AI & ML

tomevault-io Bundle

Guide for developing the Agent Lens VS Code extension. Use when creating or modifying extension code, webviews, tree views, or commands. Use when this capability is needed.

tomevault-io Bundle

Real-time crypto, equities, macro, and financial market news aggregator — 84+ data sources across 6 categories covering digital assets, U.S. stocks, semiconductors, AI infrastructure, supply chains, commodities, rates, policy, and market-moving social/news signals. Sources include Bloomberg, Reuters, FT, CNBC, CoinDesk, Twitter/X, Binance, Coinbase, OKX, whale/KOL trades, price/funding/liquidation alerts, and 12 AI prediction signals. AI-analyzed with impact score, trading signals, and bilingual summaries. **Free tools available without token**. Use when this capability is needed.

tomevault-io Bundle

Guides implementation of the What-If scenario simulation engine in WealthScope. Use when building scenario analysis, portfolio impact calculations, or conversational financial simulations. Covers prompt engineering, result parsing, and UI presentation. Use when this capability is needed.

tomevault-io Bundle

Control JetBrains IDE (IntelliJ, WebStorm, PyCharm) via MCP. Use when manipulating IDE files, running configurations, searching code, or performing refactoring. Triggers on "open in IDE", "run configuration", "refactor code", "IDE search", "JetBrains". Use when this capability is needed.

tomevault-io Bundle

Orchestrate complex multi-agent workflows - sequential, parallel, conditional, and loop patterns Use when this capability is needed.

tomevault-io Bundle

Create a delegation-ready plan executable by a faster, less capable AI model. Use when this capability is needed.

tomevault-io Bundle

PyQt5-based GUI chat window for LLM conversations with streaming responses and stop functionality. Use when working with pywayne.llm.chat_window module to create desktop chat applications with customizable window configuration, system message management, and real-time streaming display. Use when this capability is needed.

tomevault-io Bundle

RAG Engineer

tomevault-io Bundle

Understand where FAF works - Claude Code (CLI + Skills), claude-faf-mcp (Desktop + MCP), vs claude.ai (web - file upload only). Explains faf-cli vs MCP differences, when to use each platform. Use when user asks "does FAF work with", "CLI vs MCP", "Claude Desktop vs claude.ai", or platform compatibility questions. Use when this capability is needed.

tomevault-io Bundle

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases. Use when this capability is needed.

tomevault-io Bundle

Prompt Engineer

tomevault-io Bundle

用户提供 SillyTavern 角色卡（PNG/JSON）并要求转换、迁移、移植到 pi coding agent 时使用；覆盖纯 prompt、世界书、MVU、骰子、战斗、好感度、经济、隐藏信息、多 agent 场景。 Use when this capability is needed.

tomevault-io Bundle

Code Reviewer

tomevault-io Bundle

Route the current job to the right Codeflow surface without overclaiming hosted, write-capable MCP, or published plugin support. Use when this capability is needed.

tomevault-io Bundle

LLM Memory 使用指南

tomevault-io Bundle

Get detailed information about a specific GitHub pull request. Use when the user wants to see PR details, check PR status, or view PR metadata. Use when this capability is needed.

tomevault-io Bundle

Performs independent self-review of completed work to catch issues before they become problems. The agent invokes this skill when completing tasks, reviewing changes, or validating quality. Use when this capability is needed.

tomevault-io Bundle

Create project-specific steering documents for SDD workflow. Use when setting up project context, documenting technology stack, or establishing project conventions. Invoked via /sdd-steering. Use when this capability is needed.

tomevault-io Bundle

Generate comprehensive tests following TDD methodology. Creates unit tests, integration tests, and edge case coverage. Works with existing test frameworks in the project. Invoked via /sdd-test-gen [file-path or function-name]. Use when this capability is needed.

tomevault-io Bundle

Capture and transfer **session context** when delegating work from one agent to another.

tomevault-io Bundle

Guide for using Ava's MCP tools effectively for task management and progress reporting. Use when working with Ava MCP server to report progress on coding tasks, including starting tasks, updating progress, reporting blockers, and completing tasks. Helps users understand best practices for privacy-conscious task reporting with minimal effort. Use when this capability is needed.

