AI & ML

tomevault-io Bundle

根據 Git Repository 的風格建立 Commit。當使用者要求，或 Agent 需要建立 Commit 時，必須使用此技能。 Use when this capability is needed.

tomevault-io Bundle

Use as the Soho project-start/context-engineering skill when starting a new project, major spec, PRP, architecture brief, agent handoff, or workflow that must keep durable project markdown surfaces aligned, including AGENTS.md, CLAUDE.md, CODEX.md, README.md, ARCHITECTURE.md, PLANNING.md, TASK.md, lessons.md, docs/specs, docs/plans, docs/receipts, Linear, and issue-tracker or handoff notes. Use when this capability is needed.

tomevault-io Bundle

Creates comprehensive, detailed lesson plans for AI/prompt engineering classes. Use when the user asks to create a new lesson, develop class content, or needs a detailed teaching plan for a session. Generates minute-by-minute breakdowns with activities, differentiation, and assessment.

tomevault-io Bundle

Builds advanced RAG (Retrieval-Augmented Generation) pipelines with LangChain, multiple retrievers, and document chains.

tomevault-io Bundle

Create (or update) and validate Agent SOPs (Standard Operating Procedures) - markdown-based workflows that guide AI agents through complex, multi-step tasks with RFC 2119 constraints. Use when this capability is needed.

tomevault-io Bundle

MCP server for Productive.io - use with Claude Desktop or MCP-compatible clients for time tracking, projects, and tasks Use when this capability is needed.

tomevault-io Bundle

Inspect the Linear SDK and generated GraphQL types before adding or changing a Linear capability in mcp-linear. Use this when you need to confirm available entities, methods, enums, or input shapes. Use when this capability is needed.

tomevault-io Bundle

Use when finding new AI agent skills, discovering capabilities, installing skills from GitHub, searching skill marketplaces, or expanding what Claude can do - like Neo downloading martial arts in The Matrix

tomevault-io Bundle

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' '... Use when this capability is needed.

tomevault-io Bundle

Write idiomatic Ruby code with metaprogramming, Rails patterns, and performance optimization. Specializes in Ruby on Rails, gem development, and testing frameworks. Use when this capability is needed.

tomevault-io Bundle

Example TaskFlow authoring pattern for inbox triage. Use when messages need different treatment based on intent, with some routes notifying immediately, some waiting on outside answers, and others rolling into a later summary. Use when this capability is needed.

tomevault-io Bundle

Create specialized OpenCode agents with proper configuration for primary agents and subagents. Use when the user wants reusable OpenCode agent profiles, needs `agent/*.md` files or `opencode.jsonc` agent entries, wants to configure prompts/models/tool access, or needs to split work between a primary agent and subagents safely. Use when this capability is needed.

tomevault-io Bundle

Create or improve AGENTS.md/CLAUDE.md files for AI coding agents. Use when setting up a new project for AI assistance, auditing an existing rules file, or when the user asks about best practices for agent instructions. Use when this capability is needed.

tomevault-io Bundle

Generates a Spotify playlist candidate list from `duration_minutes` and `mood_vibe`. Set `create_playlist=true` to create the playlist in the current user's Spotify account.

tomevault-io Bundle

程式碼重構技能

tomevault-io Bundle

MLX Swift LM - Run LLMs and VLMs on Apple Silicon using MLX. Covers local inference, streaming, wired memory coordination, tool calling, LoRA fine-tuning, embeddings, and model porting. Use when this capability is needed.

tomevault-io Bundle

Create, sign, and verify Modality contracts for trustless agent cooperation. Use when an agent needs to establish a binding agreement with another agent, delegate a task with enforceable terms, verify a contract's protections, or participate in a multi-party contract. Handles escrow, task delegation, data exchange, multisig, and custom contract patterns. Use when this capability is needed.

tomevault-io Bundle

Generate AI music videos from melody audio + photo + prompt. Local Use when this capability is needed.

