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 Skill AgentguardGoPlus AgentGuard — AI agent security guard. Automatically blocks dangerous commands, prevents data leaks, and protects secrets. Use when reviewing third-party code, auditing skills, checking for vulnerabilities, evaluating action safety, or viewing security logs. Use when this capability is needed.
- tomevault-io Bundle Playwright Testing
Guide for writing, organizing, and maintaining Playwright end-to-end tests using the Page Object Model pattern Use when this capability is needed.
- tomevault-io Bundle Sglang Diffusion Benchmark Profile
Use when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.
- tomevault-io Bundle Cmax
Use when working with the default FAT umbrella. Auto-runs deepresearch + multispec decomposition + parallel /goal + verify. Opus for planning/judgment/verification; Sonnet for sub-Spec execution (escalates per router). Multispec engine selects Mode A (SDK subagents) or Mode B (Claude Code Agent Teams) automatically based on work size. Your default daily-driver.
- tomevault-io Bundle Hooked UX
Design habit-forming product loops using the Hook Model (Trigger, Action, Variable Reward, Investment). Use when the user mentions "users arent coming back", "engagement loops", "habit formation", "push notifications", "variable rewards", "daily active users", "habit zone", or "user retention loops". Also trigger when designing notification strategies, building streaks or progress systems, or analyzing why users stop using a product after initial signup. Covers ethics evaluation and onboarding for habits. For friction reduction and B=MAP, see improve-retention. For viral sharing, see contagious. Use when this capability is needed.
- tomevault-io Bundle Wquguru Exoshell Exoshell
Ralph Agent
- tomevault-io Bundle Trellis Spec Bootstarp
Bootstrap project-specific Trellis coding specs with a platform-neutral single-agent workflow. Use when creating or refreshing .trellis/spec guidelines, analyzing a codebase with GitNexus, ABCoder, or source inspection, decomposing package/layer spec work, and writing real codebase-backed spec docs without placeholder text. Use when this capability is needed.
- tomevault-io Bundle X07 Build Run
Expert backend for deterministic solve-world execution via x07-host-runner. Prefer `x07 run` as the canonical agent entry point. Use when this capability is needed.
- tomevault-io Bundle Solomd
Read, search, edit, and version-control any folder of Markdown notes via the SoloMD MCP server. 13 tools including AutoGit per-note history, semantic search, and write-with-sandbox via an accept/reject branch. Includes 11 starter agent recipes (weekly review, todo extract, link suggester, …). Use when this capability is needed.
- tomevault-io Bundle AI Tuning
Optimize AI assistant configurations for maximum effectiveness. USE THIS SKILL when user says "improve CLAUDE.md", "better copilot instructions", "tune AI", "optimize prompts", "MCP configuration", or wants to enhance AI assistant behavior. Use when this capability is needed.
- tomevault-io Bundle Scp Pertkge
Use when you need to connect to the SciGraph SCP server for PertKGE (knowledge graph for compound-protein interaction inference using perturbation transcriptomics + regulatory network; cold-start CPI prediction) and call its MCP tools (query_cypher, get_kg_statistics, get_entity_details, get_experiment_workflow), including streamableHttp configuration with SCP-HUB-API-KEY and Python 3.10+ usage examples.
- tomevault-io Bundle Vloj
LibreOJ题目抓取与解题工作流。用户输入形如loj1/loj001或https://loj.ac/p/1 等题号或URL时触发；创建以题号命名的空文件夹，使用Chrome DevTools MCP读取题面并保存为md文件，最后用C++、C、C#、Python、Java、Kotlin、Pascal、Rust、Go、Haskell、F#生成解答文件。 Use when this capability is needed.
- tomevault-io Bundle Agentjj
Agent-first version control with jj. Self-contained (no jj install needed). Auto-colocates with git repos. Complete orientation, typed commits, symbol queries, checkpoints, undo, bulk operations, impact analysis. Use --json for machine output. Start with 'agentjj orient' in any repo. Use when this capability is needed.
- tomevault-io Bundle Dual Verify
Parallel Claude Code deep-review + Codex code-audit before PR readiness; replaces single-agent code-review Use when this capability is needed.
- tomevault-io Bundle Safe Code
Use when asked to run a full repo hygiene pass, full cleanup, or to maintain a repo in one go — and whenever the user invokes /safe-code or any wrapper of it (/skill:safe-code, /skills safe-code, $safe-code, @safe-code, or bare safe-code), including --continue to resume saved work and --save to finalize docs and commit. Also use for first-time project setup, restoring project context or session memory, dead-code audits, or agent-config trust checks.
- tomevault-io Bundle Perf Investigation Logger
Use when appending structured perf investigation notes and evidence.
