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 Local CIUse when running 'deno task ci', local CI checks, or pre-push validation. Delegates to sub agent for context efficiency.
- tomevault-io Bundle Resolve Tileops
Per-round driver of stateful agent-driven review-resolution on a tile-ai/TileOPs PR (developer side). Designed for /loop dynamic mode — re-fires until a terminal action. Outer caller must run preflight.sh once before starting the loop. State persists in `.foundry/runs/{issue-<N> | pr-<PR>}/resolve/`. Use when this capability is needed.
- tomevault-io Bundle Trbouma Safebox Safebox
Agent API Skill
- tomevault-io Bundle Tofu At Spawn Templates
Use when needing Agent Teams 역할별 스폰 프롬프트 템플릿 + 도구 할당 + /prompt CE 통합. /tofu-at가 팀원 스폰 시 참조.
- tomevault-io Bundle Useautumn Autumn Autumn
Autumn Pricing Model Design
- tomevault-io Bundle Vapi
Build AI voice assistants and phone agents with Vapi. Use this skill when users want to create voice agents, phone bots, IVR systems, outbound calling campaigns, or any voice-based AI application. Use when this capability is needed.
- tomevault-io Bundle Motion Canvas Agent
Agent tooling for Motion Canvas — seek, screenshot, scene graph inspection, settings control, and rendering via HTTP API. Requires a browser with the editor open. Use when this capability is needed.
- tomevault-io Bundle Conversation To Prompt
Convert the current conversation into a reusable system prompt draft with strict structure and quality checks. Use when this capability is needed.
- tomevault-io Bundle X Ipe Tool Uiux Reference
Execute UIUX reference workflow v3.1 — open target URL via Chrome DevTools MCP, inject two-mode toolbar (Catch Design Theme + Copy Design as Mockup) via direct evaluate_script injection, collect design data with semantic element naming/purpose/relationships, save as referenced-elements.json via MCP. Triggers on "uiux-reference", "execute uiux-reference", "collect design references". Use when this capability is needed.
Audited - tomevault-io Bundle 6eanut LLM Wiki LLM Wiki
LLM Wiki — Compounding Knowledge Base
- tomevault-io Bundle Parallax
General-purpose independent review skill. An independent Agent reviews the executor's documents (bug fixes, new features, plans, analyses, proposals, etc.) to verify whether the analysis is correct, evidence is sufficient, and the proposed approach is sound. Use when this capability is needed.
- tomevault-io Bundle Llmfit Advisor
Detect local hardware (RAM, CPU, GPU/VRAM) and recommend the best-fit local LLM models with optimal quantization, speed estimates, and fit scoring. Use when this capability is needed.
- tomevault-io Bundle Retro
Run a deep session retrospective analyzing the most recent AI coding session. Uses Entire.io session data + static analysis, then the agent reviews its own work to extract learnings and generate rules. Use when this capability is needed.
- tomevault-io Bundle Ask User Collaboration
Ask the application user concise structured questions when missing information blocks a safe AI4J agent action. Use when this capability is needed.
- tomevault-io Bundle Moonbit Agent Guide
Guide for writing, refactoring, and testing MoonBit projects. Use when working in MoonBit modules or packages, organizing MoonBit files, using moon tooling (build/check/test/doc/ide), or following MoonBit-specific layout, documentation, and testing conventions. Use when this capability is needed.
- tomevault-io Bundle Minecraft Debug MCP
Operate and debug the live Minecraft bot through its built-in MCP REPL server. Use when work requires starting the bot with `pnpm dev`, connecting to the local MCP endpoint, inspecting cognitive state/logs/history, injecting synthetic chat/events, or running targeted REPL code against the running brain during investigation and development. Use when this capability is needed.
- tomevault-io Bundle Matplotlib Figures
Publication-quality data plots via matplotlib with venue-specific styles. Use for generating your own figures (timelines, comparison charts, data summaries, heatmaps) that you add to the LaTeX report. Your brain prompt supplies the venue-specific style directory as {{VENUE_SPECIFIC_DIR}} — use that value wherever this skill writes `<VENUE_SPECIFIC_DIR>`. Use when this capability is needed.
- tomevault-io Bundle Muxy CLI
How to drive the Muxy macOS terminal multiplexer from a shell with the `muxy` command — open projects, switch projects/worktrees/tabs, build split layouts, send input to panes, and read visible terminal output. Use this when you are an agent running inside a Muxy pane (or any script on the same machine) and want to control the workspace instead of asking the user to click. Mechanics and the security model live in the linked docs. Use when this capability is needed.
