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 Planner Manager ExplorerUse when a planning or manager agent must maintain architecture, framework decomposition, TODO tables, and next-session objectives while also exploring missing context from the repository, official docs, external APIs, datasets, or similar open-source projects before handing concrete work to an execution agent.
- tomevault-io Bundle Add Wasp Skills
Install Wasp agent skills (plugins) that add Wasp knowledge and best practices to your AI coding tools. Use when this capability is needed.
- tomevault-io Bundle Auth Bypass
认证绕过漏洞检测与利用。当目标存在登录功能、权限控制、JWT/Session 认证时使用。包括 IDOR、越权访问等。 Use when this capability is needed.
- tomevault-io Bundle Sdd Implement
Implementation guidelines for SDD workflow. Use when implementing features, applying TDD, checking security, or ensuring code quality. Invoked via /sdd-implement <feature-name>. Use when this capability is needed.
- tomevault-io Bundle Setup Opencode
Set up Open Code agent as an alternative to Claude Code. Supports OpenRouter, Gemini, and OpenAI providers. Triggers on "setup opencode", "setup open code", "use opencode", "switch to opencode". Use when this capability is needed.
- tomevault-io Bundle Hyper Auto
Use when plan-harden → implement-harden should chain in one gesture — hyper-plan-loop produces a clean plan, then hyper-implement-loop executes and hardens it. Also when the user invokes /hyperclaude:hyper-auto. For manual control between phases use /hyperclaude:hyper-plan-loop, inspect the plan, then /hyperclaude:hyper-implement-loop. Inherits both loops' agent-teams requirement (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`).
- tomevault-io Bundle Trend Modeling
This skill should be used when the user asks to "model trends with limited data", "three-valued logic analysis", "scenario generation", "transitional graphs", "qualitative trend analysis", "uncertain data analysis", "minimal-information modeling", or needs guidance on trend-based modeling using INC/DEC/CONST logic, scenario planning with limited quantitative data, or generating transitional scenario graphs. Use when this capability is needed.
- tomevault-io Bundle Deck LLM
Machine learning for deck analysis using PyTorch neural networks Use when this capability is needed.
- tomevault-io Bundle Optimize Protocol
Autonomous framework engineer — reads VibeHQ post-run analysis, understands root causes of multi-agent coordination failures, then designs and implements real code changes (new features, refactors, architectural improvements) to fix them. Not parameter tuning — actual engineering. Use when this capability is needed.
- tomevault-io Bundle MCP Testing
MCP Testing Strategies with Vitest, Inspector, and Integration Tests Use when this capability is needed.
- tomevault-io Bundle Noui Generate MCP
Use this skill when the user wants to start, stop, check, or list generated NoUI MCP servers, or connect a server to Claude Code. Triggers on "start the MCP server", "run noui mcp", "connect to Claude Code", "add to mcpServers", "noui mcp start", "noui mcp list", "noui mcp status", "how do I use the generated server", or "I want to call this tool from Claude".
- tomevault-io Bundle Afine907 Skills Pr Description
PR Description — Pull Request 描述生成 Agent
- tomevault-io Bundle Anp Multilang Release
在 ANP SDK 仓库里统一发布 Go、Python、Rust 三个 SDK。用于同时更新 pyproject.toml、anp/__init__.py、uv.lock、rust/Cargo.toml、rust/Cargo.lock、golang/version.go，执行 uv/cargo/go 校验，发布 PyPI 与 crates.io，并按 Go 子目录 module 规则推送 golang/vX.Y.Z tag。用户提到 Go/Python/Rust 一起发版、统一版本号、固定发布 0.7.2、下一版自动 +1、保持版本段为一位数时使用此 skill。 Use when this capability is needed.
- tomevault-io Bundle Aidemd MCP Server Aide Handoff
Aidemd Mcp Server Aide Handoff
- tomevault-io Bundle Create Subagents
Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents. Use when this capability is needed.
- tomevault-io Bundle Cugenopt Problem Gen
Generate cuGenOpt GPU-accelerated optimization Problem definitions from natural language descriptions. Use when the user describes a combinatorial optimization problem (TSP, VRP, knapsack, scheduling, assignment, graph coloring, bin packing, etc.) and wants to solve it with cuGenOpt, or asks to generate, create, model, or run an optimization problem on GPU. Use when this capability is needed.
