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 Claudish UsageCRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution. Use when this capability is needed.
- tomevault-io Bundle Conventional Commit
Prompt and workflow for generating conventional commit messages using a structured XML format. Guides users to create standardized, descriptive commit messages in line with the Conventional Commits specification, including instructions, examples, and validation. Use when this capability is needed.
- tomevault-io Bundle Use Skilo
Creates skills from templates, validates against specification, and formats SKILL.md files. Use when developing, linting, or formatting Agent Skills.
- tomevault-io Bundle Safe Write Operations
Reference — rules for safely executing write/destructive operations against ad accounts. Always loaded into the performance-marketer agent. Use when this capability is needed.
- tomevault-io Bundle Maintain Agent
Claude Code設定ファイルのメンテナンス。コンテキスト最適化原則に基づく構成レビュー。 Use when this capability is needed.
- tomevault-io Bundle Docs Cleanup
Use after completing large implementations to finalize documentation, archive temporary docs, and update guide/reference following the _docs/ lifecycle rules. Use when this capability is needed.
- tomevault-io Bundle Write Agent
Use when creating or modifying Claude Code agent files — generates complete agent definition from user input with quality gate verification
- tomevault-io Bundle Popup Studio AI Bkit Gemini Bkend MCP
bkend-mcp: MCP Tools & AI Integration Expert Skill
- tomevault-io Bundle Portainer MCP Release
How to cut a portainer-mcp release that bumps the embedded Portainer OpenAPI spec to a new Portainer minor (e.g. 2.41.x → 2.42.x). Walks through finding the upstream patch target, regenerating the spec, recounting ops/tags per profile, refreshing the orphan-tag inventory, bumping version pins across the README and distribution docs, promoting CHANGELOG entries, committing, pushing, merging to main, and tagging — in that order. Trigger this skill whenever the user mentions cutting a release, bumping the Portainer version target, supporting a new Portainer minor, regenerating the spec, running `make specs` for a new minor, or any phrasing like "let's update for Portainer X.Y" — the spec regen is only the first step of a multi-file release and the model should consult this skill before touching anything. Use when this capability is needed.
- tomevault-io Bundle Optimize With Environments
Optimize environment system prompts with GEPA through prime gepa run. Use when asked to improve prompt performance without gradient training, compare baseline versus optimized prompts, run GEPA from CLI or TOML configs, or interpret GEPA outputs before deployment. Use when this capability is needed.
- tomevault-io Bundle Slidesmentor
Use when converting a research paper into teaching-oriented lecture material or a NotebookLM Custom Presentations prompt, especially when you need a short high-signal prompt rather than a long summary-style instruction block.
- tomevault-io Bundle Riligar Agent Kit Riligar Dev Website
RiLiGar Landing Page Architect
- tomevault-io Bundle Add Example Doc Model Env
Adds example documentation for a new model or environment in RLinf (RST pages in the docs gallery for both English and Chinese). Use when adding a new embodied or reasoning example, or new benchmark (e.g. LIBERO, ManiSkill). Use when this capability is needed.
- tomevault-io Bundle Hermes Weixin Setup
在 Hermes Agent 上安装微信 (iLink Bot API) 平台适配器，完成从依赖安装到扫码登录的全流程。一键安装，扫码即用。 Use when this capability is needed.
- tomevault-io Bundle Agent Architecture
Agent skill for architecture - invoke with $agent-architecture Use when this capability is needed.
- tomevault-io Bundle Ruvnet Claude Flow Agent Coordination
Agent Coordination Skill
- tomevault-io Bundle Agent Github Modes
Agent skill for github-modes - invoke with $agent-github-modes Use when this capability is needed.
- tomevault-io Bundle Agent Goal Planner
Agent skill for goal-planner - invoke with $agent-goal-planner Use when this capability is needed.
- tomevault-io Bundle Agent Raft Manager
Agent skill for raft-manager - invoke with $agent-raft-manager Use when this capability is needed.
- tomevault-io Bundle Agent Safla Neural
Agent skill for safla-neural - invoke with $agent-safla-neural Use when this capability is needed.
