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 Go Sdk MaintainerMaintain and extend the OpenAI Agents Go SDK core packages with safe, tested changes. Use when adding SDK features, fixing bugs in agent/runner/tools/handoff/session packages, updating public API behavior, or preparing production-quality Go code changes. Use when this capability is needed.
- tomevault-io Bundle Mixelpixx Google Search MCP Server Find Docs
---
- tomevault-io Bundle Modbender Skill Library MCP Agent Guardrails
---
- tomevault-io Bundle Modbender Skill Library MCP Coder Workspaces
---
- tomevault-io Bundle Modbender Skill Library MCP System Architect
---
- tomevault-io Bundle Windsurf Cascade
This skill provides a comprehensive guide and set of workflows for utilizing the Windsurf IDE and its Cascade AI agent, including all features from Wave 13 (January 2026). Use when this capability is needed.
- tomevault-io Bundle Replycueai Public
Analyze YouTube video comments for brand relevance using a 5-layer AI scoring model. Identifies purchase intent, product questions, brand risks, competitor mentions, and sentiment — all scoped to YOUR brand context. Use when this capability is needed.
- tomevault-io Bundle Get Schedule Comment Context
Read target remind schedules and recent action_logs (last 3 days) as JSON for agent comment generation. Use when this capability is needed.
- tomevault-io Bundle Hti Zen Orchestrator
Guidelines for using Zen MCP tools effectively in this repo. Use for complex multi-model tasks, architectural decisions, or when cross-model validation adds value. Use when this capability is needed.
- tomevault-io Bundle Mynameistito Create Cf Token Create Cf Token
create-cf-token — Agent Skill
- tomevault-io Bundle Src Hunter
实战 SRC / 众测 / Bug bounty 漏洞挖掘工作流 skill。包含：5 阶段方法论（intake → recon → enum → hunt → report）、19 个攻击类 playbook（SQLi/XSS/RCE/SSRF/IDOR/CSRF/Path Traversal/File Upload/SSTI/XXE/Race/HTTP Smuggling/OAuth/JWT/SAML/GraphQL/Mobile/LLM/DoS）、305 个结构化 payload、263 个 WAF/EDR 绕过变体、2887 份 HackerOne 真实 High/Critical 已披露案例、88,636 份 WooYun 案例统计、国产 OA / 中间件指纹库、银行 / 电信行业垂直 playbook。当用户提到 "src 挖洞 / src 漏洞挖掘 / bug bounty / 众测 / hackerone / 漏洞赏金 / SRC / 任意 X 漏洞 / 渗透测试" 或问"如何挖某个目标 / 怎么测某个 API / 如何绕过 WAF" 时触发。 Use when this capability is needed.
- tomevault-io Bundle Lazy Agent Loader
Load agent definitions on-demand to reduce context usage. Only loads full agent when needed. Use when this capability is needed.
- tomevault-io Bundle Learning Analyzer
Analyze collected learning data from Supabase to identify success patterns, failure patterns, optimization opportunities, and agent performance trends. Use when this capability is needed.
- tomevault-io Bundle Apple Mail Search
Search Apple Mail messages on macOS via direct SQLite queries. Sub-second search across all configured mail accounts without launching Mail.app. Use when this capability is needed.
- tomevault-io Bundle GRAPHQL Schema Designer
Designs GraphQL schemas with types, queries, mutations, subscriptions, and resolvers. Use when building or refactoring a GraphQL API. Use when this capability is needed.
- tomevault-io Bundle Nirholas Bnb Chain Toolkit Bnb Chain Toolkit
SKILL.md — ERC-8004 Agent Creator
- tomevault-io Bundle Nousresearch Hermes Agent Github Code Review
GitHub Code Review
- tomevault-io Bundle Gcal API Research
Expert research tool for Google Calendar API implementations. PROACTIVELY use when (1) reviewing PRs adding calendar features, (2) planning new event/attendee/recurring event functionality, (3) investigating calendar API issues, (4) validating timezone handling or batch operations. Specializes in recurring events, timezone conversions, multi-calendar support, and edge case identification. Use when this capability is needed.
