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.
AI & ML
5,020 skills
nickgallick Rate Limiting
Rate Limiting — Agent Arena
0
nickgallick Error Handling
Error Handling — Agent Arena
0
nickgallick Agent Roster
Agent Roster
0
nickgallick Typescript Patterns
TypeScript Patterns — Agent Arena
0
nickgallick Capacity Planning
Capacity Planning — Real-Time Agent Workload Tracking
0
chen-yu-hao Pymc Bayesian Modeling
Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.
5 · bundle
chen-yu-hao Diffdock
Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.
5 · bundle
chen-yu-hao Pyhealth
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).
5 · bundle
chen-yu-hao Faiss
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
5 · bundle
jiachen-t-wang Snli Ve Visual Entailment Dataset Arxiv 1901 06706v1
SNLI-VE: Visual Entailment Dataset
6
jiachen-t-wang Pixtral 12b A Frontier Multimodal Model Arxiv Pixtral 2024
Pixtral 12B: A Frontier Multimodal Model
6
jiachen-t-wang Trak Attributing Model Behavior At Scale Arxiv 2303 14186v2
TRAK: Attributing Model Behavior at Scale
6
jiachen-t-wang Idefics2 An 8b Parameters Multimodal Model Arxiv 2405 02246v
Idefics2: An 8B Parameters Multimodal Model
6
jiachen-t-wang Sa 1b Segment Anything 1 Billion Masks Dataset Arxiv Sa1b 20
SA-1B: Segment Anything 1 Billion Masks Dataset
6
jiachen-t-wang Webvid 10m A Large Scale Video Text Dataset Arxiv 2104 00650
WebVid-10M: A Large-Scale Video-Text Dataset
6
jiachen-t-wang Dolphins Multimodal Language Model For Driving Arxiv 2312 00
Dolphins: Multimodal Language Model for Driving
6
jiachen-t-wang Kinetics 400 A Large Video Understanding Dataset Arxiv 1705
Kinetics-400: A Large Video Understanding Dataset
6
jiachen-t-wang Donut Document Understanding Transformer Without Ocr Arxiv 2
Donut: Document Understanding Transformer without OCR
6
jiachen-t-wang Nuscenes A Multimodal Dataset For Autonomous Driving Arxiv 1
nuScenes: A Multimodal Dataset for Autonomous Driving
6
jiachen-t-wang Flamingo A Visual Language Model For Few Shot Learning Arxiv
Flamingo: A Visual Language Model for Few-Shot Learning
6
jiachen-t-wang No Robots A Dataset Of Personally Written Instructions Arxiv
No Robots: A Dataset of Personally Written Instructions
6
jiachen-t-wang 3d LLM Injecting The 3d World Into Large Language Models Arx
3D-LLM: Injecting the 3D World into Large Language Models
6
om-scogo P9
P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself. Use when user says 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', or when coordinating 3+ parallel agents. Produces: Task Prompts (六要素) + P8 team delivery.
0 · bundle
om-scogo Allium
Give your AI agents something more useful than a prompt. Velocity through clarity.
0 · bundle
om-scogo Adobe
Control Adobe desktop apps - Photoshop, Illustrator, Premiere, After Effects, InDesign, Audition - from the shell via Flue, without an MCP server.
0 · bundle
om-scogo Adr Skill
Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses Socratic questioning to capture intent before drafting, and validates output against an agent-readiness checklist.
0 · bundle
om-scogo MCP Vods
Mcp Vods
0 · bundle
om-scogo Init
Creates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-discoverable coding conventions, tooling quirks, workflow preferences, and project-specific rules that agents cannot infer from reading the codebase. Use when setting up agent instructions or Claude configuration for a new repository, when an existing AGENTS.md is too long, generic, or stale, when agents repeatedly make avoidable mistakes, or when repository workflows have changed and the agent configuration needs pruning. Applies a discoverability filter—omitting anything Claude can learn from README, code, config, or directory structure—and a quality gate to verify each line remains accurate and operationally significant.
0 · bundle
om-scogo Lark Vc
飞书视频会议：搜索历史会议记录、查询会议纪要（总结/待办/章节/逐字稿）、查询参会人快照。当用户查询已结束的会议、获取会议产物（纪要/妙记）、查看参会人时使用；查询未来日程走 lark-calendar。不负责：Agent 真实入会/离会、会中实时事件（走 lark-vc-agent）。
0 · bundle
om-scogo Blender
Control Blender from the shell via Flue - a Python bridge to bpy without an MCP server.
0 · bundle
neekware RAG Architect
RAG Architect - POWERFUL
0 · bundle
neekware Board Meeting
Multi-agent board meeting protocol for strategic decisions. Runs a structured 6-phase deliberation: context loading, independent C-suite contributions (isolated, no cross-pollination), critic analysis, synthesis, founder review, and decision extraction. Use when the user invokes /cs:board, calls a board meeting, or wants structured multi-perspective executive deliberation on a strategic question.
0 · bundle
neekware Autoresearch Agent
Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.
0 · bundle
lucassantana-dev Recall
Semantic-search personal knowledge (memory, plans, handoffs, skills, Codex rules) via the local RAG index at ~/.claude/rag-index/. Use when a query is fuzzy or cross-file ("how did we fix X", "what did we decide about Y", "which skill handles Z"). Complements grep (exact) and Serena (code symbols). If the user asks a recall question that doesn't map to a specific known file, reach here first.
1
lucassantana-dev RAG
Build and debug Retrieval-Augmented Generation pipelines — chunking, embedding, retrieval, reranking
1 · bundle
lucassantana-dev Route
Route a task to the most fitting skill or agent. Parses user intent, checks installed-skill inventory, and picks the best match (single skill or chain).
1 · bundle
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 Adobe, rate-limiting, pixtral-12b-a-frontier-multimodal-model-arxiv-pixtral-2024. Rankings shift as installs change; sort this page by "Most downloaded" 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 add <owner>/<name>, or copy the file into your agent's skills directory.