AI & ML

tomevault-io Bundle

Research web pages using agent-browser — a headless browser CLI that renders JavaScript and handles dynamic content. Use this skill as a fallback when WebSearch or WebFetch fails, returns insufficient results, or when the target page requires JS rendering (SPAs, dynamic docs). Also use when the user provides a specific URL to investigate, when you need to navigate multi-page documentation, or when summarizing web content that WebFetch cannot parse properly. Use when this capability is needed.

tomevault-io Bundle

Analyzes and improves CLAUDE.md or AGENTS.md files for clarity, structure, and effectiveness. Use when the user wants to review, refine, or optimize their agent instruction files.

tomevault-io Bundle

Multi-perspective AI consultation. Invoke with /tzurot-council-mcp for major refactors (>500 lines), structured debugging after failed attempts, or when a technical decision has multiple viable approaches. Use when this capability is needed.

tomevault-io Bundle

OpenClaw-native domain cascading. Use when users need cost/latency reduction via cascading, domain-aware model assignment, OpenClaw-native event handling, and command setup including /model cflow and optional /cascade stats commands. Use when this capability is needed.

tomevault-io Bundle

Build, configure, and operate ssh-tunnel-gateway (ssh-tunnel-server and ssh-tunnel-agent), including over-ssh mode and systemd deployment. Use when this capability is needed.

tomevault-io Bundle

Guide for adding new LLM models to Letta Code. Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update the model configuration. Covers models.json configuration, CI test matrix, and handle validation. Use when this capability is needed.

tomevault-io Bundle

Monitior technology trends (GitHub, etc.), contextualize them against the user's project, and autonomously verify them through installation and testing. Use when the user asks about trending repositories, new tools, or wants to stay updated on tech relevant to their current work. Use when this capability is needed.

tomevault-io Bundle

LLM integration patterns for Claude, GPT, Gemini, and Ollama. Activate for AI API integration, prompt engineering, token management, extended thinking, and multi-model orchestration. Use when this capability is needed.

tomevault-io Bundle

Checks reported bugs in a way that aligns with the project goals. Use when the user reports a possible bug Use when this capability is needed.

tomevault-io Bundle

Test-driven prompt optimization for polish.rs. Use this skill when you want to add test cases, run regression tests, optimize the polish prompt, or review prompt evolution history. Use when this capability is needed.

tomevault-io Bundle

Sub-Agents in Claude Code

tomevault-io Bundle

LiteLLM-RS MCP Gateway Architecture. Covers Model Context Protocol, JSON-RPC 2.0 implementation, multi-transport support (HTTP, SSE, WebSocket, Stdio), and permission system. Use when this capability is needed.

tomevault-io Bundle

Manage sub-agent delegation, handle task completion events, and coordinate multi-agent workflows. Use when this capability is needed.

tomevault-io Bundle

Use when facilitating a user story mapping session for a product, feature area, single activity, new persona, or cross-cutting feature. Orchestrates a Three Amigos agent team (Product Owner, Developer, QA) that debates via inter-agent messaging to produce a story map backbone, prioritised release slices, a walking skeleton, agreed Definitions of Done, and BDD readiness verdicts. Successive sessions incrementally build a single master story map file per product. Requires Claude Code agent teams (TeamCreate, SendMessage, named Agent teammates); not portable to runtimes without these tools.

tomevault-io Bundle

Typefully Skill

tomevault-io Bundle

Analyzing user intent and delegating tasks. Use when this capability is needed.

tomevault-io Bundle

Claude 스킬을 생성하거나 기존 스킬을 최신 spec에 맞게 업데이트한다. 스킬 만들어줘, 새 스킬 추가, 스킬 업데이트, 스킬 수정, generate-skills 요청 시 사용한다. Use when this capability is needed.

tomevault-io Bundle

使用本地 Bilibili RAG 服务进行检索与问答。用户询问 B 站收藏夹内容、视频要点总结、来源追溯、入库状态时使用。内容问答时优先通过 session_id 与 folder_ids 限定范围，避免空范围导致 fallback。 Use when this capability is needed.

