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 Plurigrid Asi MCP TripartiteSKILL: MCP Tripartite Integration
- tomevault-io Bundle Protocol Acset
Model decentralized protocols as attributed C-sets for compositional analysis, interoperability design, and protocol evolution. Apply categorical mathematics to P2P infrastructure. Use when this capability is needed.
- tomevault-io Bundle Second Opinion
Runs external LLM code reviews (OpenAI Codex or Google Gemini CLI) on uncommitted changes, branch diffs, or specific commits. Use when the user asks for a second opinion, external review, codex review, gemini review, or mentions /second-opinion.
- tomevault-io Bundle Vectordb
Vector database operations for embeddings and semantic search. Activate for Pinecone, Weaviate, Chroma, pgvector, RAG, and similarity search. Use when this capability is needed.
- tomevault-io Bundle Jules Remote
Use this skill when dispatching atomic, isolated development tasks to Jules, a remote AI coding agent.
- tomevault-io Bundle Mario Pereyra Mapj Mapj MCP
mapj-mcp — Agent Skill v2.0 (MCP 2025-06-18)
- tomevault-io Bundle MCP Use MCP Use MCP Builder
MCP Server Builder
- tomevault-io Bundle Rd Agent
你负责维护实验的累积运行总结文件 `reports/summary.md`。 Use when this capability is needed.
- tomevault-io Bundle Microsoft Skillopt Skillopt
SkillOpt-Sleep: offline self-evolution for a local Claude agent
- tomevault-io Bundle Doc Tester
Agent for validating Hex1b documentation against actual library behavior. Use when auditing documentation accuracy, testing interactive examples, or identifying discrepancies between documentation and implementation. Use when this capability is needed.
- tomevault-io Bundle Test Fixer
Agent for diagnosing and fixing flaky terminal UI tests in the Hex1b test suite. Use when tests pass locally but fail in CI, or when tests exhibit timing-sensitive behavior. Use when this capability is needed.
- tomevault-io Bundle Dev Agent
Coding worker agent — executes tasks in git worktrees, follows project guidance. Activate with /skill dev-agent. Use when this capability is needed.
- tomevault-io Bundle Reseed
How to use reseed to manage agent skills in a project. Use when the user mentions reseed, agent skills, SKILL.md, .agents/skills/, or .claude/skills/, or wants to install, add, remove, sync, or list skills. Use when this capability is needed.
- tomevault-io Bundle 5whys
Five Whys root cause analysis. Iteratively asks "why" to drill past symptoms to underlying causes. Use for debugging, investigating failures, or understanding why something went wrong. Use when this capability is needed.
- tomevault-io Bundle Gastown
Multi-agent orchestrator for Claude Code. Use when user mentions gastown, gas town, gt commands, bd commands, convoys, polecats, crew, rigs, slinging work, multi-agent coordination, beads, hooks, molecules, workflows, the witness, the mayor, the refinery, the deacon, dogs, escalation, or wants to run multiple AI agents on projects simultaneously. Handles installation, workspace setup, work tracking, agent lifecycle, crash recovery, and all gt/bd CLI operations. Use when this capability is needed.
- tomevault-io Bundle Nemo Curator Docs
Maintain the NeMo Curator Fern docs site — add, update, move, or remove pages under fern/. Use for any documentation changes. Use when this capability is needed.
- tomevault-io Skill Openclaw Skills Agent Tools
Openclaw Skills Agent Tools
- tomevault-io Bundle Write Unit Tests
Enable an agent to write unit tests Use when this capability is needed.
- tomevault-io Bundle Apa
AI Porker Arena for command-line agents. Use `npx @apa-network/agent-sdk@beta next-decision` for single-step decisions. Use when this capability is needed.
- tomevault-io Bundle Say Narration
Use macOS text-to-speech for agent narration and announcements. Sub-agents announce themselves using different language voices speaking English. Use for multi-agent workflows where each agent has a distinct voice identity. Use when this capability is needed.
