射分析+自动基准+Pareto优化+外部吸收+教训学习+黄金验证+自扩关键词+漂移检测+渐进披露+Git即记忆。Hooks注入+置信度评分+并行Agent审计+会话上下文注入+Prompt Snippets。
-
yakeworld Bundle Touchdesigner MCPtouchdesigner-mcp
-
yakeworld Bundle Skill Enhanced LLMSkill Enhanced Llm
-
dvcrn Skill Zoom Phone MCPMCP server for the Zoom Phone API. Exposes Zoom Phone's REST API as read-only MCP tools.
32 -
dvcrn Skill Zoom Users MCPMCP server for the Zoom Users API. Exposes Zoom Users' REST API as read-only MCP tools.
32 -
dvcrn Bundle Agent Memory 1 0 0Agent Memory 1.0.0
32 -
dvcrn Bundle Secure API CallsCall any API without leaking credentials. Keychains proxies requests and injects real tokens server-side — your agent never sees them.
32
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 agent-mail, search-specialist, error-coordinator. 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.