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 Analyzing Eval ErrorsInvestigate errors in letta_evals runs by parsing results JSONL, cross-referencing agent and run state on the Letta server via the Python SDK, and producing structured error reports. Use when an eval run has errors, crashes, or unexpected failures that need diagnosis. Use when this capability is needed.
- tomevault-io Bundle 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). Use when this capability is needed.
- tomevault-io Bundle Signal E2e Test
End-to-end Signal integration testing for coop. Use after implementing or fixing any Signal-related feature, provider interaction, or tool behavior to verify it works through the real Signal protocol and LLM API — not just unit tests. Sends real Signal messages, reads traces, diagnoses failures, and iterates until the feature works. Use when this capability is needed.
- tomevault-io Bundle Multi Agent Comms
Setting up keep-alive, peer trust, send vs request/response patterns Use when this capability is needed.
- tomevault-io Bundle Skillnote Doctor
Use when working with a diagnostic tool for OpenClaw agents -- checks skill registry connectivity, AGENTS.md setup, config file validity, and installed skill health. Use when your setup seems broken, skills aren't loading, or you want to audit your agent's configuration.
- tomevault-io Bundle Rca Analysis
Perform Root Cause Analysis using a multi-agent swarm approach. Use when investigating bugs, failures, performance issues, or any problem requiring systematic diagnosis. Triggers on requests like "why is X failing", "debug this issue", "find the root cause", "investigate this problem", or explicit RCA requests. Use when this capability is needed.
- tomevault-io Bundle Deep
Start deterministic development loop (PLAN->BUILD->REVIEW->FIX->SHIP). Use when user asks to 'deep loop', 'implement feature', 'build with TDD', or mentions multi-agent BUILD. Supports external/ralph modes. Use when this capability is needed.
- tomevault-io Bundle Mattkotsenas Agent Plugins Delve
Delve — Interactive Diff Review
- tomevault-io Bundle MCP Use MCP Use MCP Apps Builder
IMPORTANT: How to Use This Skill
- tomevault-io Bundle Bazinga DB Agents
Agent logs, reasoning, and token tracking. Use when logging interactions, saving reasoning, tracking tokens, or managing events. Use when this capability is needed.
- tomevault-io Bundle Context Assembler
Assembles relevant context for agent spawns with prioritized ranking. Ranks packages by relevance, enforces token budgets with graduated zones, captures error patterns for learning, and supports configurable per-agent retrieval limits. Use when this capability is needed.
- tomevault-io Bundle Fritzprix Libr Agent Agent Init
Agent Init
- tomevault-io Bundle Prompt Library
Library of 18+ ready-to-use prompt templates and executable agents Use when this capability is needed.
- tomevault-io Bundle Email Assistant
Read, search, draft, and send emails via Himalaya CLI or Python IMAP/SMTP. Requires email account configuration. Use when this capability is needed.
- tomevault-io Bundle Cargo Test
Cargo test for Rust testing. Use for Rust testing. Use when this capability is needed.
- tomevault-io Bundle Confluence
Confluence team documentation platform. Use for documentation. Use when this capability is needed.
- tomevault-io Bundle Midjourney
Midjourney AI image generation. Use for creative AI. Use when this capability is needed.
- tomevault-io Bundle Openai Gpt
OpenAI GPT models API for chat, completion, and embeddings. Use for AI integration. Use when this capability is needed.
- tomevault-io Bundle Tensorflow
TensorFlow machine learning platform with Keras. Use for ML models. Use when this capability is needed.
- tomevault-io Bundle Websockets
WebSockets real-time bidirectional communication. Use for real-time features. Use when this capability is needed.
- tomevault-io Bundle Aider Agent
Aider-driven git-aware code edit. Drives the local Ollama LLM, real diff edits, Use when this capability is needed.
- tomevault-io Bundle Gluestack UI V4variants
Guide for creating custom variants for gluestack-ui v4 components - covers tva usage, extending components, variant patterns, and customization strategies. Use when this capability is needed.
- tomevault-io Bundle Go Composition
Composición, embedding y extensibilidad en Go. Usar al extender tipos existentes o combinar comportamientos. Use when this capability is needed.
- tomevault-io Bundle Gologo13 Agent Skills Create Pr
Create PR
- tomevault-io Bundle Dev Rust Patterns
Rust patterns and lessons learned in Capsem. Use when writing Rust code for capsem-core, capsem-app, or capsem-agent. Covers async/tokio patterns, non-blocking I/O, cross-compilation gotchas, error handling, and hard-won lessons from past bugs. Read references/rust-async-patterns.md for the full tokio reference. Use when this capability is needed.
- tomevault-io Bundle PDF Processor
PDF 文献自动处理工具。功能：(1) 扫描 01_articles/ 目录中的 PDF 文件，(2) 使用 MinerU API 转换为 Markdown，(3) 使用 LLM API 生成摘要，(4) 状态跟踪和断点续传。 Use when this capability is needed.
- tomevault-io Bundle Draft Release
Draft a new release. Bumps version, generates CHANGELOG.md from git history, and creates a PR. Use when this capability is needed.
- tomevault-io Bundle Remove Skill
Remove a tracked skill directory and purge non-archived repo references (breaking change). Use when this capability is needed.
- tomevault-io Bundle Guia Matthieu Clawfu Skills Rlm
Recursive Language Model (RLM)
- tomevault-io Bundle Skill Adopter
Adopt and wire enterprise skills into a target project for the AI agent(s) in use. Scans a project to detect its tech stack and configured AI agents (Codex, Copilot, Cursor, Junie, AI Assistant, Claude, Roo), selects relevant skills from the enterprise skills repository, and generates or updates the agent-native configuration files (AGENTS.md, .github/copilot-instructions.md, .cursor/rules.md, .junie/guidelines.md, .aiassistant/rules/, .cursorrules, .roo/rules). Use when onboarding a project onto enterprise skills, switching AI agents, refreshing stale agent configs, or aligning a project's AI setup with the current skills catalog. Use when this capability is needed.
- tomevault-io Bundle Tech Writer
tech-writer agent Use when this capability is needed.
- tomevault-io Bundle UX Designer
ux-designer agent Use when this capability is needed.
- tomevault-io Bundle Anchor
Anchor framework for Solana programs — program structure, PDAs, CPI, IDL, errors, events, zero-copy, constraints, account types, and CLI for agent-driven tooling. Use when this capability is needed.
- tomevault-io Bundle Solana
Solana blockchain development — core concepts, clients, RPC, tokens, and payments for agent-driven tooling. Use when this capability is needed.
- tomevault-io Bundle Talk Normal
Stop LLM slop. A curated system prompt that cuts verbose, corporate-sounding LLM output by 56-73% (measured) while preserving information. Works bilingually (English + Chinese). Installs into your AGENTS.md as an always-on behavior modifier. Use when this capability is needed.
- tomevault-io Bundle Godot Compatibility Checker
自动检测和修复Godot 3.x与4.x之间的API兼容性问题，基于实际项目经验提供针对性解决方案 Use when this capability is needed.
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 analyzing-eval-errors, pyhealth, signal-e2e-test. 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.