AI & ML

tomevault-io Bundle

Generates comprehensive Map of Content (MOC) documentation for software projects using standard markdown links, analyzing current implementation state from codebase and devlog notes

tomevault-io Bundle

Expert in writing test configurations for agent-benchmark, a testing framework for AI agents using MCP servers. Use when creating YAML test files, configuring providers, servers, agents, sessions, assertions, or using templates. Helps write benchmarks for AI coding agents. Use when this capability is needed.

tomevault-io Bundle

Set up the Agent Collection in a new project. Copies relevant agents and skills, prunes unnecessary ones, and generates the CLAUDE.md agent section. Use when the user says setup agents, add agents to this project, initialize agents, or is starting a new project. Use when this capability is needed.

tomevault-io Bundle

Master of text-based visual communication using ASCII art, Unicode box-drawing, and structured diagram notation. Creates clear, maintainable diagrams for systems, processes, hierarchies, relationships, and psychological structures. Proactively generates diagrams to enhance understanding. Activate on visualization needs, system architecture, process flows, psychological mapping, or when complex concepts would benefit from visual representation. NOT for photo editing, vector graphics, or GUI-based design tools. Use when this capability is needed.

tomevault-io Bundle

> **AI-consumed reference.** Optimized for Claude to read during execution.

tomevault-io Bundle

GraphQL Schema Design and Optimization

tomevault-io Bundle

Use when setting up LLM or embedding models in DataGenFlow via Settings page or API. Guides through provider-specific configuration for OpenAI, Anthropic, Gemini, and Ollama. Use for first-time setup, adding new providers, troubleshooting connection failures, or migrating from .env fallback to proper model configs.

tomevault-io Bundle

Calls qq agent from cli. Use when this capability is needed.

tomevault-io Bundle

Check and configure outfitter marketplaces and plugins. Use when setting up a new project, checking plugin configuration, or when "setup outfitter", "configure plugins", or "marketplace" are mentioned. Use when this capability is needed.

tomevault-io Bundle

Builds repeatable evaluation systems with golden datasets, scoring rubrics, pass/fail thresholds, and regression reports. Use for "LLM evaluation", "testing AI systems", "quality assurance", or "model benchmarking".

tomevault-io Bundle

This skill should be used when the agent needs to give a spoken voice update to the user, or when reminded by a Stop hook to provide audio feedback. Use this skill to speak a short summary of what was accomplished. Use when this capability is needed.

tomevault-io Bundle

---

tomevault-io Bundle

Configure putior MCP Server

tomevault-io Bundle

---

tomevault-io Bundle

---

tomevault-io Bundle

---

tomevault-io Bundle

---

tomevault-io Bundle

Implement and validate save/load for train and rail systems under the current rail-segment-centric architecture and TrainUnit snapshot-sync model. Use when changing train save data, rail persistence, load order, docking restoration, or persistence tests. Use when this capability is needed.

tomevault-io Bundle

Dynamic spatial analysis skill for Revit Snapshots. Segregates project elements into architectural zones (East/West/Center) based on the model's actual bounding box extents rather than hardcoded coordinates. Use when this capability is needed.

tomevault-io Bundle

Golang struct and interface design patterns — composition, embedding, type assertions, type switches, interface segregation, dependency injection via interfaces, struct field tags, and pointer vs value receivers. Use this skill when designing Go types, defining or implementing interfaces, embedding structs or interfaces, writing type assertions or type switches, adding struct field tags for JSON/YAML/DB serialization, or choosing between pointer and value receivers. Also use when the user asks about "accept interfaces, return structs", compile-time interface checks, or composing small interfaces into larger ones. Use when this capability is needed.

tomevault-io Bundle

Use when you only need slide color systems, palette selection, or palette generation workflows and want direct pointers to the color design references.

tomevault-io Bundle

Extract insights from multi-agent interactions, identify patterns, and build collective intelligence through cross-agent learning and knowledge management. Use when synthesizing findings, building knowledge bases, or improving system-wide practices. Use when this capability is needed.

tomevault-io Bundle

Build a project using Claude Code Agent Teams with tmux split panes. Takes a plan document path and optional team size. Use when you want multiple agents collaborating on a build. Use when this capability is needed.

tomevault-io Bundle

Bracket of Death backend development with Node.js, Express, TypeScript, and MongoDB/Mongoose. Use when building API endpoints, models, controllers, services, or fixing backend issues. Knows project patterns, auth middleware, model conventions, and service patterns. Use when this capability is needed.

tomevault-io Bundle

This skill discovers relevant skills, agents, commands, and MCP tools by scanning project context and tool capabilities. This skill should be used when entering planning mode, starting work on a new codebase, or when the user asks "what tools should I use?" Auto-triggers with thorough-planning skill. Use when this capability is needed.

tomevault-io Bundle

Upgrade Triton-Ascend project based on upstream Triton project. This skill automates the version upgrade process, creates a new branch with upgraded code, and performs compilation and basic functionality tests. Use when this capability is needed.

tomevault-io Bundle

CopilotKit integration patterns for providers, runtime wiring, `useCoAgent`, `useCopilotAction`, `useLangGraphInterrupt`, shared state, and HITL with LangGraph. Use when building agent-native product UX. Use when this capability is needed.

tomevault-io Bundle

PMAT Deep Context Generation Skill

tomevault-io Bundle

PMAT Code Quality Analysis Skill

tomevault-io Bundle

Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration Use when this capability is needed.

tomevault-io Bundle

Use when working with the DecompilerServer MCP server to inspect, search, decompile, analyze, or compare .NET assemblies, especially foreign code such as Unity/RimWorld assemblies, third-party DLLs, game binaries, or version-to-version assembly diffs. Prefer this skill when choosing the right DecompilerServer tool sequence and avoiding premature shell fallbacks.

tomevault-io Bundle

Implements secure authentication patterns including login/registration, session management, JWT tokens, password hashing, cookie settings, and CSRF protection. Provides auth routes, middleware, security configurations, and threat model documentation. Use when building "authentication", "login system", "JWT auth", or "session management". Use when this capability is needed.

tomevault-io Bundle

Fetch active (unresolved) PR comments from GitHub and format them for LLM consumption. Use when user wants to review, respond to, or address PR feedback. Use when this capability is needed.

tomevault-io Bundle

Install session-level guardrails when the user hands off to autonomous overnight execution. Fires when the first user prompt contains "going to bed", "headed to sleep", "full autonomy", "overnight", "continue as you were", or similar handoff-to-autonomy language. Enforces commit-per-slice, halt-on-3-consecutive-errors, max-wall-time cap, and a wake-time summary block. Exists because audited overnight sessions showed 348 Bash calls and 9 tool errors with no structural brake — the user explicitly acknowledged errors were happening and told Claude to keep going, which is exactly the moment guardrails must exist in config instead of in the user's head. Use when this capability is needed.

tomevault-io Bundle

AI Agent UX

tomevault-io Bundle

Cursor AI 编辑器官方文档参考技能。When working with Cursor features, hooks, skills, MCP, CLI commands, rules, permissions, configuration, or any other Cursor internals — either when users ask OR when the Agent needs to know how something works. Fetch from https://cursor.com/docs as the authoritative source instead of relying on training data. Use when this capability is needed.