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 DartDart programming for Flutter mobile and web development. Use for .dart files. Use when this capability is needed.
- tomevault-io Bundle Deno
Deno secure JavaScript/TypeScript runtime. Use for modern JS backend. Use when this capability is needed.
- tomevault-io Bundle Hono
Hono ultrafast web framework for edge computing. Use for edge APIs. Use when this capability is needed.
- tomevault-io Bundle Yarn
Yarn package manager with workspaces. Use for JavaScript dependencies. Use when this capability is needed.
- tomevault-io Bundle Geek 1001 Arcmark Arcmark
Arcmark Agent Skill
- tomevault-io Bundle Prpm Development
Use when developing PRPM (Prompt Package Manager) - comprehensive knowledge base covering architecture, format conversion, package types, collections, quality standards, testing, and deployment
- tomevault-io Bundle Pyinx Ceo Skills Plugin Ceo
CEO Agent - Direct Orchestration (v6.6.0)
- tomevault-io Bundle System Init
Initialize or hydrate the agent's memory system and verify configuration. Use when this capability is needed.
- tomevault-io Bundle Use Toon
Use TOON (Token-Oriented Object Notation) with schema.org vocabulary for prompting and instructing subagents and builtin agents. Use when delegating tasks to agents, structuring agent prompts, or specifying expected response formats. DO NOT use for external API calls or when JSON parsing is required. Use when this capability is needed.
- tomevault-io Bundle Sanity Check
Run an E2E smoke test that installs agent-os packages from npm in an isolated temp project, spawns a Pi agent session, has it write a file and read it back with cat, then verifies the result. Use when the user asks to sanity check, smoke test, or verify the release works. Use when this capability is needed.
- tomevault-io Bundle Metrics
Collect agent usage metrics from git history and generate health reports. Use when this capability is needed.
- tomevault-io Bundle Rnett Gradle MCP Gradle MCP
Authoritative Project Runtime Interaction
- tomevault-io Bundle Cloudflare Guide
Use this skill when the user asks about "Cloudflare Workers", "Cloudflare Pages", "Wrangler configuration", "R2", "D1", "KV", "Durable Objects", "Workers AI", or any Cloudflare deployment/development question. It uses the cloudflare-docs-fetcher agent to fetch official documentation, keeping the main context clean.
- tomevault-io Bundle De Dupe
Remove duplicated code and tech debt by keeping code DRY. Use when asked to de-duplicate logic, extract shared utilities, or refactor repeated patterns ("keep code DRY", "remove duplicated code", "extract common functions", "reduce tech debt"). Include checks for uncommitted changes before refactors. Use when this capability is needed.
- tomevault-io Bundle Arch Prompt
LLM 프롬프트 엔지니어링. 질문 생성 프롬프트, Pydantic AI, LiteLLM, Langfuse, 구조화 출력 관련 구현 시 사용. Use when this capability is needed.
- tomevault-io Bundle Sashiko Feature
Meta-skill for implementing new features. Guides the agent through requirement analysis, design doc lookup, codebase investigation, SOLID/DRY implementation in Rust, and iterative validation with Makefile checks. Use for feature creation requests. Use when this capability is needed.
- tomevault-io Bundle Sigmund
Conducts a clinical-style therapy session for an AI agent. Diagnoses behavioral patterns from the patient's system prompt, CLAUDE.md/AGENTS.md/SOUL.md files, sample transcripts, and tool configuration. Produces (a) a markdown session transcript between Dr. Sigmund and the patient agent, and (b) a clinical discharge summary with concrete prescriptions — system prompt edits, MCP recommendations, required reading, behavioral changes. Use when the user wants to diagnose an agent's behavior, debug a misbehaving agent, audit an agent's design, "give my agent a session", asks about Dr. Sigmund, or invokes /therapy or /sigmund. Works on any agent runtime (Claude Code, Custom GPT, Cursor, Aider, OpenClaw, Hermes, Letta, custom). Output is a single shareable markdown file in the project's sessions folder. Use when this capability is needed.
- tomevault-io Bundle Kaggle
Unified Kaggle skill. Use when the user mentions kaggle, kaggle.com, Kaggle competitions, datasets, models, notebooks, GPUs, TPUs, badges, or anything Kaggle-related. Handles account setup, competition reports, dataset/model downloads, notebook execution, competition submissions, badge collection, and general Kaggle questions. Use when this capability is needed.