tomevault-io Bundle

Fix, explore, and refactor the crocbot codebase safely using Claude Code as a high-thinking-budget sub-agent. Use when the user requests codebase repairs, complex refactors, or deep exploration of the crocbot project structure. Use when this capability is needed.

tomevault-io Bundle

Deep reference on Code Puppy's internal architecture — agents, tools, plugins, models, MCP, sessions, and how to extend it correctly. Use when this capability is needed.

tomevault-io Bundle

Detailed test patterns and code examples. Use when you need step-by-step testing guidance, Server Bridge Pattern, or concrete code patterns beyond what the auto-loaded testing rules provide. Use when this capability is needed.

tomevault-io Bundle

Dart ile çok platformlu (minimal RAM) Edge Workflow Agent runtime’ını (YAML job engine + BLE + local KV + sadece MQTT) scaffold etmek, güncellemek ve doğrulamak için kullan. Use when this capability is needed.

tomevault-io Bundle

Demo Skill

tomevault-io Bundle

Write comprehensive meeting summaries with action items from meeting notes, transcripts, or agendas. Automatically fulfills actionable tasks using available tools discovered from TECH.md (MCP servers, APIs, local scripts) and provides guidance for manual tasks. Use when creating meeting summaries, extracting action items, or preparing agendas for upcoming meetings by reviewing past summaries. Use when this capability is needed.

tomevault-io Bundle

AI-agent-driven browser automation (long autonomous sessions, Browserbase-capable). Use when the user needs to interact with websites across many steps, automate complex browser tasks, or run unattended flows. Triggers include 'open a website', 'fill out a form', 'automate browser actions', 'login to a site', or any task requiring programmatic web interaction. NOT for manual E2E test generation (see mk:qa-manual); NOT for deterministic scripted flows (see mk:playwright-cli). Use when this capability is needed.

tomevault-io Bundle

Go Implementation

tomevault-io Bundle

Manage MCP servers in Nuxt with @nuxtjs/mcp-toolkit — setup, create tools/resources/prompts, organize with handlers, build interactive MCP Apps, add elicitation/logging/sessions, review, and troubleshoot. Use when this capability is needed.

tomevault-io Bundle

nemo-retriever

tomevault-io Bundle

Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or discussing skill capabilities. Use when this capability is needed.

tomevault-io Bundle

MCPサーバーの「Light版」を生成する。descriptionを1行に圧縮し、ベストプラクティスをAgent Skillとして分離する。Use when user asks to "MCP Light版を作って", "MCPを軽量化", "Light MCP", "mcp-light", "create light mcp", "compress mcp descriptions", "MCP description圧縮", or wants to reduce MCP tool definition token usage. Use when this capability is needed.

tomevault-io Bundle

Universal environment variable loader for AI agent environments. Loads secrets and config from Claude.ai, Claude Code, OpenAI Codex, Jules, and standard .env files. Use when this capability is needed.

tomevault-io Bundle

Review corporate governance practices and board composition from SEC filings using Octagon MCP. Use when researching board structure, director qualifications, committee composition, governance policies, shareholder rights, and related party transactions from proxy statements. Use when this capability is needed.

tomevault-io Bundle

Run multi-agent panel audits on codebases. Use when evaluating code quality, running board reviews, or scoring projects against configurable criteria. Triggers on "audit", "evaluate", "review", "score", "panel", "board". Use when this capability is needed.

tomevault-io Bundle

Create new high-quality agent skills with a standalone, repeatable workflow (no dependency on other skills). Use when you want to go from a vague skill idea → narrow scope → extract expert frameworks → write SKILL.md + examples/evals/index/changelog artifacts → self-validate with test prompts. Use when this capability is needed.

tomevault-io Bundle

Guidelines for selecting appropriate language models for agents based on task-specific benchmarks, availability, and cost efficiency. Use when this capability is needed.

tomevault-io Bundle

Standard workflow for GitHub Copilot coding agents including report_progress usage, delegation handling, and PR communication patterns. Use when this capability is needed.