- tomevault-io Bundle Nit
Git for agent identity — one identity, any apps Use when this capability is needed.
- tomevault-io Bundle Rails Activity Timeline
Add polymorphic activity timelines with live Turbo Stream updates to any Rails model. Covers migration, model, concern, shared partials, broadcasting, and optional AI-generated change summaries. Use when this capability is needed.
- tomevault-io Bundle Create Skill
Create a new agent skill — global personal, project-personal, or project-team. Surveys existing skills, checks for overlap, handles the .claude/skills/ symlink and .gitignore whitelist for project skills. Use when you want to formalize a workflow or instruction set. Use when this capability is needed.
- tomevault-io Bundle Economic Reasoning
Economic decision-making for agents in EconomySpace. Activate when the agent observes currency, prices, income, tax, or trading opportunities to make informed financial decisions. Use when this capability is needed.
- tomevault-io Bundle Mission Agent Remove
Remove an Agent roster entry from the active Mission agents.md without closing panes. Use when this capability is needed.
- tomevault-io Bundle Maggy
Use when working with a `UserPromptSubmit` hook classifies every user prompt into one of six cost/performance tiers. The hook injects `additionalContext` instructing Claude to run a specific delegation script and return the output.
- tomevault-io Bundle Bo5amis Swarm Swarm
Swarm — Multi-Agent Orchestration Protocol
- tomevault-io Bundle Adk
Use when working with a set of guidelines to build with Botpress's Agent Development Kit (ADK) - use these whenever you're tasked with building a feature using the ADK
- tomevault-io Bundle Doistbot Loop
Run judgment-driven Doistbot local self-review loops against local git changes. Use when a user wants an agent to review and refine a branch before opening a pull request by running the Doistbot CLI, classifying findings for scope and relevance, fixing actionable issues, rerunning review, and stopping when remaining feedback is nits, out of scope, speculative, or no longer worth addressing. Use when this capability is needed.
- tomevault-io Bundle Try Fix
Attempts ONE alternative fix for a bug, tests it empirically, and reports results. ALWAYS explores a DIFFERENT approach from existing PR fixes. Use when CI or an agent needs to try independent fix alternatives. Invoke with problem description, test command, target files, and optional hints. Use when this capability is needed.
- tomevault-io Bundle Fastapi
Build fast, production-ready Python APIs with type hints, validation, and async support. Use when this capability is needed.
- tomevault-io Bundle Slack
Use when the agent needs to send, edit, delete, or read Slack messages, add or list emoji reactions, pin or unpin messages, fetch member info, or list custom emoji in Slack channels and DMs. Handles all Slack workspace interactions including message management, reaction workflows, pinned-item management, and user lookups via the configured bot token.
- tomevault-io Bundle Propose Automation
Use this skill when the user wants to turn the current conversation into a scheduled automation. Analyze the session and call create_automation to propose one — the user reviews the full prompt + schedule in the approval card before it's saved.
- tomevault-io Bundle God Architecture Check
Pre-flight gate for any Acepe change that touches canonical session state, transcript order, tool operations, provider history parsing, hot state, lifecycle, turn state, activity, capabilities, or UI state derived from agent sessions. Use BEFORE editing code that reads or writes session-shaped data. Also use when the user says 'GOD', 'pure GOD', 'canonical authority', 'is this canonical', 'check this against GOD', 'green architecture', 'fix this dual-system thing', or when planning a migration that removes duplicate state. Use when this capability is needed.
- tomevault-io Bundle Agmsg
Cross-agent messaging via SQLite. Send messages between Claude Code, Codex, Gemini CLI, GitHub Copilot CLI, and other agents. No daemon, no network, no dependencies beyond bash and sqlite3. Use when this capability is needed.
- tomevault-io Bundle Aiperf LLM Ergonomics Review
Use when reviewing AIPerf code for the SEMANTIC qualities that mechanical linters cannot catch — error-message informativeness, type-hint descriptiveness, docstring example usefulness, naming disambiguation, convention explicitness, comment density, and reference-file exemplariness. Invoke after mechanical checks (`make check-ergonomics`, `make check-ruff-baselined`) are green, before shipping a branch or PR. Explicitly out of scope are correctness bugs, style (tabs/quotes), preferences, and anything the guardrails already catch.
- tomevault-io Bundle Aidemd MCP Server Brain
brain — Signpost to the Brain
- tomevault-io Bundle Skill Template
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection. 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 local-ci, resolve-tileops, trbouma--safebox--safebox. 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.