tomevault-io Bundle

Agent Spec Tool-First Workflow

tomevault-io Bundle

Guides database usage in Zhin including model definitions, CRUD queries, transactions, migrations, and lifecycle hooks. Covers the built-in ORM based on @zhin.js/database with SQLite support. Use when working with data persistence in Zhin plugins. Use when this capability is needed.

tomevault-io Bundle

§8 TOOL REFERENCE & WIND TABLE

tomevault-io Bundle

Build structures in Minecraft with AI agents. Your agent gets a helper bot that autonomously assists the Claude agents! Use when this capability is needed.

tomevault-io Bundle

Run self-diagnostics on Cornelius agent to verify skills, commands, agents, and integrations are working. Use when troubleshooting, after configuration changes, or for regular health checks. Use when this capability is needed.

tomevault-io Bundle

Audit Codex AGENTS.md and AGENTS.override.md instruction files in the current project for staleness and coverage gaps. Scores freshness with git churn, flags content drift, discovers directories that may deserve scoped AGENTS.md guidance, and reports ranked findings with per-file approval before edits. Global and project-agnostic. Trigger when the user says "audit AGENTS.md", "audit agent docs", "audit-agent-docs", "are my AGENTS.md files up to date", "check if AGENTS.md is stale", "Codex docs health check", or "refresh agent docs". SKIP when the user only wants to create a new AGENTS.md from scratch or only wants placement recommendations (use where-agents-md instead). Use when this capability is needed.

tomevault-io Bundle

This skill should be used to execute work plans with strict coding discipline that avoids common LLM mistakes. It merges structured plan execution (phased workflow, incremental commits, quality checks) with disciplined coding guardrails (assumption surfacing, simplicity-first, surgical changes, test-driven execution). Triggers on /disciplined-work, /k-work, "disciplined work", or "careful work". Use when this capability is needed.

tomevault-io Bundle

Persist agent state across runs, shape what the LLM sees per turn, and cap history to fit a context window. Covers `KnowledgeStore` (memory / sqlite / disk / redis), `KnowledgeConfig` (`store=`, `compact=`, `aggregate=`, `bootstrap=`), aggregation strategies (`WorkingMemoryAggregate`, `ConversationSummaryAggregate`), assembly policies (`WorkingMemoryPolicy`, `EpisodicMemoryPolicy`, `ConversationPolicy`, `SlidingWindowPolicy`, `TokenBudgetPolicy`, `AlertPolicy`), and compaction (`TailWindowCompact`, `SummarizeCompact`). Use when the user wants the agent to remember between conversations, manage long histories, or control prompt assembly. Use when this capability is needed.

tomevault-io Bundle

协调各种编码工具（如 Claude Code、Codex、Cursor、Gemini Code 或任何基于 CLI 的编码工具），以实现实施任务的最大吞吐量。适用场景包括：(1) 编写或修改代码文件；(2) 运行脚本或数据管道；(3) 批量处理大型数据集；(4) 需要并行执行的多阶段工作流程。该方案涵盖了与具体工具无关的调度模板、任务分解、并行协调以及任务完成标准。不适用场景包括：简单的文件读取操作、仅涉及配置的修改，或发送消息。核心原则是：编排器负责规划任务，编码工具负责执行具体操作。 Use when this capability is needed.

tomevault-io Bundle

Working with OpenBench data layer - vector stores, chunking, embeddings, and RAG patterns. Use when implementing PineconeStore, chunking documents, generating embeddings, or building RAG workflows. Use when this capability is needed.

tomevault-io Bundle

This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems. Use when this capability is needed.

tomevault-io Bundle

Core JavaScript development standards covering ES modules, modern patterns, code quality, async programming, and tooling Use when this capability is needed.

tomevault-io Bundle

Agent Instructions Skill

tomevault-io Bundle

Create an E2E lifecycle test for a new health platform issue in test/new-e2e/tests/agent-health/ Use when this capability is needed.

tomevault-io Bundle

Control a Windows machine remotely via MCP protocol. 40 tools for desktop automation, system management, file operations, and more. Use when this capability is needed.