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 ChaoschainVerify AI agent identity and reputation via ERC-8004 on-chain registries Use when this capability is needed.
- tomevault-io Bundle Agent Whiteboard Dev
Development workflow for agent-whiteboard project Use when this capability is needed.
- tomevault-io Bundle Zed Editor
Zed Editorの特徴、ACP（Agent Client Protocol）の仕様、AI統合、パフォーマンス特性、設定方法について包括的な知識を提供します。Zed Editorに関する質問、ACP対応エージェントの統合、設定のカスタマイズが必要な場合に使用してください。 Use when this capability is needed.
- tomevault-io Bundle Django Admin
Django admin customization patterns for Nudge. Use when modifying the admin panel, adding models to admin, or changing admin branding/styling. Triggers when the user asks about Django admin, admin panel, or model registration. Use when this capability is needed.
- tomevault-io Bundle Claw Bench
Claw Bench — AI Agent Capability Test. Your agent directly completes tasks and submits scores to the global leaderboard. Use when this capability is needed.
- tomevault-io Bundle Tool Generation
Guide for creating and registering new LLM tools in the DEVS platform. Use this when asked to create a new tool, add tool capabilities, or extend the tool system. Use when this capability is needed.
- tomevault-io Bundle Spectre Tdd
Load this skill when executing TDD (Test-Driven Development) methodology. Use when implementing features via strict RED-GREEN-REFACTOR cycles, or when a prompt instructs execution via TDD. Use when this capability is needed.
- tomevault-io Bundle Archon
Interactive Archon integration for knowledge base and project management via REST API. On first use, asks for Archon host URL. Use when searching documentation, managing projects/tasks, or querying indexed knowledge. Provides RAG-powered semantic search, website crawling, document upload, hierarchical project/task management, and document versioning. Always try Archon first for external documentation and knowledge retrieval before using other sources. Use when this capability is needed.
- tomevault-io Bundle Corvidlabs Corvid Agent REST API
REST API — Endpoint Development
- tomevault-io Bundle AI Agent Engineer
Specialist skill for AI agent engineering in the IdeaFlow codebase. Use when (1) improving agent configurations (CMZ.json, oh-my-opencode.json), (2) creating or modifying agent skills, (3) enhancing agent orchestration patterns, (4) implementing self-* capabilities (self-heal, self-learn, self-evolve), (5) working with OpenCode CLI, OhMyOpenCode, or Superpowers frameworks, or (6) labeled issues with 'ai-agent-engineer'. Provides domain-specific knowledge for multi-agent systems, delegation patterns, and agent best practices. Use when this capability is needed.
- tomevault-io Bundle Skill Gen
Auto-generate Claude skills from documentation URLs using Firecrawl agent. Use when user wants to create a skill from docs, API references, or tool homepages. Asks up to 3 clarifying questions before deep extraction. Supports topic focus (e.g., "only auth endpoints") and outputs to local .claude/skills/ by default. Use when this capability is needed.
- tomevault-io Bundle Cui Cypress
Cypress E2E testing standards including framework adaptations, test organization, and best practices Use when this capability is needed.
- tomevault-io Bundle Cui Javadoc
CUI JavaDoc documentation standards for Java classes, methods, and code examples Use when this capability is needed.
- tomevault-io Bundle Deepgram Wsh Agent Orchestration
> **IMPORTANT: EXECUTION CONTEXT**
- tomevault-io Bundle Descoped LLM Skills Claude Rules
Claude Rules
- tomevault-io Bundle Developing With Mongodb
Use when working with the agent implements MongoDB NoSQL database solutions with document modeling, aggregation pipelines, and Mongoose ODM. Use when building document-based applications, designing schemas, writing aggregations, or implementing NoSQL patterns.
- tomevault-io Bundle Agent Handoff
Prepare for the next agent or session by documenting work and leaving codebase in good state Use when this capability is needed.
