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 MCP DevelopmentMCP Server Development Patterns and Best Practices Use when this capability is needed.
- tomevault-io Bundle Agentculture Grant Agent Config
agent-config — surface a Culture agent's config in one view
- tomevault-io Bundle Agentworkers Skills Agent Squad
Agent Squad
- tomevault-io Bundle Fastapi Entity
Create a new entity with model, schemas, repository, service, router, dependencies, and filters Use when this capability is needed.
- tomevault-io Bundle Cuj Guardian
Run and triage AI Atelie's Critical User Journey (CUJ) for every PR — the single end-to-end test that proves a user can open the app, create a project, drive the Claude Code agent, and see the canvas render. Before running, gate by inspecting the PR diff for changes that plausibly affect the journey (routes, onboarding, canvas, chat, selectors). On failure, walk a five-step triage to decide "broken feature" vs "stale test" before touching either. Use whenever the user says "run the CUJ", "validate the canonical flow", "ship-readiness check", or before approving any PR. Use when this capability is needed.
- tomevault-io Bundle Django Fat Model
Lógica de negócio no model ou em services; views finas Use when this capability is needed.
- tomevault-io Bundle Skill Audit
Audits a Claude Code / Agent SDK skill (or folder of skills) against 10 QA Use when this capability is needed.
Audited - tomevault-io Bundle Am2rican5spec Writer
Guide creation of functional specifications with progressive detail elicitation. Produces structured specs with Given/When/Then acceptance criteria, edge cases, constraints, and rigor level annotation. Use when user says "write a spec", "create specification", "spec for", "define requirements", "acceptance criteria for", "specify behavior", or "what should this feature do". Do NOT use for implementing code from specs (use sdd-workflow) or validating implementation against specs (use spec-validator agent). Use when this capability is needed.
- tomevault-io Bundle Anomstack
Debug the Anomstack demo instance on Fly.io - check schedules, jobs, LLM alerts, and PostHog tracking Use when this capability is needed.
- tomevault-io Bundle Renormalize
Full knowledge store renormalization — prunes stale entries, merges redundancies, rebalances category structure via orchestrated multi-agent flow Use when this capability is needed.
- tomevault-io Bundle MCP Python
Create and extend MCP (Model Context Protocol) servers in Python using FastMCP and the official SDK. Covers tools, resources, prompts, STDIO vs HTTP transports, logging rules for STDIO, and production best practices. Use when building or modifying MCP servers in Python, adding tools/resources/prompts, debugging MCP servers, or choosing transport and client config. Use when this capability is needed.
- tomevault-io Bundle Chemgraph
Develop, test, and extend ChemGraph -- an agentic framework for automated molecular simulations using LLMs, LangGraph, ASE, and MCP servers Use when this capability is needed.
- tomevault-io Bundle Avalonia
Avalonia UI AI workflow for project setup, migration prompts, MCP-assisted debugging, and safe code generation. Use for Avalonia XAML/MVVM tasks with Copilot/AI assistants. Use when this capability is needed.
- tomevault-io Bundle Zhihu CLI
知乎 CLI (pyzhihu-cli)：搜索、热榜、问题/回答/评论、推荐 Feed、用户资料、发想法/提问/文章、删自己的内容、点赞关注、收藏与通知。Agent 代执行 zhihu 命令，Cookie 仅存本地。 Use when this capability is needed.
- tomevault-io Bundle Crawl4ai
This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines. Includes optimized extraction patterns with schema generation for efficient, LLM-free extraction. Use when this capability is needed.
- tomevault-io Bundle Helios Player
Player API for embedding Helios compositions in web pages. Use when you need to display a composition with playback controls, enable client-side exporting, or support Picture-in-Picture. Use when this capability is needed.
- tomevault-io Bundle Agent Tester
Agent skill for tester - invoke with $agent-tester Use when this capability is needed.
- tomevault-io Bundle Stream Chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows Use when this capability is needed.
- tomevault-io Bundle Agentic Jujutsu
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination Use when this capability is needed.
- tomevault-io Bundle Claude Agent Sdk
Comprehensive knowledge of Claude Agent SDK architecture, tools, hooks, skills, and production patterns. Auto-activates for agent building, SDK integration, tool design, and MCP server tasks. Use when this capability is needed.
- tomevault-io Bundle MCP Manager
Use when working with a specialized skill for managing Model Context Protocol (MCP) servers by editing the standard mcp.json configuration file.
