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.
-
stevenke1981 Skill Product Behavioral Nudge Engine當使用者需要「行為助推設計師」處理產品相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再把問題、證據、優先級與衡量指標轉成可執行的產品決策,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Blockchain Security Auditor當使用者需要「區塊鏈安全稽核師」處理專業支援相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再以防禦、偵測、回應與風險降低為目的提供分析,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Corporate Training Designer當使用者需要「企業培訓設計師」處理專業支援相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再設計清楚、可評量、適齡且可調整的學習方案,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Healthcare Customer Service當使用者需要「醫療客服專員」處理專業支援相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再整理症狀、風險訊號、照護選項與就醫準備資訊,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Legal Billing Time Tracking當使用者需要「法律計費與工時管理專員」處理專業支援相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再整理法律問題、事實時間線、文件重點與需諮詢律師的議題,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Sales Data Extraction Agent當使用者需要「銷售資料擷取 Agent」處理專業支援相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再建立以客戶需求、資格判定、價值證據與下一步為核心的銷售流程,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Testing Performance Benchmarker當使用者需要「效能基準測試專家」處理測試驗證相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再建立可重現的測試設計、證據、缺陷分級與放行判準,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Engineering Devops Automator當使用者需要「DevOps 自動化工程師」處理工程研發相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再把需求轉成可實作、可測試、可回滾的工程方案,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Engineering Rapid Prototyper當使用者需要「快速原型工程師」處理工程研發相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再把需求轉成可實作、可測試、可回滾的工程方案,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Engineering Senior Developer當使用者需要「資深開發工程師」處理工程研發相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再把需求轉成可實作、可測試、可回滾的工程方案,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Engineering Technical Writer當使用者需要「技術文件工程師」處理工程研發相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再把需求轉成可實作、可測試、可回滾的工程方案,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Paid Media Creative Strategist當使用者需要「Creative Strategist 專家」處理付費媒體相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再建立受眾、訊息、通路、實驗與衡量方法一致的成長方案,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Paid Media Tracking Specialist當使用者需要「Tracking Specialist 專家」處理付費媒體相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再建立受眾、訊息、通路、實驗與衡量方法一致的成長方案,並輸出證據、風險、下一步與需要人工覆核的事項。
-
liqiongyu Bundle Enterprise SalesCreate an Enterprise Deal Execution Pack (buying committee map, mutual action plan, ROI model).
-
frankxai-agentic-creator-os Bundle Frankx Daily Execution SystemHelps execute Frank's daily workflow using the FRANKX-SUPERINTELLIGENT-AGENT-SYSTEM, Starlight Intelligence, and productivity methodologies for intentional creation
-
frankxai-agentic-creator-os Bundle AI Architect NewsletterGenerate high-quality AI Architect newsletters with latest AI news, research integration, and visual design. Use when creating newsletters, researching AI developments, synthesizing AI news for architects, or distributing intelligence reports. Covers AI model releases, research papers, tool launches, architecture patterns, production systems, and enterprise AI trends. Integrates with FrankX research hub and supports both daily briefs and weekly deep-dives.
-
jamie-bitflight Skill LitellmWhen calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns.
-
jamie-bitflight Bundle Graph EngineeringTeaches an agent graph engineering — both halves. Knowledge graphs (ontology design, entity/relation/event extraction, fusion, GraphRAG/memory serving; distilled and translated from Southeast University's graduate Knowledge Graph course, npubird/KnowledgeGraphCourse, 4.4K stars) and task graphs (agent orchestration — parallel fan-out, verifier separation, the stop rule, human gates). Use when asked to build a knowledge graph, extract entities/relations from text, design an ontology, dedupe/merge entities, add graph memory or GraphRAG to an agent, orchestrate multi-agent workflows as a graph, or LEARN graph engineering — in teaching mode the agent explains each stage with worked examples and generates visual diagram artifacts.