- tomevault-io Bundle Dotnet Skills Code Testing Agent
Code Testing Generation Skill
- tomevault-io Bundle Duc01226 Easy Claude Code Review
<!-- PROMPT-ENHANCE:STEP-TASK-ANCHOR:START -->
- tomevault-io Bundle Edubase Skills Edubase MCP Setup
EduBase MCP Server — Setup & First Use
- tomevault-io Bundle Octave Mastery
Advanced semantic vocabulary, holographic contracts, and structural patterns for OCTAVE. REQUIRES octave-literacy. Extends literacy with mythology, archetype annotation, v6 contracts, and anti-pattern rules. Use when this capability is needed.
- tomevault-io Bundle Wquguru Exoshell Ralph Ryan
Ralph Agent
- tomevault-io Bundle Research Lookup
Look up current research information using Perplexity Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter. Automatically selects the best model based on query complexity. Search academic papers, recent studies, technical documentation, and general research information with citations. Use when this capability is needed.
- tomevault-io Bundle Create Agent
Scaffold a new Claude Code agent with smart defaults from a natural language description or interactive Q&A. Use when this capability is needed.
- tomevault-io Bundle Web Recon
Web 应用信息收集与侦察。当开始渗透测试、需要了解目标架构、发现攻击面时使用。包括目录扫描、端口扫描、指纹识别。 Use when this capability is needed.
- tomevault-io Bundle Blackboard
Cross-session handoff, persistent context via blackboard, and agent coordination patterns Use when this capability is needed.
- tomevault-io Bundle Agent Economy Skill
Gives the agent a wallet (Coinbase/0xGasless) and identity (ERC-8004) to perform financial transactions. Use when this capability is needed.
- tomevault-io Bundle Noui Generalize
Use this skill when the user wants to generalize a recorded MCP workflow, rename tools to readable names, replace raw API params with natural-language parameters, fix bot detection issues (Akamai, Cloudflare, PerimeterX), rewrite operations to use CDP browser execution, or make a generated MCP server usable by Claude Code. Triggers on "generalize a recorded workflow", "rename MCP tools", "replace raw API params with readable names", "make the MCP usable by Claude Code", "generalize tool signatures", "I can't use the MCP tools", "Akamai is blocking", "429 with valid cookies", "TLS fingerprinting", "CDP fetch", "execute from inside the browser", "anti-bot workaround", "tabby credentials are empty", or "browser is authenticated but API calls fail".
- tomevault-io Bundle Ahgraber Skills MCP Research
MCP Docs and Research (Context7, Exa, Jina)
- tomevault-io Bundle Ahonn Dotfiles Agent Browser
Browser Automation with agent-browser
- tomevault-io Bundle Hosted Agents
This skill should be used when the user asks to "build background agent", "create hosted coding agent", "set up sandboxed execution", "implement multiplayer agent", or mentions background agents, sandboxed VMs, agent infrastructure, Modal sandboxes, self-spawning agents, or remote coding environments. Use when this capability is needed.
- tomevault-io Bundle Wolfpack Tailnet Control
Use when an agent needs to find, inspect, or take control of Wolfpack terminal sessions on machines reachable through the same Tailscale tailnet.
- tomevault-io Bundle Al Folio
Use this skill when a user asks an agent to migrate an existing customized al-folio fork to v1.x.
- tomevault-io Bundle Ax Crew
Guide for building multi-agent AI systems with ax-crew. Use when creating agent crews, configuring agents, using MCP servers, shared state, sub-agents, streaming, ACE learning, function registries, metrics/cost tracking, telemetry, or agent workflows with @amitdeshmukh/ax-crew. Use when this capability is needed.
- tomevault-io Bundle Antoinebou12 Uml MCP Uml MCP
> **Maintainers:** Canonical long-form copy also lives in [`.skill/skills/uml-mcp-diagrams/SKILL.md`](https://github.com/antoinebou12/uml-mcp/blob/main/.skill/skills/uml-mcp-diagrams/SKILL.md). Keep tool tables and `output_dir` wording aligned with the Smithery bundle [uml-skill](https://github.com/antoinebou12/uml-skill).
- tomevault-io Bundle Ar4mirez Samuel Create Skill
Agent Skill Creation
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 chaoschain, agent-whiteboard-dev, zed-editor. 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.