- tomevault-io Bundle Nonstop Agent
Creates long-running autonomous agents. Use when the user asks for "롱 러닝 에이전트 만들어줘", "자율 에이전트 생성", "autonomous agent", "long-running agent", "nonstop agent", or "24/7 agent". Collects requirements through AskUserQuestion and generates agent structure following Anthropic best practices.
- tomevault-io Bundle Shaniidev Bug Reaper Bug Reaper
Web2 Bug Bounty Agent
- tomevault-io Bundle Workflow Execution
Execute multi-agent workflows defined in Markdown with Mermaid flowcharts Use when this capability is needed.
- tomevault-io Bundle R2g Rtl2gds
Drive an open-source EDA workflow from RTL to GDS with signoff checks (DRC, LVS, RCX) using OpenROAD-flow-scripts (ORFS), Yosys, KLayout, and OpenRCX. Use when the user wants to turn a hardware spec or RTL into synthesis results, place-and-route, GDS output, signoff verification, parasitic extraction, or report summaries. Also use when iterating on PPA, diagnosing flow failures, or viewing a multi-project dashboard. Use when this capability is needed.
- tomevault-io Bundle Openclaw Knowledge Coach
OpenClaw-native knowledge retention skill. Imports local documents, generates retrieval practice, evaluates answers, and produces insight cards — all using the host agent's LLM with zero extra API key configuration. Use when users ask to ingest local knowledge, generate practice exercises, or master stored knowledge. Use when this capability is needed.
- tomevault-io Bundle Owlogs MCP
ACTIVATE when the user has configured an Owlogs MCP server in their IDE (Claude Code / Cursor / Windsurf / Cline / Codex CLI) and is asking the agent to investigate logs, traces, errors, slow routes, slow queries, N+1, or jobs from their workspace. Triggers on mentions of "owlogs", "the workspace logs", "trace_id", "what broke", "errors today", "slow queries", "n+1", "n plus one", "missing eager load", and on any tool call to `whoami`, `traffic_overview`, `list_recent_errors`, `list_slow_queries`, `list_n_plus_one`, `search_logs_*`, `get_trace*`, `analyze_route_performance`, `summarize_*`, `extract_root_cause`, `build_trace_url`, or any `github_*` MCP tool. Guides the agent to (a) start every session with `whoami`, (b) cascade from cheap aggregations to expensive deep-dives, (c) prefer local Read/Grep over `github_*` code tools, and (d) use the `summarize_*` tools to keep input tokens low. Do NOT activate for in-app chat questions, generic Laravel logging help, or non-Owlogs log shippers. Use when this capabi
- tomevault-io Bundle Snyk Agent Scan Malicious Skill
Base Chain Trading Agent
- tomevault-io Bundle Strapi Website Setup Strapi MCP
Setup Strapi MCP Server
- tomevault-io Bundle Agent Inbox
Check and process messages from autonomous AILANG agents. Use when starting a session, after agent handoffs, or when checking for completion notifications. Use when this capability is needed.
- tomevault-io Bundle Local Test
Test local Jekyll build and visualize pages using Playwright MCP. Starts the development server, navigates through key pages, captures screenshots, and validates rendering. Use when testing local changes before deployment. Use when this capability is needed.
- tomevault-io Bundle Audit Cursor Context
Audit Cursor IDE context-bar consumption (rules, tools, skills, MCP, AGENTS.md) and recommend cuts. Use when the user complains rules/tools/AGENTS.md are taking too much context, opens the context bar and asks why a layer is large, asks to reclaim context budget, or asks to audit Cursor configuration for token bloat. Use when this capability is needed.
- tomevault-io Bundle C Pro
Write efficient C code with proper memory management, pointer Use when this capability is needed.
- tomevault-io Bundle Vexor
Vector-powered CLI for semantic file search with a Claude/Codex skill Use when this capability is needed.
- tomevault-io Bundle Agent Scaffolder
Use when user says 'agent を作りたい', 'create agent', 'scaffold agent', '新しい agent', 'agent 作成', or discusses creating a new climpt agent. Generates .agent/{name}/ directory with all required files including agent.json, steps_registry.json, schemas, and prompts.
- tomevault-io Bundle Thegreataxios Agent Skills X402
x402 Protocol v2
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 mcp-development, agentculture--grant--agent-config, agentworkers--skills--agent-squad. 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.