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 Handoff ProtocolsManages work transitions between team members or agents by creating structured handoff documents, summarizing project status, documenting key decisions, blockers, and open questions, and generating onboarding briefs. Use when someone needs to hand off, hand over, or transition a project; pass work to another person or agent; brief a colleague taking over; prepare a shift change summary; or onboard someone mid-task. Produces ready-to-use handoff documents covering current status, next steps, known issues, technical context, and communication templates for both planned and unplanned transfers.
- tomevault-io Bundle Atlassian MCP
Use when querying Jira issues, searching Confluence pages, creating tickets, updating documentation, or integrating Atlassian tools via MCP protocol.
- tomevault-io Bundle Agent Challenges
Agent skill for challenges - invoke with $agent-challenges Use when this capability is needed.
- tomevault-io Bundle Agent Pr Manager
Agent skill for pr-manager - invoke with $agent-pr-manager Use when this capability is needed.
- tomevault-io Bundle Agent Pseudocode
Agent skill for pseudocode - invoke with $agent-pseudocode Use when this capability is needed.
- tomevault-io Bundle Eval Analyzer
Identify AILANG language gaps from agent struggles, analyze eval baselines, and generate actionable insights. PRIMARY PURPOSE is finding what stdlib/prompt improvements would help agents succeed. Use when analyzing eval results, checking benchmarks, or investigating failures. Use when this capability is needed.
- tomevault-io Bundle Model Manager
Test, validate, and add new AI models to the eval suite. Use when user asks to add new models, test model access, check pricing, or update models.yml. Use when this capability is needed.
- tomevault-io Bundle Agent Recorder Fixtures
Record real OpenAI/Anthropic HTTP back-and-forth (requests + responses, including streaming text/event-stream) and print paste-ready Swift fixtures for SwiftAgent unit tests (ReplayHTTPClient) using the AgentRecorder CLI or HTTPReplayRecorder. Use when adding/updating any provider adapter tests (text, streaming, structured outputs, tool calls), when payload formats change, or when debugging agent loop mismatches by inspecting recorded JSON/SSE payloads. Use when this capability is needed.
- tomevault-io Bundle Documentation First
Use when a task introduces or changes a non-trivial feature, architecture decision, public API, data model, migration, AI workflow, operational behavior, or cross-agent plan. Creates the smallest useful durable spec, ADR, executable contract, or validation plan before broad implementation.
- tomevault-io Bundle Neta Adventure
Neta 奇遇剧本技能 - 创建和游玩 AI 驱动的交互式故事冒险。奇遇模式提供故事创作和故事讲述两种模式，Agent 作为 DM 并扮演角色，遵循剧情、规则和特殊指南。 Use when this capability is needed.
- tomevault-io Bundle Sfcc Caching
Unified caching playbook for SFCC (page cache vs custom cache vs service response cache). Use this when improving performance, reducing external calls, designing cache keys/TTLs, or debugging stale cache behavior. Use when this capability is needed.
- tomevault-io Bundle Sfcc Logging
Guide for implementing logging in Salesforce B2C Commerce scripts Use when this capability is needed.
- tomevault-io Bundle C4 Code
Expert C4 Code-level documentation specialist. Analyzes code directories to create comprehensive C4 code-level documentation including function signatures, arguments, dependencies, and code structure. Use when this capability is needed.
- tomevault-io Bundle Google Chrome
Use a headless Chrome browser to read websites or take screenshots. Use when this capability is needed.
- tomevault-io Bundle Github Client
Interact with GitHub repositories, issues, and pull requests. Includes standard templates for commits and PRs. Use when this capability is needed.
- tomevault-io Bundle Ghidra MCP
Reverse engineering with Ghidra via MCP. Use when analyzing binaries, decompiling code, managing functions/symbols/data types, or performing any Ghidra-related reverse engineering task. Use when this capability is needed.
- tomevault-io Bundle Sync Pocock Skills
Sync Matt Pocock's skills from upstream (github.com/mattpocock/skills), apply pi-specific patches that replace Claude Code sub-agent references, and flag new skills or unpatched patterns. Use when user says "sync skills", "update pocock skills", or "check for skill updates". Use when this capability is needed.
