AI & ML

tomevault-io Bundle

Metal GPU Code Skill

tomevault-io Bundle

当用户想「创建/生成一个 workflow(可复用的多子-agent 编排脚本)」时使用。讲清 deepx workflow 的 JavaScript 脚本格式、可用 API,以及如何用 Workflow 工具保存与运行。 Use when this capability is needed.

tomevault-io Bundle

Add Agent Skill

tomevault-io Bundle

Flutter

tomevault-io Bundle

Detect and use llms.txt files for LLM-optimized documentation. Use when checking if a site has LLM-ready docs before scraping. Use when this capability is needed.

tomevault-io Bundle

CytoScnPy MCP Server

tomevault-io Bundle

Build or adapt Oak Curriculum API learning experiences, especially child-facing Apps SDK flows. Use when the user wants Oak endpoints or curriculum data turned into guided learning interactions with age-appropriate guardrails. Use when this capability is needed.

tomevault-io Bundle

Gemini CLI invocation patterns for code and design reviews. Defines standard flags, prompt templates, and skip conditions. Preferred over codex-review when both CLIs are installed. Use when spawning ext-review agents. Use when this capability is needed.

tomevault-io Bundle

Real Claude vs GPT multi-round debate. Use when you need a second opinion, want to debate architecture decisions, or evaluate competing approaches with multi-model collaboration. Use when this capability is needed.

tomevault-io Bundle

Use when working with the missing todo list for AI agents. Your agent has memory, cron jobs, and chat — but no way to say 'do this when you get to it.' clawdo is a persistent task queue that works in heartbeats, cron, pipes, and conversations. add → inbox → start → done.

tomevault-io Bundle

All your tools. None of your passwords. Use Danube's API tools (Gmail, GitHub, Notion, etc.) through MCP. Search for tools, check authentication, execute with parameters, and handle errors gracefully. Use when this capability is needed.

tomevault-io Bundle

Use when operating the Codex delegation MCP server and tools (delegate.spawn, delegate.question.*, delegate.cancel, github.merge confirmation flow), or when configuring delegation mode/tool_profile with delegation MCP enabled by default.

tomevault-io Bundle

Generate images through OpenAI-compatible /v1/images/generations APIs such as gpt-image-2, custom proxy endpoints, or self-hosted image gateways. Use when the user asks to test an image-generation endpoint, adapt a script to a base URL/API key/model, generate one or many images from prompts, or package a reusable OpenAI-compatible image generation workflow. Use when this capability is needed.

tomevault-io Bundle

Control and test terminal applications with the termctrl CLI by reading visible screen state, driving named live sessions, sending typed keyboard input, waiting for text, collecting explicit evidence, recording timelines, marking important moments, and exporting edited videos. Use when an agent must operate or verify a TUI, REPL, interactive CLI, shell process, OpenTUI application, or other terminal-backed workflow. Use when this capability is needed.

tomevault-io Bundle

agent-browser

tomevault-io Bundle

Setup MCP

tomevault-io Bundle

Automatically reduce code complexity in any repository (Python/Rust) through deterministic sensing, LLM-driven refactoring, and multi-gate verification. Use when this capability is needed.

tomevault-io Bundle

Create and manage AI agent sessions with multiple backends (SDK, Claude CLI, Codex, Cursor). Also supports multi-agent workflows with shared context, @mention coordination, and collaborative voting. Use for "start agent session", "create worker", "run agent", "multi-agent workflow", "agent collaboration", "test with tools", or when orchestrating AI conversations programmatically. Use when this capability is needed.

tomevault-io Bundle

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model. Use when this capability is needed.

tomevault-io Bundle

Refresh the managed Spec Kit section in the coding agent context file Use when this capability is needed.

tomevault-io Bundle

HTTP MCP Header Secret Support - Implementation Summary Use when this capability is needed.

tomevault-io Bundle

Multi-agent orchestration over a shared SQLite event queue. Use when this capability is needed.

tomevault-io Bundle

Mandatory: Use the Search Agent

tomevault-io Bundle

Add agent-first observability to code — structured logs, health endpoints, failure-state persistence, and explicit failure modes — so the next agent hitting a problem at 3am has the signals it needs to diagnose. Use when asked to "add logging", "add observability", "add metrics", "debug later", "make this observable", or when building/refactoring a subsystem that will run unattended (auto-mode engine, background jobs, servers, watchers). Operationalizes VISION.md's "agent-first observability" principle. Use when this capability is needed.

tomevault-io Bundle

Elfiee MCP Tools

tomevault-io Bundle

Comprehensive AI risk management, EU AI Act compliance, and LLM usage governance Use when this capability is needed.

tomevault-io Bundle

Use when you need to fine-tune(ファインチューニング) and optimize LangGraph applications based on evaluation criteria. This skill performs iterative prompt optimization for LangGraph nodes without changing the graph structure.

tomevault-io Bundle

---

tomevault-io Bundle

This skill should be used when the user asks to "test the harness", "run integration tests", "validate features with real API", "test with real model calls", "run agent loop tests", "verify end-to-end", or needs to verify OpenHarness features on a real codebase with actual LLM calls. Use when this capability is needed.

tomevault-io Bundle

Build LLM apps, RAG systems, and prompt pipelines. Use for AI-powered features. Use when this capability is needed.

tomevault-io Bundle

Actor model expert covering message passing, state isolation, supervision trees, deadlock prevention, fault tolerance, Actix framework, and Erlang-style concurrency patterns. Use when this capability is needed.

tomevault-io Bundle

Use when a user gives one or many WeChat or Xiaohongshu links and wants the parsed notes saved to a specific local path without relying on the Obsidian plugin UI. This skill wraps the repository's import capability as a direct agent tool through the bundled script, including batch import, frontmatter generation, media download, and JSON result reporting.

tomevault-io Bundle

Use when finishing work in a repository that has agent-md installed; runs the declared checks, updates memory/progress.md, and reports concrete verification evidence instead of self-grading.

tomevault-io Bundle

Guide for adding a new dataset loader to AReaL. Use when user wants to add a new dataset. Use when this capability is needed.

tomevault-io Bundle

Format, lint, vet, validate config, and test the `llm-proxy` Go service. Runs `gofmt -s`, `gofumpt`, `go vet`, the config validator, and the race-enabled unit test suite — the same checks CI's `lint` and `unit-tests` jobs enforce. Use when the user says "format", "lint", "check", "gofmt", "gofumpt", "go vet", "run checks", "pre-commit checks", "CI checks", "/format-lint-generate", or pastes the "Go code is not formatted:" CI failure. Use when this capability is needed.

tomevault-io Bundle

CodeRabbit