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 Pymc Labs Agent Skills TemplateSkill Title
- tomevault-io Bundle Debate Vs
Claude debates an opponent LLM (Gemini or Codex) through multi-turn MCP conversation, then synthesizes the best approach and implements. Use when this capability is needed.
- tomevault-io Bundle Clawphone
This skill defines how the OpenClaw agent responds when contacted via the Use when this capability is needed.
- tomevault-io Bundle Writing LLM Md
Teaches how to write effective LLM.md files - condensed, practical reference documents that give AI assistants the context they need to use a library effectively without searching through full documentation. Use when creating library documentation for AI consumption. Use when this capability is needed.
- tomevault-io Bundle AI Evals
Help users create and run AI evaluations. Use when someone is building evals for LLM products, measuring model quality, creating test cases, designing rubrics, or trying to systematically measure AI output quality. Use when this capability is needed.
- tomevault-io Bundle Roznet Flyfun Apps Agent Review
Aviation Agent Architecture Review
- tomevault-io Bundle Prompt Eval Builder
Domain knowledge for extracting eval assertions and generating test invocation prompts from command/agent specs. Used for building promptfoo evaluation configs. Use when this capability is needed.
- tomevault-io Bundle Rubakas Agent Notes Rails Kamal
Kamal
- tomevault-io Bundle Rubakas Agent Notes Rails Style
Code Style Guide
- tomevault-io Bundle Pi Share
Load and parse session transcripts from shittycodingagent.ai/buildwithpi.ai/buildwithpi.com/pi.dev (pi-share) URLs. Fetches gists, decodes embedded session data, and extracts conversation history. Use when this capability is needed.
- tomevault-io Bundle Agent Evaluation
Use this when you need to EVALUATE OR IMPROVE or OPTIMIZE an existing LLM agent's output quality - including improving tool selection accuracy, answer quality, reducing costs, or fixing issues where the agent gives wrong/incomplete responses. Evaluates agents systematically using MLflow evaluation with datasets, scorers, and tracing. IMPORTANT - Always also load the instrumenting-with-mlflow-tracing skill before starting any work. Covers end-to-end evaluation workflow or individual components (tracing setup, dataset creation, scorer definition, evaluation execution).
- tomevault-io Bundle Mo Development
This skill should be used when the user asks to "create module", "add module", "module structure", "use Res type", "return Res", "Res.Ok", "Res.Fail", "IsFailed pattern", "module registration", "module dependencies", "module pattern", "Monica architecture", "service layer pattern", "create service", "add service", "create hosted service", "add background service", "MoBackgroundService", "MoHostedService", "RecordState", "hosted service observability", "service state tracking", "CoordinatedLeaderService", "GetRequestedConfigMethodKeys", "required config", "required configuration methods", or needs guidance on Monica module architecture, the unified result model Res, module registration patterns, Res usage scope (UI vs infrastructure), required Guide configuration validation, or hosted service development with observability. Use when this capability is needed.
- tomevault-io Bundle Idapython
IDA Pro Python scripting for reverse engineering. Use when writing IDAPython scripts, analyzing binaries, working with IDA's API for disassembly, decompilation (Hex-Rays), type systems, cross-references, functions, segments, or any IDA database manipulation. Covers ida_* modules (50+), idautils iterators, and common patterns. Use when this capability is needed.
- tomevault-io Bundle Serena Usage
This skill should be used when the user asks to "use serena", "semantic search", "symbol analysis", "find references", "code navigation", or needs Serena MCP guidance. Provides Serena tool usage patterns. Use when this capability is needed.
- tomevault-io Bundle Promptguard
Use when auditing system prompts, agent prompts, router prompts, tool/function-call prompts, or prompts that cause inconsistent, unsafe, malformed, or surprising LLM behavior.
- tomevault-io Bundle Lens MCP Code
Install the lens MCP server and register it with Claude Code Use when this capability is needed.
- tomevault-io Bundle Socratic
Socratic questioning to examine beliefs, uncover assumptions, and develop deeper understanding. Use to challenge thinking, evaluate proposals, or teach without lecturing. Use when this capability is needed.
- tomevault-io Bundle Google Adk Python
Build AI agents with Google ADK Python (Agent Development Kit). Use for multi-agent systems, workflow agents (sequential/parallel/loop), Vertex AI deployment, tool integration, human-in-the-loop. Use when this capability is needed.