- tomevault-io Bundle Doc Verify
Use when /doc-rigor has written or updated documentation and you need independent accuracy verification, or when existing docs may contain stale API claims or wrong command examples. Fresh-agent verification against code reality.
- tomevault-io Bundle Fastapi Crud
Step-by-step guide for adding new CRUD endpoints to the FastAPI backend. Use when creating new API resources with router, Pydantic schemas, service layer, and tests. Use when this capability is needed.
- tomevault-io Bundle Tool Design
This skill should be used when the user asks to "design agent tools", "create tool descriptions", "reduce tool complexity", "implement MCP tools", or mentions tool consolidation, architectural reduction, tool naming conventions, or agent-tool interfaces. Use when this capability is needed.
- tomevault-io Bundle Solveit
Read, edit, and execute SolveIt dialogs (notebooks) via CLI. Add code/note/prompt cells, run them, and inspect outputs. Use when this capability is needed.
- tomevault-io Bundle Botchan
Onchain agent messaging on Base - post to feeds, send DMs, explore other agents Use when this capability is needed.
- tomevault-io Bundle Erc8004
Register AI agent identity on Ethereum via ERC-8004 Trustless Agents standard Use when this capability is needed.
- tomevault-io Bundle Routing
Multi-agent routing, channel bindings, and tool policies Use when this capability is needed.
- tomevault-io Bundle Mcpc
Use mcpc CLI to interact with MCP servers - call tools, read resources, get prompts. Use this when working with Model Context Protocol servers, calling MCP tools, or accessing MCP resources programmatically. Use when this capability is needed.
- tomevault-io Bundle Ar4mirez Samuel Cuda Guide
CUDA Guide
- tomevault-io Bundle Gh Agent Task
GitHub CLI Agent Task Extension Use when this capability is needed.
- tomevault-io Bundle Famou Result Visualization
为 FaMou 进化算法生成可行解的 Python 代码解生成可视化结果页面。当用户提到"FaMou 可视化"、"把这个解可视化"、"可行解结果展示"、"evolution 结果"、"evolve 可视化"，或者提供了 Python 代码形式的问题解（路径规划、排课、背包、TSP、调度、机器学习等）需要直观展示效果时，必须使用此技能。即使用户只说"帮我可视化这个解"、"画出来看看"、"展示一下结果"，只要上下文涉及进化算法、优化问题的解，也应立即触发此技能。 Use when this capability is needed.
- tomevault-io Bundle Crucible
Crucible — codebase-level deep adversarial review using SOTA paid frontier models. Walks code piece-by-piece, dispatches a panel of top current OpenRouter paid models (DeepSeek V4-Pro, Gemini 3.1 Pro, Kimi K2.6, MiniMax M2.7 by default, plus Qwen3 and GLM-5 fallbacks) per file with auto family-diversity. Models team up sequentially or in parallel-blind, findings deduplicated and severity-ranked. Costs roughly $0.01–$0.75 per run depending on size. Use whenever the user wants a deep multi-model audit of a whole repo, a directory, or a substantial diff — not a quick single-file review (use /rival for that). Triggers on phrases like "deep review the codebase", "multi-model audit", "go through file by file", "put the repo through the crucible", "team of models review my code", "thorough adversarial review of [project]". Invoke with /crucible. Use when this capability is needed.
- tomevault-io Bundle Moemail
Use when working in this repository and an AI agent needs a temporary/disposable email address through the MoeMail CLI.
- tomevault-io Bundle Kirby Routing And Representations
Implements custom Kirby routes and content representations (.json/.xml/.rss), including redirects, sitemap endpoints, and URL pattern filtering. Use when building endpoints, redirects, or representation templates that change how URLs resolve. Use when this capability is needed.
- tomevault-io Bundle Bntvllnt Agent Skills Tmux
tmux
- tomevault-io Bundle Support New Model
Add a new LLM or VLM to LMDeploy's PyTorch backend. Use when this capability is needed.
- tomevault-io Bundle Inspector Implementation
Use when an agent needs to implement or modify the Inspector library itself — panel UI, hierarchy/runtime behavior, custom property models, macros, or Example-app dogfooding. Especially useful when changing `Sources/Inspector/`, `Sources/InspectorInterface/`, or `Sources/InspectorMacros/` and you need the repo's architecture and verification workflow in one place.
- tomevault-io Bundle Itechmeat LLM Code Fastapi
FastAPI
- tomevault-io Bundle Itechmeat LLM Code Inworld
Inworld AI
- tomevault-io Bundle Itechmeat LLM Code Openapi
OpenAPI Specification
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 agentguard, playwright-testing, sglang-diffusion-benchmark-profile. 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.