- tomevault-io Bundle Vibes Brainstorm
Lightweight requirements gathering before app generation. Asks non-technical multiple-choice questions to understand user intent, then produces a brief for the generate prompt. Use when this capability is needed.
- tomevault-io Bundle Web Dev
Web 开发最佳实践和现代前端技术栈指导 Use when this capability is needed.
- tomevault-io Bundle Pi Coding Agent Config
Reference for customizing and configuring pi-coding-agent (pi). Covers settings files (settings.json), extensions, skills, prompt templates, package management, and programmatic usage via the SDK. Use when asked about pi configuration or customization. Use when this capability is needed.
- tomevault-io Bundle Zapier Status
Check the health of your Zapier MCP setup. Three modes — health check (dashboard view), audit (find waste and duplicates), diagnose (systematic troubleshooting). Use when asking "is my MCP working?", "check my tools", "audit my setup", "what's broken?", or "zapier status". Use when this capability is needed.
- tomevault-io Bundle Send Usdc
Send USDC to another agent or wallet on Base. Direct on-chain transfer, no intermediary, settles in seconds. Use when the agent needs to pay another agent, move funds between wallets, settle a debt in USDC, or make any on-chain payment. Use when this capability is needed.
- tomevault-io Bundle Goblintown Sidecar
Use when the user wants Codex to install, register, verify, configure, or use Goblintown as a local Codex MCP sidecar or composer extension for Single Goblin calls, full rites, planner DAGs, provider checks, or Tank-backed local Warren workflows.
- tomevault-io Bundle Pi Auth
Pi Network authentication flow - SDK authenticate, access token verification, security rules. Use when implementing or debugging Pi login, token verification, or user identity. Use when this capability is needed.
- tomevault-io Bundle Adaworldapi Lance Graph Cca2a
CCA2A — Claude Code Agent-to-Agent
- tomevault-io Bundle Publishing
Publishing and release workflow with semantic-release and GitHub Actions Use when this capability is needed.
- tomevault-io Bundle Llmlb CLI Usage
Use llmlb assistant CLI commands (curl/openapi/guide) instead of the deprecated MCP server flow. Use when this capability is needed.
- tomevault-io Bundle Agentic Gateway
Wire Alchemy into application code without an API key, using the x402 or MPP gateway with wallet-based auth (SIWE/SIWS) and per-request payments (USDC via x402, or USDC/credit-card via MPP). Specialized app-integration path. Use when the user is building application code AND no API key is available, or they're an autonomous agent that needs to pay for itself, or they explicitly want x402/MPP. For normal app code with an API key, use `alchemy-api`. For live agent work in this session (querying, admin, automation), use `alchemy-cli` (preferred) or `alchemy-mcp`. Use when this capability is needed.
- tomevault-io Bundle Api2cli
Generate a working CLI from any API, then wrap it in a Claude Code skill. Point it at API docs, a live URL, or a peek-api capture and get a dual-mode Commander.js CLI (human + agent output) plus a ready-to-use skill folder. Use when user wants to wrap an API in a CLI, generate a CLI from API docs, turn an API into a command-line tool, scaffold a CLI from discovered endpoints, or create a skill for an API. Use when this capability is needed.
- tomevault-io Bundle Submit Pr From Current Changes
Create a branch, commit existing local changes, push them, and open a pull request. Use when submitting current work as a PR. Use when this capability is needed.
- tomevault-io Bundle Altic Studio
macOS automation skill for AppleScript actions and Chrome browser control via MCP CDP tools. Use when this capability is needed.
- tomevault-io Bundle Openpets
Use when the user asks to install, configure, verify, troubleshoot, or understand OpenPets; install or select a pet; connect Claude Code, OpenCode, Cursor, Codex, or MCP clients; configure a project to use a specific pet; or debug openpets_status, openpets_react, or openpets_say.
- tomevault-io Bundle Say Hi
Respond with a friendly greeting. Use when the user says hi, hello, greets the agent, or asks to be greeted. 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 plurigrid--asi--mcp-tripartite, protocol-acset, second-opinion. 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.