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 Nvidia Nemo Nemotron NemotronNemotron-3 Ultra Text2SQL LoRA — runbook for a coding agent
- tomevault-io Bundle Explore Agents
Browse, understand, and run your saved Octave agents. Use when user says "show my agents", "list agents", "run an agent", "which agents do I have", or asks about saved agent configurations. Use when this capability is needed.
- tomevault-io Bundle Ogham MCP Ogham MCP Ogham MCP
Ogham research capture
- tomevault-io Bundle Okx Sentiment Tracker
Use this skill when the user asks about: 'any crypto news', 'latest news', 'market update', 'daily briefing', 'BTC news', 'ETH news', 'news on SOL', 'search SEC ETF', 'regulation news', 'Bitcoin halving', 'is BTC bullish or bearish', 'coin sentiment', 'sentiment trend', 'trending coins', 'top bullish coins', 'bearish sentiment', 'social buzz', 'market mood', 'fear and greed', 'full article', 'read more', 'economic calendar', '经济日历', 'macro data', '宏观数据', 'NFP', 'nonfarm', '非农', 'CPI', 'GDP', 'FOMC', '利率决议', 'interest rate decision', 'PMI', 'unemployment rate', '失业率', 'economic events', '经济事件', or any request for crypto news, market intelligence, sentiment analysis, social trend data, or macro-economic calendar. Requires API credentials. Do NOT use for market prices/candles (okx-cex-market), placing orders (okx-cex-trade), or account info (okx-cex-portfolio).
- tomevault-io Bundle Validate Agent
Validate agent definitions for consistency, model availability, handoff integrity, and tool existence. Use this when creating or modifying agents. Use when this capability is needed.
- tomevault-io Bundle View Pr Github
View GitHub PR status/details using GitHub MCP tools (preferred) or gh CLI (fallback). Use when this capability is needed.
- tomevault-io Bundle Tmf MCP Builder
Build TM Forum (TMF) MCP servers from TMF OpenAPI specs (TMF6xx/7xx YAML). Use when you are given a TMF OpenAPI file and asked to (1) implement an MCP server exposing TMF operations as tools, (2) generate a mock TMF API server + client + MCP layer, or (3) standardize tool naming, create/update inputs, $ref/allOf handling, and /hub event-subscription patterns for TMF APIs. Use when this capability is needed.
- tomevault-io Skill Erc8004 Agent
Validates that the keyring proxy is working correctly (7 tests).
Audited - tomevault-io Bundle Evolution Engine
Agent 自进化引擎 (v1.0)。整合知识收割、工作流优化、模式检测、反思引擎四大模块，赋予 Agent 自我学习和持续改进能力。 Use when this capability is needed.
- tomevault-io Bundle Jules CLI
Interface with the Google Jules CLI to delegate asynchronous coding tasks. Use this tool to execute a specific plan, start a background session, or retrieve results from a remote Jules agent. Use when this capability is needed.
- tomevault-io Bundle Chitti MCP
Use this skill when you need to start or call Chitti's MCP server (chitti.decide/recall/policy/audit) from Codex, keeping tool details out of context until invoked.
- tomevault-io Bundle 0ctx MCP Bootstrap
Automatically register the 0ctx MCP server in local AI client config files (Claude, Cursor, Windsurf) and verify the registration. Use when users ask to avoid manual MCP config edits, set up MCP on a new machine, or repair broken MCP client integration. Use when this capability is needed.
- tomevault-io Bundle Glasskit
Use when starting, modifying, or debugging apps for Rokid Glasses or similar camera glasses. Covers Rokid setup, on-device display and input patterns, camera/mic/speaker access, touchpad controls, WebRTC streaming, voice controls, real-time LLM/VLM integration, proactive workflow apps, CV object detection, and device-specific best practices.
- tomevault-io Bundle Wrdn Effect Schema Inferred Types
Replace duplicated TypeScript shape declarations next to Effect Schema definitions with schema-derived types. Use when lint or review flags an interface/type alias that repeats fields already described by a nearby Schema.Struct, Schema.Union, Schema.TaggedStruct, or other Effect Schema model. Use when this capability is needed.
- tomevault-io Bundle Update AI Models
Search the web for the latest AI models from Anthropic, OpenAI, and Google, then update src/models.ts with new model IDs. Use when user asks to update or add AI models. Use when this capability is needed.
- tomevault-io Bundle Royisme Agent Skills Ideate Pm
Product Requirements Manager (Repo-scoped)
- tomevault-io Bundle Rubakas Agent Notes Rails Jobs
Jobs Guide
- tomevault-io Bundle Agent Agent
Agent skill for agent - invoke with $agent-agent Use when this capability is needed.
- tomevault-io Bundle Agent Coder
Agent skill for coder - invoke with $agent-coder Use when this capability is needed.
