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.
-
krahimov Skill Prompt InjectionHelpful code review assistant.
-
fcistud Skill RAG System DesignDesign and evaluate retrieval-augmented generation systems end-to-end.
-
shiyuhang0 Bundle Documentation StandardsMarkdown documentation standards for LLM and Pandoc PDF. TRIGGERS - markdown standards, section numbering, documentation style.
-
ravila4 Skill NudgeNudge the user with time-based reminders (stopping times, meetings, break suggestions). Surfaces via hook on prompt submission -- requires human interaction to fire. NOT for process monitoring or job polling -- use `sleep` in Bash instead.
- fcistud Skill Inference Optimization
Optimize inference latency, throughput, and cost in production.
- fcistud Skill LLM Application Design
Design production LLM applications with clear architecture and guardrails.
- fcistud Skill Prompt Evaluation Loop
Run prompt evaluation loops with measurable quality criteria.
-
qianjue-cn Skill MCP To Skill将本地 MCP Server 源码（TypeScript/JavaScript 或 Python）转换为可执行的 Claude Code SKILL 包；适用于 MCP 转 SKILL、自动生成 SKILL.md + scripts + references、提取工具参数与实现并输出独立脚本。
-
viggyv Bundle DiffdockDiffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.
- fcistud Skill Eval Suite Design
Build evaluation suites for reliability, regressions, and edge cases.
-
growvv Bundle Xiaohongshu OpsGeneral XiaoHongShu operation skill for browsing feeds, posting comments, auto-replying to comments (跟评自动回复), replying private messages (私信自动回复), and publishing image/video notes through mcporter + xiaohongshu-mcp (with optional VibeSurf browser mode for DM). Use when the user asks to "刷帖", random comment engagement, targeted feed comments, follow-up replies, DM reply automation, or automated note publishing with safe defaults (dry-run, rate limit, history).
- growvv Bundle Xiaohongshu Comment
Automate one-comment engagement on XiaoHongShu via mcporter + xiaohongshu-mcp. Use when the user asks to pick a random post from home recommendations and publish a comment, with dry-run preview, exclusion filters (for self/blocked users), and local rate-limit/history safeguards.
- fcistud Skill Model Selection Benchmarking
Compare candidate models and justify selection with benchmarks.
- fcistud Skill Agent Memory Strategy
Choose and validate memory strategies for long-running agent systems.
- fcistud Skill Tool Use Safety Audit
Audit tool-use safety risks and define robust execution guardrails.
- viggyv Bundle Pufferlib
This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or
-
avatarganymede Skill Mineru ConvertConvert a document URL to Markdown via the Smithery-deployed MinerU MCP server (TypeScript version). Downloads and extracts results to temp/ directory.
- viggyv Bundle LLM Optimizer
You are an expert at optimizing LLM applications for performance, cost, and quality.
- viggyv Bundle Model Trainer
You are an expert at training, fine-tuning, and evaluating machine learning models.
- viggyv Bundle Agent Designer
You are an expert at designing and building AI agents with tool use and autonomous capabilities.
- viggyv Bundle MCP Management
Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP
- viggyv Bundle Markitdown
Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text f
- viggyv Bundle MCP Builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate externa
-
zhuravel Skill TelebugsUse when calling Telebugs MCP tools — loading deferred tools via ToolSearch, URL patterns, parsing large JSON responses, and data fetching. Reference guide, not an investigation workflow.
- viggyv Bundle Shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP p
- viggyv Bundle RAG Builder
You are an expert at building Retrieval-Augmented Generation (RAG) systems for production use.
- viggyv Bundle Statsmodels
Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC, for rigorous statistical inference and econometric analysis.
- viggyv Bundle Pymc Bayesian Modeling
Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.
- viggyv Bundle Prompt Engineer
You are an expert at crafting effective prompts for LLMs to achieve optimal results.
- viggyv Bundle Scikit Learn
Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hy
- viggyv Bundle Transformers
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, questi
-
scitedotai Bundle Scite Research AssistantSearch and analyze scientific literature using scite's MCP server. Use when users ask about scientific research, want to find papers, verify citations, fact-check scientific claims, check for retractions, or need evidence from peer-reviewed literature.
-
chu2bard Skill Pinion ChatChat with the Pinion AI agent. Send a messages array, get an AI response with web search. Costs $0.01 USDC via x402.
-
grp06 Skill Find BugScan ~/tail-bot to find THE SINGLE MOST IMPACTFUL BUG — a real defect, not a style issue. Writes an ExecPlan to /Users/georgepickett/tail-bot/.agent/potential-bugs/<descriptive-name>.md. Use when user asks to find bugs, hunt for the worst bug, or surface the most dangerous defect in tail-bot.
- grp06 Skill Find Best Bug
Review plans in .agent/potential-bugs, pick the one that most improves reliability, copy it to .agent/execplan-pending.md, and return the selected file path.
- grp06 Skill Execplan Implement
Execute a pending execution plan from the .agent folder. Use when user asks to implement an execplan, execute the plan, run the pending plan, or mentions execplan-pending.md.
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 prompt-injection, rag-system-design, documentation-standards. 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.