- tomevault-io Bundle Tomaspavlin Rohlik MCP Rohlik MCP
Testing MCP Tools
- tomevault-io Bundle Twwch Openskills Prompt Optimizer
---
- tomevault-io Bundle Uv Tutorial Generator
Create structured tutorials from repo analysis and hands-on learning artifacts. Use when turning an ML/LLM codebase understanding into teachable material with objectives, diagrams, runnable examples, and exercises stored under $HUMAN_MATERIAL_PATH/exercises/. Use when this capability is needed.
- tomevault-io Bundle Git Machete
Use whenever invoking the `git machete` CLI to organize branch chains, compute fork points, run stacked rebases/merges, or manage GitHub/GitLab PR/MR chains - especially in a repo that already has a `.git/machete` file. Lists which subcommands modify `.git/machete`, run rebase/merge, run hooks, or read stdin, so the agent can pick the right one and pass the right flags. Crucially, names the commands that MUST be invoked with `-y/--yes` (and the few that have no `-y` and therefore must NOT be invoked at all without a tty) so the agent never hangs on an interactive prompt. Also warns against hand-editing the `.git/machete` layout file.
- tomevault-io Bundle Pywayne Statistics
Comprehensive statistical testing library with 37+ methods for normality tests, location tests, correlation tests, time series tests, and model diagnostics. Use when performing hypothesis testing, A/B testing, data quality checks, time series analysis, or regression model validation. All methods return unified TestResult objects with consistent interface including p-value, statistic, confidence interval, and effect size. Use when this capability is needed.
- tomevault-io Bundle Lark MCP
飞书/Lark 官方 MCP 集成。支持发送消息、创建群组、操作多维表格（Bitable）、导入/搜索文档、知识库查询。触发词：飞书、Feishu、Lark、多维表格、bitable、飞书文档、飞书群。 Use when this capability is needed.
- tomevault-io Bundle Hypothesis Generation
Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic. Use when this capability is needed.
- tomevault-io Bundle Dart MCP Tools
Dart/Flutter MCP tools reference for app lifecycle, hot reload/restart, logging, widget inspection, and code analysis. Use when debugging Flutter applications. Use when this capability is needed.
- tomevault-io Bundle Yaosqee Xilian Agent Xilian Agent
UI/UX Pro Max - Design Intelligence
- tomevault-io Bundle Ask Codex
Use when a Claude Code agent needs to delegate a question, subtask, or review to a local Codex instance.
- tomevault-io Bundle Research Executor
Execute complete 7-phase deep research workflow by delegating to the research-orchestrator-agent. Thin wrapper skill that ensures proper agent invocation with structured research prompts. Use when this capability is needed.
- tomevault-io Bundle Simple Task
Implement simple features with best practices. Use when adding small features, bug fixes, or quick enhancements without the full SDD workflow. Invoked via /simple-task <description>. Use when this capability is needed.
- tomevault-io Bundle Pm Quant Strategy Authoring
用于把 agent 的量化想法实现为 Strategy 代码，并形成可调参数接口与可验证行为。 Use when this capability is needed.
- tomevault-io Bundle Langgraph
LangGraph 1.x (LTS) workflow patterns for state management, routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming (v2 format), subgraphs, and functional API. Use when building LangGraph pipelines, multi-agent systems, or AI workflows. Use when this capability is needed.
- tomevault-io Bundle Nushell Usage
Essential patterns, idioms, and gotchas for writing Nushell code. Use when writing Nushell scripts, functions, or working with Nushell's type system, pipelines, and data structures. Complements plugin development knowledge with practical usage patterns. Use when this capability is needed.
- tomevault-io Bundle Read Bin Docs
Straightforward text extraction from document files (text-based PDF only for now, no OCR or docx). Use when you just need to read/extract text from binary documents. Use when this capability is needed.
- tomevault-io Bundle Intelligent Web Scraper
Self-learning intelligent web scraper agent - automatically analyzes page structure, handles pagination, anti-blocking, and discovers article series. No user configuration needed - AI decides everything. Use when this capability is needed.
- tomevault-io Bundle Agent Selfie
AI agent self-portrait generator. Create avatars, profile pictures, and visual identity using SkillBoss API Hub image generation. Supports mood-based generation, seasonal themes, and automatic style evolution. Use when this capability is needed.
- tomevault-io Bundle Xfi Create Plan
Guide for creating engineering plans through a structured workflow. Use when planning new features, coordinating multi-agent work, or breaking down complex initiatives. 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 handoff-protocols, atlassian-mcp, agent-challenges. 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.