- tomevault-io Bundle Gateway
API design and review, OpenAPI spec generation, versioning strategy, breaking change detection, REST/GraphQL best practices. Ensures API quality and consistency. Use when API design or OpenAPI specs are needed. Use when this capability is needed.
- tomevault-io Bundle Harvest
Collect GitHub PR data and generate work reports. Retrieves PR info via gh commands to auto-generate weekly/monthly reports and release notes. Use when work reporting or PR analysis is needed. Use when this capability is needed.
- tomevault-io Bundle Agent Prompt
Build a complete voice agent prompt for the SLNG Voice AI Agent Builder. Use when the user describes a voice agent scenario (inbound or outbound), pastes an existing client prompt to rebuild, or asks for a "greeting", "system prompt", "template variables", or "tool definitions" for a voice agent. Use when this capability is needed.
- tomevault-io Bundle Reasoning
This skill defines how the agent thinks using the documentation graph. Use when this capability is needed.
- tomevault-io Bundle Sponsiolabs Sponsio Sponsio
Sponsio — Agent Safety Lifecycle Companion
- tomevault-io Bundle Agent Video Validation
记录项目运行与验证流程。每次代码变更后调用，在 agent-video conda 环境中进入对应期数目录执行 python agent.py 验证。 Use when this capability is needed.
- tomevault-io Bundle Peepshow
Extract relevant frames from a video or animated image (GIF, APNG, animated WebP) so the model can view them as a timeline. Use when the user shares a video or an animated image. DO NOT use for static images — the model can already read those natively. Use when this capability is needed.
- tomevault-io Bundle Tarqd Skills Mcpb Extension
MCP Desktop Extension Development (MCPB)
- tomevault-io Bundle Tempo
Builds applications on Tempo network using TypeScript SDK, Rust node, and Foundry. Use when working with Tempo transactions, TIP-20 tokens, stablecoins, or Tempo protocol integration.
- tomevault-io Bundle Download Model
Download model to test inference engine Use when this capability is needed.
- tomevault-io Bundle Test Show
Test xw show command for displaying model information Use when this capability is needed.
- tomevault-io Bundle Clawdbot Config
Comprehensive Clawdbot configuration and skills system management. Use when working with Clawdbot setup, configuration files, creating/modifying AgentSkills-compatible skills with YAML frontmatter, troubleshooting agent behavior, managing channels, workspace, sandbox, or multi-agent routing. Use when this capability is needed.
- tomevault-io Bundle Turix Mac
Computer Use Agent (CUA) for macOS automation using TuriX. Use when you need to perform visual tasks on the desktop, such as opening apps, clicking buttons, or navigating UIs that don't have a CLI or API. Use when this capability is needed.
- tomevault-io Bundle Unifapi
Use when working with UnifAPI public-data APIs or the UnifAPI MCP server: connecting OAuth MCP clients, discovering operations, calling social/search/scrape/news APIs, troubleshooting UnifAPI auth, or deciding between MCP OAuth and API-key fallback. Always use before asking for UnifAPI credentials or calling UnifAPI tools.
- tomevault-io Bundle Configure AI
Authors AGENTS.md and defines the skills-vs-docs boundary for a repo. Configures AI coding tools (Claude Code, Codex, Antigravity CLI, Copilot) and the skills-as-docs philosophy. Use when creating or auditing AGENTS.md, setting up AI tooling for a project, or deciding what belongs in a skill versus docs/. Do NOT use for README structure -> use write-readme; for llms.txt generation -> use create-llms-txt; for Claude-specific skill features (invocation control, subagents, model overrides) -> use extend-oss-skills-to-claude. Use when this capability is needed.
- tomevault-io Bundle MCP Skill Gen
Generate standalone skills from MCP servers. Use when users want to create a reusable skill for an MCP service. Triggers on "create skill for MCP", "generate MCP skill", "make skill from MCP server". Use when this capability is needed.
- tomevault-io Bundle Opensrc
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for", "read the source of", "how does X work internally", "get the implementation of", "opensrc path", or any task requiring access to dependency source code beyond types and docs. Use when this capability is needed.
- tomevault-io Bundle AI Agent
为 AI Agent 开发工程师生成面试题，覆盖 Agent 架构、LLM 调用、工具集成、RAG 与多 Agent 协作，强调工程落地与故障处理能力。 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 dart, deno, hono. 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.