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.
-
tomevault-io Bundle Td PortmanLjung-Box portmanteau tests for model diagnostics and residual analysis Use when this capability is needed.
- tomevault-io Bundle Update Template
Sync agent and skill definitions from the original power_template repository Use when this capability is needed.
- tomevault-io Bundle Claude Md Audit
Audit the CLAUDE.md hierarchy in a repo for drift between what each CLAUDE.md claims and what's actually on disk. Validates that referenced file paths still exist, flags voice violations (em dashes, "ask" as a noun), and checks the ground-truth facts block for stale tokens (MCP spec date, transports, model lineup). Use when the user asks to audit, validate, check, or verify CLAUDE.md files, says "is my CLAUDE.md still accurate", flags possible doc drift, or wants to sanity-check the docs before a course recording or release. Use when this capability is needed.
- tomevault-io Bundle Cobrapy
Constraints-Based Reconstruction and Analysis for Python. Used for modeling large-scale metabolic networks in microorganisms. Use when this capability is needed.
- tomevault-io Bundle Jax Pde
Advanced sub-skill for JAX focused on solving Partial Differential Equations (PDEs) and Differentiable Physics. Covers Finite Difference Methods (FDM), Neural Operators, and Physics-Informed Neural Networks (PINNs). Use when this capability is needed.
- tomevault-io Bundle Shapely
Manipulation and analysis of planar geometric objects. Based on the widely deployed GEOS library. Provides data structures for points, curves, and surfaces, and standardized algorithms for geometric operations. Use for 2D geometry operations, spatial relationships, set-theoretic operations (intersection, union, difference), point-in-polygon queries, geometric calculations (area, distance, centroid), buffering, simplifying geometries, linear referencing, and cleaning invalid geometries. Essential for GIS operations, spatial analysis, and geometric computations. Use when this capability is needed.
- tomevault-io Bundle Ingestion
Structured workflow for ingesting agent run data into Docent. Use when the user wants to upload evaluation logs or agent transcripts to Docent. Triggers on phrases like "ingest into Docent", "upload to Docent", "import runs to Docent", or when working with agent evaluation data that needs to be loaded into Docent for analysis. Use when this capability is needed.
- tomevault-io Bundle LLM App Development
LLM app development with RAG, prompt engineering, vector databases, and AI agents Use when this capability is needed.
- tomevault-io Bundle Delegation Principle
Core principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents. Use when this capability is needed.
- tomevault-io Bundle U9401066 Automl Stat MCP Feature Delivery
Feature Delivery 技能 (功能交付)
- tomevault-io Bundle Revision Confirm
修订确认。触发：plan-agent 调用或用户通知"plan-agent已修订完成"时使用；读取 draft-plan.md 的"plan-agent修订意见"章节，分析后引导下一步。 Use when this capability is needed.
- tomevault-io Bundle Varunk130 AI UX Skill Library AI Agent UX
AI Agent UX
- tomevault-io Bundle CI Style Review
CI-specific style review that outputs machine-readable JSON. Used by the Gemini style review workflow and the style-reviewer sub-agent. For the complete style rules, see style-review/SKILL.md. Use when this capability is needed.
- tomevault-io Bundle Gene Database
通过E-utilities/Datasets API查询NCBI基因数据库。按基因符号/ID搜索，获取基因信息(RefSeqs、GO、位置、表型)，批量查找，用于基因注释和功能分析。 Use when this capability is needed.
- tomevault-io Bundle Pywayne LLM Chat Ollama Gradio
Gradio-based chat interface for Ollama with multi-session management. Use when working with pywayne.llm.chat_ollama_gradio module to create a web-based chat UI that connects to Ollama models, supports multiple chat sessions, model selection, and streaming responses. Integrates with ChatManager for session management. Use when this capability is needed.
- tomevault-io Bundle Wayfound AI Wayfound Agent Skills Clawhub
Wayfound — Lightweight Self-Supervision
- tomevault-io Bundle Land Skills Into Repo
Install or update an Agent Skills bundle into a repository SSOT (.ai/skills/). Use when this capability is needed.