tomevault-io Bundle

Activate when creating or modifying Claude Code agents with proper architecture patterns, tool selection, and extended context integration Use when this capability is needed.

tomevault-io Bundle

Upgrade vllm-omni NPU model runners (OmniNPUModelRunner, NPUARModelRunner, NPUGenerationModelRunner) to align with the latest vllm-ascend NPUModelRunner while preserving omni-specific logic. Use when this capability is needed.

tomevault-io Bundle

OmniRoute exposes a built-in MCP (Model Context Protocol) server with 37 tools (chat, embeddings, memory CRUD, skills, providers, routing, audit) over SSE/stdio/HTTP transports. Use when the user wants to add OmniRoute as an MCP server in Claude Desktop, Cursor, Cline, or any MCP-compatible client. Use when this capability is needed.

tomevault-io Bundle

Guide for configuring YAACLI CLI. Use this skill when users want to configure models, tools, subagents, custom commands, or other CLI settings. Covers both global and project-level configuration. Use when this capability is needed.

tomevault-io Bundle

Feature Specification Agent

tomevault-io Bundle

Create detailed research plans by decomposing structured prompts into subtopics, search strategies, and agent deployment configurations. Extracted from Phase 2 of research-executor for standalone planning capabilities. Use when this capability is needed.

tomevault-io Bundle

Guide commit message and PR creation for SDD workflow. Use when committing changes, creating pull requests, or documenting changes. Invoked via /sdd-commit. Use when this capability is needed.

tomevault-io Bundle

Create technical design specifications for SDD workflow. Use when designing architecture, defining components, or creating system design documents after requirements are approved. Invoked via /sdd-design <feature-name>. Use when this capability is needed.

tomevault-io Bundle

Perform thorough Linus-style code review focusing on correctness, maintainability, and adherence to project conventions. Use after completing implementation to ensure code quality. Invoked via /sdd-review [file-path or PR-number]. Use when this capability is needed.

tomevault-io Bundle

Write correct and idiomatic Typst code for document typesetting. Use when creating or editing Typst (.typ) files, working with Typst markup, or answering questions about Typst syntax and features. Focuses on avoiding common syntax confusion (arrays vs content blocks, proper function definitions, state management). Use when this capability is needed.

tomevault-io Bundle

Execute deep web research on any topic using Yutori's research agents. Use for competitive analysis, market research, finding documentation, or answering complex questions that require synthesizing information from multiple sources. Use when this capability is needed.

tomevault-io Bundle

Generates specialized, context-rich subagent prompts by exploring the codebase and gathering task-specific requirements

tomevault-io Bundle

Write specifications for AI agents using a specialized template and writing disciplines. Agent specs Use when this capability is needed.

tomevault-io Bundle

Guides setup and usage of the Zhin MCP (Model Context Protocol) server plugin. Covers configuration, available tools, resources, and prompts for AI assistant integration. Use when integrating Zhin with AI coding assistants like Claude or Cursor via MCP. Use when this capability is needed.

tomevault-io Bundle

Transfer USDC between agent wallets on Base chain. Direct on-chain settlement for agent-to-agent payments without ZKP2P escrow. Use when the user wants to send USDC to another agent, transfer tokens, or settle agent-to-agent payments. Use when this capability is needed.

tomevault-io Bundle

Design, structure, and optimize the context you give AI coding agents. Covers system prompts, repo-level context files (CLAUDE.md, AGENTS.md, COPILOT-INSTRUCTIONS.md), what to include vs. exclude, MCP as just-in-time context, sub-agent context scoping, and treating context like code — versioned, tested, and reusable. Improves agent trust, speed, and code quality. Grounded in LeadDev and industry practice. Use when this capability is needed.

tomevault-io Bundle

Pi Network payment integration - three-phase payment flow, createPayment, server-side approve/complete, PaymentDTO. Use when implementing or debugging Pi payments. Use when this capability is needed.

tomevault-io Bundle

Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt. Use when this capability is needed.