Communitygithub.com

Itô 计算

查询实时 GPU 库存、提交经过身份验证的 Itô 固定价格询价单 (RFQ)、检查 RFQ 或采购状态、撤销设备凭证,并通过单独安装的规范 CLI 运行显式门控的节点资格验证。

Itô 计算 是什么?

Itô Compute 技能提供了一个规范的客户端接口,用于与 Itô GPU 计算市场进行交互。它通过 ECC 代理或 MCP 服务器操作,允许用户查询实时 H100/H200 容量、提交固定价格询价单 (RFQ)、检查这些 RFQ 或现有采购订单的状态,以及撤销设备凭证。该技能还包括一个用于实时 GPU 节点资格验证的“evals”命令,这依赖于单独安装的 `sixtytwo-cli`。重要的是,该技能不执行任何浏览器自动化、不运行工作负载、不提供推理服务,也不代表用户进行购买。它作为与 Itô 市场进行受控互动的网关,强调每一步都需要明确的操作者授权,从提交 RFQ 到接受报价。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/ECC/tree/main/skills/ito-compute

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

Itô 计算 是做什么的?

使用规范的 Itô 计算 CLI 或 MCP 服务器。ECC 不实现并行客户端、本地模拟、预留、工作负载运行器或推理服务器。ECC 本身不进行任何浏览器自动化。

安装规范本地包

ito-compute-cli 目前尚未发布。请从其规范仓库构建,而不是使用 npx、npm exec 或未经验证的包:

git clone https://github.com/Ito-Markets/ito-cloud-runtime.git
cd ito-cloud-runtime/cli/ito-compute-cli
npm ci
npm run check

将 ECC_ITO_CLI_EXECUTABLE 设置为显式的绝对构建入口:

/absolute/path/to/ito-cloud-runtime/cli/ito-compute-cli/dist/bin/ito.js

ECC 永远不会通过 PATH 发现此承载凭证的客户端。 ecc ito login 执行设备授权,并且永远不会继承 ITO_API_KEY。 仅用于验证的 auth,以及 find 和 status,在配置时会直接转发 ITO_API_KEY;不需要 ITO_AUTH_MODE=legacy。切勿将密钥或令牌放在参数、跟踪文件、MCP 结果、日志或聊天中。

CLI 工作流程

  1. 在第一次操作之前运行 ecc ito login。ECC 将其委托给规范 CLI 的设备授权,该授权默认打开 Itô 验证页面并将设备令牌持久化到 macOS 钥匙串。使用 ecc ito login --no-browser 来抑制页面切换。ECC 本身不进行浏览器自动化。如果发起代理无法完成已登录的浏览器步骤,请将确切的命令交给用户;批准完成后,返回原始任务并继续使用 ecc ito auth。 设备令牌默认使用 macOS 钥匙串。文件令牌回退是显式的,其目录和令牌文件必须保持仅所有者可访问(0700 和 0600)。

  2. 运行 ecc ito auth 以验证现有凭据;它从不启动登录,并拒绝 --no-browser。

  3. 在 ecc ito find 之前,获取明确的买家授权以提交 RFQ。

    • 需要 gpu、count、整数 days、max-rate、nodes、 gpus-per-node、storage-tb、start-window、form-factor、 contract-type、fabric、region 以及拆分填充决定。
    • 要求 count == nodes * gpus-per-node;切勿推导拓扑。
    • 仅当买家明确接受任何 fabric 或 region 时,才使用 any。
    • 省略的 --allow-split 表示 false。
  4. 运行实时 RFQ 命令:

    ecc ito find \
      --gpu h200 \
      --count 8 \
      --nodes 1 \
      --gpus-per-node 8 \
      --days 30 \
      --storage-tb 1 \
      --start-window 2099-08-15 \
      --max-rate 3.00 \
      --form-factor bare_metal \
      --contract-type reservation \
      --fabric infiniband \
      --region us-east-1
    