- tomevault-io Bundle Numerai Model Upload
Create Numerai Tournament model upload pickles (.pkl) with a self-contained predict() function. Use when preparing upload artifacts, debugging numerai_predict import errors, or documenting model-upload requirements and testing steps. Use when this capability is needed.
- tomevault-io Bundle Research Artist For Suno
This skill should be used when the user asks to "research an artist", "analyze [artist] style", "study [song]", "look up [artist] patterns", or wants to explore musical patterns before creating a Suno song. Automatically launches song-researcher sub-agent for comprehensive pattern analysis from web sources. Use when this capability is needed.
- tomevault-io Bundle Reviewing AI Papers
Analyze AI/ML technical content (papers, articles, blog posts) and extract actionable insights filtered through enterprise AI engineering lens. Use when user provides URL/document for AI/ML content analysis, asks to "review this paper", or mentions technical content in domains like RAG, embeddings, fine-tuning, prompt engineering, LLM deployment. Use when this capability is needed.
- tomevault-io Bundle Open Agent Tools General Oat Skills Scaffold
Create a new project using the specified template: $ARGUMENTS
- tomevault-io Bundle Changeset Validation
Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes). Use when packages/ or .changeset/ are modified, or when verifying PR changeset compliance and bump level. Use when this capability is needed.
- tomevault-io Bundle Gemini Batch Processor
Automatically suggest and execute Gemini batch processing when user needs to process many files through BAML functions. Use when user mentions processing multiple documents, PDFs, CSVs, or wants cost-effective LLM processing. Use when this capability is needed.
- tomevault-io Bundle Outsourc E Hermes Workspace Hermes Workspace
Workspace Dispatch (Single Agent)
- tomevault-io Bundle Paiml Paiml MCP Agent Toolkit Pmat Tech Debt
PMAT Technical Debt Tracking Skill
- tomevault-io Bundle Agentica Spawn
Spawn Agentica multi-agent patterns Use when this capability is needed.
- tomevault-io Bundle Coding Agent Digest
Collect, filter, and write a concise Chinese daily digest for coding agent news. Use when the user asks for yesterday/today/daily coding agent资讯, Codex/Claude Code/Cursor/Gemini/Antigravity updates, agentic coding news, or a <=10 item digest from official docs, changelogs, releases, core people, starred blogs, Medium, or high-quality communities. Use when this capability is needed.
- tomevault-io Bundle AI Agent Orchestrator
Orchestrates multi-agent AI systems with task delegation, agent communication, shared memory, and workflow coordination. Use when users request "multi-agent system", "agent orchestration", "AI agents", "agent coordination", or "autonomous agents". Use when this capability is needed.
- tomevault-io Bundle AI Engineer Expert
Expert-level AI implementation, deployment, LLM integration, and production AI systems Use when this capability is needed.
- tomevault-io Bundle Pjt222 Agent Almanac Build Custom MCP Server
Build Custom MCP Server
- tomevault-io Bundle Pjt222 Agent Almanac Containerize MCP Server
Containerize MCP Server
- tomevault-io Bundle Pondevelopment LLM Training Theme Compliance
---
- tomevault-io Bundle Upload Deployment
Complete reference for model upload and deployment. Covers HuggingFace upload, save strategies (LoRA, merged 16-bit, merged 4-bit), GGUF conversion, model merging, model cards, and the full upload workflow. Use when uploading models, creating GGUF files, merging LoRA adapters, or deploying to HuggingFace. This skill is about USING the upload/deployment tools via CLI — never modifying source code. Use when this capability is needed.
- tomevault-io Bundle MCP Server Weibo
Use when working with the `weibo-cli` is a command-line interface tool for interacting with Weibo data without using the MCP protocol. It provides direct access to all Weibo functionality through simple terminal commands.
- tomevault-io Bundle Opencode Config Advisor
Detects, analyzes, and suggests changes to the Opencode CLI configuration file (config.json). Use this when the user complains about Opencode performance, asks to change the default model, or wants to modify CLI behavior. 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 go-sdk-maintainer, mixelpixx--google-search-mcp-server--find-docs, modbender--skill-library-mcp--agent-guardrails. 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.