- tomevault-io Bundle Tui Validate
Validates the Coop TUI by capturing output from a tmux session using freeze and applying LLM-as-judge semantic validation. Supports text and visual (PNG/SVG) validation modes.
- tomevault-io Bundle Ma1orek Replay Typescript MCP
TypeScript MCP on Cloudflare Workers
- tomevault-io Bundle Mauromedda Agent Toolkit Bash
ABOUTME: Bash scripting skill for production-quality scripts with Bash 4.x+
- tomevault-io Bundle Mauromedda Agent Toolkit Make
ABOUTME: Make skill for idiomatic, maintainable Makefiles with modular patterns
- tomevault-io Bundle Prompt Builder
Build complete agent prompts deterministically via Python script. Use BEFORE spawning any BAZINGA agent (Developer, QA, Tech Lead, PM, etc.). Use when this capability is needed.
- tomevault-io Bundle Mempalace Recall
Recall protocol for MemPalace — search the palace before answering about past work, people, projects, or prior decisions. Apply when the user asks what was decided, what happened before, who someone is, what was discussed last time, or anything that may already be filed in their memory palace; or when mempalace-recall is invoked. Complements the mempalace setup skill and requires the mempalace-mcp server. Use when this capability is needed.
- tomevault-io Bundle Skillgrade Setup
Sets up and runs skillgrade evaluation pipelines for Agent Skills. Use when initializing eval configurations, running trials, reviewing results, or integrating with CI. Don't use for writing grader scripts, general test authoring, or non-agentic documentation.
- tomevault-io Bundle Microsoft Sre Agent Sre Agent
SRE Agent Administration
- tomevault-io Bundle Synapseml Local Setup
Set up and validate SynapseML locally in WSL or Linux. Use when an agent needs SynapseML working locally, runs sbt compile/test, sees Java 21, Scala 2.12 compiler-bridge, bad constant pool index, Spark, or local validation failures. Use when this capability is needed.
- tomevault-io Bundle CLI To JS
Use when wrapping CLI binaries in JavaScript, automating shell workflows in TypeScript, composing multiple CLIs into scripts, or building agent tool-use. Covers convertCliToJs, $command, $validate, $spawn, script(), .text()/.lines()/.json() output parsing.
- tomevault-io Bundle Miro Platform
Comprehensive guide to Miro as a visual collaboration platform. Covers canvas features, content types, AI capabilities, and enterprise use cases. For MCP tool documentation, see the miro plugin's skill (miro-mcp). Use when this capability is needed.
- tomevault-io Bundle Mthines Agent Skills Charting
Charting Skill
- tomevault-io Bundle Mullzhang Skills Agent Memory
Agent Memory
- tomevault-io Bundle AI Review Skill
Generates structured AI paper reviews (SoT style) for LaTeX, PDF, and Word manuscripts. Uses SoT prompt in English for English papers and SoT prompt in Chinese for Chinese papers. Use when the user asks to review a paper, 审稿, 论文审稿, review manuscript, or get strengths/weaknesses/suggestions for a .tex, .pdf, or .docx file.
- tomevault-io Bundle Cynefin
Cynefin sense-making framework categorizing problems as Simple, Complicated, Complex, Chaotic, or Confused to select the right approach. Use when unsure how to tackle a problem. Use when this capability is needed.
- tomevault-io Bundle Feynman
Feynman Technique for deep learning—explain a concept simply, identify gaps, fill them, then refine. Use when learning something new, testing understanding, or preparing to teach. Use when this capability is needed.
- tomevault-io Bundle Redteam
Red team adversarial analysis to find weaknesses, vulnerabilities, and failure modes. Use before launches, for security review, or when a plan feels too perfect. Use when this capability is needed.
- tomevault-io Bundle Sixhats
Six Thinking Hats parallel thinking—explore from six perspectives (facts, feelings, caution, benefits, creativity, process). Use for group decisions or ensuring all angles are considered. Use when this capability is needed.
- tomevault-io Bundle Codegen Refactor
Perform refactoring using TDD starting from README + Issue (following codegen-test), aligning with existing implementation conventions, and leveraging Serena MCP semantic search/editing to improve internal quality with high performance and race-safety in mind. Use when this capability is needed.
- tomevault-io Bundle Lettactl
Manage Letta AI agent fleets with kubectl-style CLI 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 planner-manager-explorer, add-wasp-skills, auth-bypass. 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.