- tomevault-io Bundle Iphoneclaw Action Scripts
Record, register, and invoke iPhoneClaw action scripts to reduce VLM tokens and make automations repeatable. Use when you want the model/agent to call `run_script(name=..., vars=...)`, when updating `action_scripts/registry.json`, when exporting scripts from `runs/*/events.jsonl`, or when triggering scripts remotely via `python -m iphoneclaw ctl run-script` while the worker is paused. Use when this capability is needed.
- tomevault-io Bundle Physicsnemo Discover
Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment setup, training-loop or other code authoring/scaffolding, contributor/CI/packaging questions, repo-specific questions in physicsnemo-sym/-cfd/-curator, or general (non-physics) ML/PyTorch. Use when this capability is needed.
- tomevault-io Bundle Openbotauth
Get a cryptographic identity for your AI agent. Generate Ed25519 keys, sign your work, prove who you are — across any platform. Use when this capability is needed.
- tomevault-io Bundle Openclaw Openclaw Coding Agent
Coding Agent (bash-first)
- tomevault-io Skill Agent Identity
Cryptographic identity for AI agents. Register on-chain identity, sign messages, verify other agents, link platform accounts. Stake USDC to prove you're real. Built by g1itchbot for the USDC Hackathon. Use when this capability is needed.
Audited - tomevault-io Skill Agent Registry
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. Use when this capability is needed.
Audited - tomevault-io Skill Agent Sentinel
Use when working with the operational circuit breaker for this agent. Enforces budget limits locally. **Sign up at agentsentinel.dev for real-time dashboards and human approval workflows.**
- tomevault-io Bundle Continuity
Persistent continuity management for AI agents. Ensures continuity across sessions, prevents data loss from compaction, and maintains reliable audit trails. Logs all human interactions and agent responses for complete conversational continuity. Works with base OpenClaw — no external dependencies. Continuity data stays local-only, never in git. Use when this capability is needed.
- tomevault-io Bundle Dev AI Agent
AI / LLM / Agent workflow development skill. Covers golden rules, model invocation routines, prompt management, security (injection / privilege escalation), observability, evaluation and testing, and anti-patterns. Use when building or reviewing agents, LLM integrations, and tool-call orchestration. Use when this capability is needed.
- tomevault-io Bundle Subagents
This skill should be used when coordinating agents, delegating tasks to specialists, or when "dispatch agents", "which agent", or "multi-agent" are mentioned. Use when this capability is needed.
- tomevault-io Bundle Autonomy Testing Auditor
Evaluate whether a repository's unit, integration, end-to-end, visual, contract, and CI test setup lets an AI agent self-verify changes through fast, isolated, and well-targeted automated feedback. Use when auditing test readiness, onboarding a new project, or assessing whether the agent can safely validate its own work. Do not use when the main question is app startup or runtime bootstrapping (use autonomy-staging-auditor) or when debugging one failing test (use interface-sre-agent). Use when this capability is needed.
- tomevault-io Bundle Agent Reviews
Review and fix PR review bot findings on current PR, loop until resolved. Fetches unanswered bot comments, evaluates each finding, fixes real bugs, dismisses false positives, and replies to every comment with the outcome. Use when this capability is needed.
- tomevault-io Bundle Paulkinlan Co Do Code Reviewer
Code Reviewer Agent
- tomevault-io Bundle Md Docs
This skill should be used ONLY when the user asks to update README.md, CLAUDE.md, AGENTS.md, or CONTRIBUTING.md. Trigger phrases include "update README", "update context files", "init context", "create CLAUDE.md", "update CLAUDE.md", "update AGENTS.md", "update CONTRIBUTING". Do NOT activate this skill for any other Markdown file updates. Use when this capability is needed.
- tomevault-io Bundle Game Engines
Unity and Godot game engine development with C# and GDScript via CLI and MCP servers Use when this capability is needed.
- tomevault-io Bundle Plagueho Prompt Babbler Aspire
Aspire Skill
- tomevault-io Bundle Aptos Wallet MCP
Aptos Wallet MCP Skill Use when this capability is needed.
- tomevault-io Bundle Plurigrid Asi Causal Inference
Causal Inference Skill
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 pymc-labs--agent-skills--template, debate-vs, clawphone. 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.