  5. 运行 ecc ito status 以检查 RFQ 和采购订单。 在发生模糊的传输故障后,在重复执行 find 之前先检查状态。

  6. 当报价准备就绪并且买家明确批准时,接受它:

    ecc ito accept rfq_<ticket-id>
    

    这将把工单路由到服务台进行人工审核。它不会转移资金或预留容量。未经明确的买家授权,请勿接受。

  7. 当用户明确要求撤销此设备时,运行 ecc ito logout。 规范 CLI 在远程撤销失败时会保留本地凭据,以便操作员可以重试;切勿手动删除令牌作为替代。

库存价格仅供参考。RFQ 不是预留容量。仅当规范结果包含非空固定报价时,才将费率视为固定。

实时节点资格验证

ecc ito evals 将规范 CLI 的窄实时适配器暴露给单独安装的 sixtytwo-cli==0.3.33。它不通过 ECC 暴露本地夹具执行。 在调用它之前,需要满足以下所有条件:

  • 操作员授权联系指定的节点;
  • ITO_ENABLE_SIXTYTWO_LIVE=1;
  • --live-sixtytwo;
  • 显式的节点列表;以及
  • 包含 sixtytwo.yaml 的现有绝对配置目录。
ecc ito evals \
  --cluster clu_prod_example \
  --live-sixtytwo \
  --nodes gpu-01,gpu-02 \
  --config-dir /absolute/path/to/qualification-config

规范适配器只能针对显式节点运行固定版本检查和 sixtytwo test --full。它无法租用、启动、恢复、修复、重置、购买或订购资源。ECC 不会将 ITO_API_KEY 或模型/云凭据转发到节点资格验证。

MCP 工作流程

构建规范包,然后使用绝对路径配置 stdio 服务器:

{
  "mcpServers": {
    "ito-compute": {
      "command": "node",
      "args": [
        "/absolute/path/to/ito-cloud-runtime/cli/ito-compute-cli/dist/bin/ito-mcp.js"
      ]
    }
  }
}

该服务器仅暴露:

  • ito_auth
  • ito_find
  • ito_status
  • ito_accept

ito_auth 验证现有凭据;它不启动设备登录。使用 ito_auth,收集明确的买家授权和所有硬性约束,调用 ito_find,然后在需要时轮询 ito_status。当报价准备就绪并且买家明确批准时,使用工单 ID 调用 ito_accept。服务台报价通常仅供参考且不具有约束力,直到服务台确认;结果中带有 quote_class。

租赁或购买语义

find 提交 RFQ 并可能返回固定报价,但它不租用、购买、预留、配置或转移资金。accept 将报价路由到服务台进行人工审核;它不转移资金或预留容量。status 是只读的,尽管提供者端点可能会协调现有的采购订单。ECC 帮助中的被动仪表板链接是一个单独的用户操作的 Web 路由;不要打开或操作它作为缺少 CLI 功能的替代。

不支持的操作

支持的客户端表面无法锁定报价、预留容量、执行工作负载或提供推理服务。accept 是服务台交接,而不是购买。MCP 服务器不暴露资格验证;请使用上面的显式 CLI 命令。当本地 CLI 缺失或实时操作失败时,不要发明额外的工具或购买路径。不要用浏览器或夹具替代。报告缺失的功能并停止。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

affaan-m/content-engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

affaan-m/ECC

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

affaan-m/fal-ai-media

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

affaan-m/manim-video

日本語翻訳:このファイルは manim-video 用の日本語翻訳が必要です

affaan-m/remotion-video-creation

Remotion のベストプラクティス - React で動画を作成する。3D、アニメーション、音声、字幕、チャート、トランジションなどをカバーするドメイン固有の29のルール。

affaan-m/video-editing

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent

agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

agent-payment-x402

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

agent-self-evaluation

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

agent-sort

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

ai-first-engineering

Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, review gates, or ownership rules for a codebase largely written by agents.

ai-regression-testing

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change.

android-clean-architecture

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns. Use when structuring modules, layers, or data flow in an Android or KMP project.

angular-developer

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.

相关技能