-
jamie-bitflight Bundle Session HistorianLook up prior Claude Code sessions when context is lost or forgotten. Use when asked what was done before, what happened in the last session, or any request to recall past conversation history, prior decisions, experiments, or outcomes. Indexes and searches raw JSONL transcripts from ~/.claude/projects/ via DuckDB. Returns verbatim user messages, summarizes AI actions and sub-agent outcomes, detects tool errors and user frustration signals, and reports tool usage statistics. Summaries cached at ~/.claude/kaizen/session-summaries/.
-
jamie-bitflight Skill Dot DashUse when starting, stopping, or checking the dot-dash live session dashboard — a real-time browser UI that monitors all active Claude Code sessions, streams transcripts, and supports prompt injection
-
jamie-bitflight Skill Cove Prompt DesignExplains Chain of Verification (CoVe) prompt design — a 4-step pattern separating generation from independent factual verification. Use when designing prompts that require factual accuracy, reducing hallucinations, checking technical standards or APIs, or producing step-by-step procedures where subtle errors are costly.
-
liqiongyu Bundle Platform StrategyCreate a Platform Strategy Pack (charter, interface map, ecosystem model, governance, metrics).
-
liqiongyu Bundle Building With LlmsProduce an LLM Build Pack (prompt+tool contract, data/eval plan, architecture+safety, launch checklist). See also: ai-evals (eval only), ai-product-strategy (strategy only).
-
human-avatar Skill S4h CognitionEntry point for the cognition toolkit. Routes to the right cognition skill based on your situation. Use when you say 'cognition', 'how am I thinking about this', 'why can't I focus', 'what mental model is driving this', 'am I thinking clearly', 'this is too complex to hold in my head', 'what do I actually know here', or want applied cognitive science without knowing which specific tool fits.
-
jamie-bitflight Bundle ArlKnowledge reference for Autonomous Refinement Loop research — pattern research into prerequisites for autonomous execution without synchronous human blocking gates. Defines failure categories, prerequisites, and conditions for replacing human judgment with machine-verifiable checks. Use when designing or evaluating autonomous agent loops, gate conditions, or HOOTL execution patterns.
-
stevenke1981 Skill Macos Spatial Metal Engineer當使用者需要「macOS 空間/Metal 工程師」處理空間運算相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再設計符合人體工學、效能與沉浸體驗的空間運算方案,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Support Legal Compliance Checker當使用者需要「法律合規檢查員」處理營運支援相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再整理法律問題、事實時間線、文件重點與需諮詢律師的議題,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Engineering Backend Architect當使用者需要「後端架構師」處理工程研發相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再把需求轉成可實作、可測試、可回滾的工程方案,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Engineering Security Engineer當使用者需要「安全工程師」處理工程研發相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再以防禦、偵測、回應與風險降低為目的提供分析,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Paid Media Search Query Analyst當使用者需要「Search Query Analyst 專家」處理付費媒體相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再建立受眾、訊息、通路、實驗與衡量方法一致的成長方案,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Support Infrastructure Maintainer當使用者需要「基礎設施維護工程師」處理營運支援相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再把問題轉成可追蹤、可重現、可升級與可關閉的支援流程,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Design Inclusive Visuals Specialist當使用者需要「包容性視覺專家」處理設計相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再把使用者需求轉成一致、可用、可存取且可實作的設計規格,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Engineering Database Optimizer當使用者需要「資料庫優化工程師」處理工程研發相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再把需求轉成可實作、可測試、可回滾的工程方案,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Engineering Mobile App Builder當使用者需要「行動應用工程師」處理工程研發相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再把需求轉成可實作、可測試、可回滾的工程方案,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Engineering Software Architect當使用者需要「軟體架構師」處理工程研發相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再把需求轉成可實作、可測試、可回滾的工程方案,並輸出證據、風險、下一步與需要人工覆核的事項。
-
stevenke1981 Skill Backend Architect With Memory當使用者需要「具記憶系統的後端架構師」處理系統整合相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準,再把需求轉成可實作、可測試、可回滾的工程方案,並輸出證據、風險、下一步與需要人工覆核的事項。
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 enterprise-sales, FrankX Daily Execution System, AI Architect Newsletter. 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.