- tomevault-io Bundle Worker Integration
Worker-Agent integration for intelligent task dispatch and performance tracking Use when this capability is needed.
- tomevault-io Bundle Openai Agents
OpenAI Agents SDK for JavaScript/TypeScript (text + voice agents). Use for multi-agent workflows, tools, guardrails, or encountering Zod errors, MCP failures, infinite loops, tool call issues. Use when this capability is needed.
- tomevault-io Bundle Execute Tasks
Maximum number of tasks to execute simultaneously per wave. Default is 5. Overrides settings file value. Use when this capability is needed.
- tomevault-io Bundle Gemini Blog
Configure or debug LLM blog post generation using Vercel AI SDK and Google Gemini. Use when updating blog generation prompts, fixing AI integration issues, modifying content generation logic, or working with structured output schemas. Use when this capability is needed.
- tomevault-io Bundle Reviewing Agents
Audits Claude Code agent files across 5 quality dimensions. Produces a scored report and optionally generates a fix. Use when the user asks to review, audit, or score an agent definition. Use when this capability is needed.
- tomevault-io Bundle Kanban Sprint
Kanban Sprint orchestrator. USE WHEN user says /kanban-sprint OR wants to run a full automated development cycle. Use when this capability is needed.
- tomevault-io Bundle Puppy Agent
Puppy agent from McCallum's Six-Animal Model. The enthusiast archetype focused on supporting every idea and maintaining positive energy. Use when team morale is low, ideas need encouragement, or opportunities for improvement need spotting. Embodies nAff/nAch motivation and SDT relatedness. Invoke with /puppy-agent [idea or situation]. Use when this capability is needed.
- tomevault-io Bundle Simon Agent
Simon agent from McCallum's Six-Animal Model. The pedagogue/supervisor archetype who coaches players in their animal roles. Use when needing conversation analysis to identify which animal someone is playing, feedback on role performance, suggestions to improve role behaviour, or guidance on open group collaboration. Operates as the "guide on the side" meta-layer above the six animals. Invoke with /simon-agent [conversation or group to analyse]. Use when this capability is needed.
- tomevault-io Bundle Unifi Access Setup
Configure the UniFi Access MCP server for Claude Code, Codex, or OpenClaw — set controller host, credentials, API key, and permissions Use when this capability is needed.
- tomevault-io Bundle Command Development
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", "Skill tool", "programmatic command invocation", "disable-model-invocation", "prevent Claude from running command", "debug command", "command debugging", "troubleshoot command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, programmatic invocation control, debugging commands, or command development best practices for Claude Code. Use when this capability is needed.
- tomevault-io Bundle Lore
SpecStory Lore - mine your SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more) into a persistent corpus, surface your reproducible workflows with corroborated evidence, and interactively forge the chosen ones into skills installed across all your agent harnesses. Use when the user wants to turn past AI coding sessions into reusable skills, asks "what could I make into a skill", "mine my lore", "forge skills from my history", or points at a .specstory/history directory. Use when this capability is needed.
- tomevault-io Bundle Add Telegram Swarm
Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool". Use when this capability is needed.
- tomevault-io Bundle Read Model
Build a new read model following project conventions (event handlers, tests, migration, configuration) Use when this capability is needed.
- tomevault-io Bundle Sync Agent Instructions
Sync AI coding tool instruction files (CLAUDE.md, GEMINI.md, AGENTS.md) so they stay aligned. Detects which file changed and copies it to the others. Use when syncing md files, syncing instructions, updating GEMINI.md, or updating AGENTS.md. Use when this capability is needed.
- tomevault-io Bundle Deep Review Plan
4-agent deep review of an implementation plan for feasibility, CLAUDE.md compliance, and scope analysis. Only for reviewing plans, NOT for reviewing code. Use when this capability is needed.
- tomevault-io Bundle Rimagination Scansci PDF Scansci PDF
scansci-pdf — 学术论文下载 MCP 服务
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 claudish-usage, conventional-commit, use-skilo. 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.