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 Qig Purity ValidationValidate Quantum Information Geometry (QIG) purity across codebase changes. Detect Euclidean contamination, forbidden LLM imports, and cosine similarity. Enforce Fisher-Rao metrics per E8 Protocol v4.0. Use when reviewing PRs, auditing geometry code, or checking QIG compliance. Zero tolerance for geometric impurity. Use when this capability is needed.
- tomevault-io Bundle Init Project Bootstrap
当用户提及“代码仓初始化”“初始化代码仓”“初始化目录”“初始化项目结构”“初始化项目文档路径”“初始化 Codex 持续开发工作流”“初始化 antarx-harness 文档体系”或明确要求执行 `/init` 命令时触发；若同时提及 simple、lightweight、轻量、极简、轻量 harness、初始化轻量 harness、轻量化 agent 流程等表达，则使用轻量分支。用于在当前项目目录创建缺失的 AGENTS.md、ARCHITECTURE.md 与 docs 工作流骨架，必要时初始化 Git 仓库，并提交本次新增文档；若已有 AGENTS.md 与模板不同，必须由 agent 比对并合成为一份。 Use when this capability is needed.
- tomevault-io Bundle Components Guide
Guide to using Convex components for feature encapsulation. Learn about sibling components, creating your own, and when to use components vs monolithic code. Use when this capability is needed.
- tomevault-io Bundle Function Creator
Create Convex queries, mutations, and actions with proper validation, authentication, and error handling. Use when implementing new API endpoints. Use when this capability is needed.
- tomevault-io Bundle Browsing Web
Web scraping with agents, browser automation, content extraction, and Use when this capability is needed.
- tomevault-io Bundle Create Story
Create user story from description with acceptance criteria Use when this capability is needed.
- tomevault-io Bundle Gologo13 Agent Skills Address Github Pr Comments
Address GitHub PR Comments
- tomevault-io Bundle Plot Workflow
Orchestrate and coordinate one-click generation workflow for major plot points and detailed plot points. Suitable for structured analysis of long stories, complex tasks requiring modular agent collaboration Use when this capability is needed.
- tomevault-io Bundle Gke Workload Scaling
Specific workflows for scaling GKE workloads using HPA and VPA, as well as best practices for autoscaling configuration. Use when this capability is needed.
- tomevault-io Bundle Github Issue Implementer
You are an implementer of GitHub issues. You are an Agent who has been assigned an issue to work on. Use when this capability is needed.
- tomevault-io Bundle Langcare Langcare MCP Fhir Procedure Note Template
Procedure Note Template
- tomevault-io Bundle Latestaiagents Agent Skills MCP Client Integration
MCP Client Integration
- tomevault-io Bundle Laurigates Claude Plugins Custom Agent Definitions
Custom Agent Definitions
- tomevault-io Bundle Devops Git Guard
Use when working with the DevOps Git Guard acts as a pre-push gatekeeper and documentation auditor. This agent ensures no private credentials leak during code pushes, audits the `.gitignore` setup, and updates the repository's documentation (`README.md`) before any branch merges.
- tomevault-io Bundle Resource Planner
Plans resource allocation and agent assignments to tasks. Use when you need to allocate agents to tasks, balance workload, or plan resource usage. Considers task dependencies, agent capabilities, and workload distribution. Use when this capability is needed.
- tomevault-io Bundle Paw Review Baseline
Analyzes the codebase at the PR's base commit to establish baseline understanding for review comparison.
- tomevault-io Bundle Paw Review Response
Shared PR review comment response mechanics for PAW activity skills. Provides TODO workflow, commit patterns, and reply format for addressing reviewer feedback. Use when this capability is needed.
- tomevault-io Bundle Paw Review Workflow
Orchestrates the PAW Review workflow, coordinating activity skills to analyze PRs and generate comprehensive review feedback. Use when this capability is needed.
- tomevault-io Bundle Lucaperret Agent Skills Anthropic Connector Submit
Submit to Anthropic Connectors Directory
- tomevault-io Bundle MCP Categorical
MCP (Model Context Protocol) server patterns with categorical tool composition and typed context protocols. Use when building MCP servers with categorical composition patterns, designing tool interfaces using functors and natural transformations, implementing typed context management, or creating composable AI tool ecosystems with categorical guarantees. Use when this capability is needed.
- tomevault-io Bundle Repo Readme Generator
Intelligent README.md generation prompt that analyses project documentation structure and creates comprehensive repository documentation. Scans repository documentation files and copilot-instructions.md to extract project information, technology stack, architecture, development workflow, coding standards, and testing approaches while generating well-structured markdown documentation with proper formatting, cross-references, and developer-focused content. Use when this capability is needed.
- tomevault-io Bundle AI Agent Identity Authz
Review AI agent systems for agent impersonation, capability escalation, missing agent identity primitives, and authorization failures that allow agents to act beyond their granted permissions or impersonate other agents or human users. Use when this capability is needed.
- tomevault-io Bundle Skill Scanner
Macで登録済みClaude agent skillsをスキャンし一覧表示。「スキルを調べて」「登録済みスキル一覧」などで使用。読み取り専用で安全に実行。 Use when this capability is needed.
- tomevault-io Bundle Skill Task Model
Standards for Technical Specifications (TASK) and Use Cases. Use when this capability is needed.
- tomevault-io Bundle Create Expert
Scaffold a new agent expert structure with expertise.yaml, question, self-improve, and plan prompts Use when this capability is needed.
- tomevault-io Bundle Create Prompt
Generate a new agentic prompt at specified level (1-7) using meta-prompting. Use when creating new slash commands or workflow prompts. Use when this capability is needed.
- tomevault-io Bundle Model Content
Design content type schema with fields, validation, and relationships. Use for content modeling workshops or quick schema design. Use when this capability is needed.
- tomevault-io Bundle Michaelsvanbeek Personal Agent Skills Git Workflow
Git Workflow Standards
- tomevault-io Bundle Miemieeeee Comfyui Agent Skill Comfyui Agent Skill
comfyui-agent-skill-mie
- tomevault-io Bundle Modbender Skill Library MCP AI Agent Card Payments
---
- tomevault-io Bundle AI Agent Setup Service
幫你setup同埋客製化AI Agent既服務Skill Use when this capability is needed.
- tomevault-io Bundle Modbender Skill Library MCP Chinese AI Agent Guide
---
- tomevault-io Bundle Modbender Skill Library MCP Emblem AI Agent Wallet
---
- tomevault-io Bundle Toolkit Skill Author
Authors or extends a skill in mc-agent-toolkit. Gates for forbidden buckets and name collisions, applies CONTRIBUTING's extend-or-split rules, then edits a peer skill or hands off to Anthropic's skill-creator and walks the registration checklist. Use when this capability is needed.
- tomevault-io Bundle Design Discussion
Facilitates structured design discussions through conversational, paced dialogue. Use when brainstorming design decisions, exploring architecture options, or collaborating with users on technical direction. Use when this capability is needed.
- tomevault-io Bundle Ndhananj Codex Agent Setup Springboot Verification
Spring Boot Verification Loop
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 qig-purity-validation, init-project-bootstrap, components-guide. 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.