- tomevault-io Bundle Celeste Python
Use whenever writing, modifying, reviewing, or debugging code involving Celeste, celeste-ai, celeste-python, import celeste, src/celeste, or withceleste app integrations. This includes providers, modalities, models, artifacts, MIME types, parameters, tools, multimodal messages, streaming, structured outputs, protocol/base URL support, OpenSpec changes, and tests. Always use this skill before inventing Celeste types, registries, model catalogs, provider abstractions, request/response shapes, or syntax.
- tomevault-io Bundle Team Composition Patterns
Design optimal agent team compositions with sizing heuristics, preset configurations, and agent type selection. Use this skill when deciding how many agents to spawn for a task, when choosing between a review team versus a feature team versus a debug team, when selecting the correct subagent_type for each role to ensure agents have the tools they need, when configuring display modes (tmux, iTerm2, in-process) for a CI or local environment, or when building a custom team composition for a non-standard workflow such as a migration or security audit. Use when this capability is needed.
- tomevault-io Bundle Oneshot With Feedback
Execute a plan document into code as a single uninterrupted parcel, locally — no sprint loop, no per-phase manual review pauses, and no push during the loop. The user reviews the finished result at the end. Use when the work is most reviewable as a whole — refactors, codemods, migrations, bulk transforms — and per-sprint review would be busywork. LOCAL-ONLY — never pushes during execution. Use when this capability is needed.
- tomevault-io Bundle Github Todo Triage
Use this skill in this repository when asked to fetch, review, triage, or update todos from GitHub issues and pull requests, especially for xing5/mcp-google-sheets. It defines the local workflow for refreshing GitHub state, reviewing new work, prioritizing next actions, and maintaining the repo todo status ledger.
- tomevault-io Bundle Sdd Steering Custom
Create custom steering documents for specialized contexts. Use when you need domain-specific guidance for particular file types, modules, or workflows. Invoked via /sdd-steering-custom. Use when this capability is needed.
- tomevault-io Bundle Tui CLI
Ensures TUI+CLI+Documentation parity for all feature changes. CRITICAL - Use this for EVERY change that affects commands, screens, shortcuts, or settings. Validates that changes are reflected in TUI implementation, CLI commands, docs/cli/, docs/tui/, docs/tui/shortcuts.md, CLAUDE.md, and feature registry. Prevents documentation drift and missing implementations. Use when this capability is needed.
- tomevault-io Bundle Git Analyzer
Analyzes a local Git repository to provide summaries of recent activity, top contributors, and uncommitted changes.
- tomevault-io Bundle Melsaeed276 Flutter Agent Skills Advanced
Advanced Skills
- tomevault-io Bundle Melsaeed276 Flutter Agent Skills Platform
Platform Skills
- tomevault-io Bundle Miaoge Ge Coding Agent Skills Rust Expert
Rust Expert
- tomevault-io Bundle Michaelboeding Skills Patent Lawyer Agent
Patent Lawyer Agent
- tomevault-io Bundle Microsoft Agent Framework Agent Framework
Python Package Management
- tomevault-io Bundle Transformers Huggingface
Expert guidance for working with Hugging Face Transformers library for NLP, computer vision, and multimodal AI tasks. Use when this capability is needed.
- tomevault-io Bundle Net Domain Model
Create domain models following Domain-Driven Design principles Use when this capability is needed.
- tomevault-io Bundle Mjrtl Pm Agent Skills Idea Prioritization
Idea Prioritization (ICE Framework)
- tomevault-io Bundle Modbender Skill Library MCP Agent Evolver
---
- tomevault-io Bundle Modbender Skill Library MCP Documentation
---
- tomevault-io Bundle Modbender Skill Library MCP Strava Python
---
- tomevault-io Bundle Modbender Skill Library MCP Vscode Tunnel
---
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 td-portman, update-template, claude-md-audit. 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.