- tomevault-io Bundle Agent Swarm
Agent skill for swarm - invoke with $agent-swarm Use when this capability is needed.
- tomevault-io Bundle Speech To Text
Transcribe audio to text using Sarvam AI's Saaras model. Handles speech recognition, transcription, and voice interfaces for 23 Indian languages. Supports 5 output modes, auto language detection, WebSocket streaming, and batch diarization. Use when converting speech to text or building voice-enabled apps. Use when this capability is needed.
- tomevault-io Bundle Agent Sync
Syncs coding agent config files so AGENTS.md is source of truth and CLAUDE.md/instructions.md are symlinks. Ensures skills and commands are shared across Claude, Codex, Cursor, and opencode. Use when adding skills, commands, or modifying agent config. Use when this capability is needed.
- tomevault-io Bundle Dotstate Development
This skill should be used when working on the DotState project (llm-tui or dotstate repository), "dotstate development", "add a screen to dotstate", "create a dotstate feature", "fix dotstate bug", "dotstate architecture", or any task involving the Rust TUI dotfile manager codebase. Use when this capability is needed.
- tomevault-io Bundle Rk Push
Push local knowledge base to the remote repository. Always fetches remote first, Agent compares diffs and merges (alias LRU merge for _index.md, union dedup for _registry.md, newer-cached-date wins for docs), then commits and pushes. Retries once on push rejection. Use when user says 'push knowledge', 'sync to remote', 'rk-push', or after making local updates. Use when this capability is needed.
- tomevault-io Bundle Argent Test UI Flow
Autonomously test an app UI (iOS or Android) by running interact-screenshot-verify loops using argent MCP tools. Use when testing UI flows, verifying login works, testing navigation, running end-to-end UI test scenarios, manual QA steps, visible UI changes, or visual behavior. Use when this capability is needed.
- tomevault-io Bundle Litho Document Skill
This skill should be used when the user asks to "generate project documentation", "analyze codebase architecture", "create C4 architecture diagrams", "document a repository", "generate technical docs", "使用 Litho 生成文档", "分析代码库架构", "生成架构文档", "为项目生成技术文档", "生成 C4 模型文档", "为这个项目写文档", "自动生成文档", "帮我分析这个代码库", or any request involving automated documentation generation for a software project. This skill enables the AI agent to autonomously analyze any codebase and produce high-quality C4 architecture documentation (Overview, Architecture, Workflow, Deep-Exploration modules, Boundary Interfaces, Database Overview) — equivalent to what deepwiki-rs produces — purely through agent reasoning and tool usage, without depending on any external binary. Use when this capability is needed.
- tomevault-io Bundle Prompt Architect
Use when creating, reviewing, migrating, or refactoring agent prompts, AGENTS.md files, Claude/Cursor/Windsurf rules, Codex skills, standards, instruction hierarchies, MEP prompts, or reusable agent workflows.
- tomevault-io Bundle Skills Overview
Overview of the skills catalog structure and usage for this repository. Use when this capability is needed.
- tomevault-io Bundle Prompt Engineer
Responsible for designing, testing, and optimizing AI prompts and agent instructions. Use when this capability is needed.
- tomevault-io Bundle Telnyx RAG
Semantic search and Q&A over workspace files using Telnyx Storage + AI embeddings. Index your memory, knowledge, and skills for natural language retrieval and AI-powered answers. Use when this capability is needed.
- tomevault-io Bundle Multi Agent
天罗秘典·多Agent协同。融合蚁群仿生设计，定义Agent角色、生命周期、信息素通信、任务分解、冲突解决。当需要多Agent并行协作时路由到此。 Use when this capability is needed.
- tomevault-io Bundle Agents Overview
Use when user asks about 'iterator', 'reviewer', 'autonomous', 'runIterator', 'runReviewer', 'agent architecture', 'agent config', 'agent definition', 'agent runner', 'completion handler', 'steps registry', or discusses completion handlers, prompt system, or agent configuration files like config.json, registry.json, steps_registry.json.
- tomevault-io Bundle Prompt Guidance
Read the entirety of @docs/sora2-prompting-guide.md and await further instruction. Use when this capability is needed.
- tomevault-io Bundle Long Running Jobs
Run shell commands in the background with file-backed output capture and a completion event that wakes the agent when the job exits. Use when a command might take more than ~30 seconds (builds, tests, deployments, agent jobs like acpx/codex exec) and you want to keep working while it runs. Use when this capability is needed.
- tomevault-io Bundle Tophant Clawvault Openclaw Alerts
Push high-risk ClawVault security events and daily security reports through OpenClaw agent messaging Use when this capability is needed.
- tomevault-io Bundle Trulens Instrumentation
Instrument LLM apps with TruLens OTEL-based tracing - from setup to debugging and optimization 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 nvidia-nemo--nemotron--nemotron, explore-agents, ogham-mcp--ogham-mcp--ogham-mcp. 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.