Communitygithub.com

itô-compute

查詢即時 GPU 庫存、提交已認證的 Itô 固定費率報價請求、檢查報價或採購狀態、撤銷裝置憑證,並透過獨立安裝的標準 CLI 執行明確限定的節點驗證。當使用者要求尋找 H100/H200 容量、請求固定運算費率、檢查 Itô 運算狀態、驗證 GPU 節點、撤銷 Itô 存取權限,或租用/購買 GPU 運算資源並需要了解支援範圍時使用。

itô-compute 是什麼?

這個技能提供了一個完整的介面,用以管理 Itô 市場上的 GPU 運算資源。它封裝了標準的 Itô CLI 工具,讓 AI 代理可以查詢即時 GPU 庫存(H100/H200)、提交固定費率的報價請求(RFQ)、檢查 RFQ 與採購訂單狀態、以及撤銷裝置憑證。技能不會自行實作租用、購買、保留、或執行工作負載等操作,而是將這些操作委派給標準 CLI 處理。使用者必須先完成裝置授權登入(`ecc ito login`),然後才能進行後續操作。支援兩種工作流程:命令列介面(CLI)與 MCP 伺服器。CLI 流程涵蓋了登入、認證、尋找資源、接受報價與登出;MCP 伺服器則僅提供 `ito_auth`、`ito_find`、`ito_status` 與 `ito_accept` 四個工具。此外,還支援 `ecc ito evals` 命令,可透過獨立安裝的 `sixtytwo-cli` 對指定 GPU 節點進行即時驗證。技能會確保所有操作都需取得使用者的明確授權,並且不會執行任何未經支援的替代動作。

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

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

Itô Compute

使用標準的 Itô 運算 CLI 或 MCP 伺服器。ECC 不會實作並行用戶端、本地模擬、保留、工作負載執行器或推理伺服器。ECC 本身不會進行任何瀏覽器自動化。

安裝標準的本地套件

ito-compute-cli 目前尚未發布。請從其標準儲存庫建置,而不要使用 npx、npm exec 或未經驗證的套件:

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

將 ECC_ITO_CLI_EXECUTABLE 設定為明確的絕對建置入口路徑:

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

ECC 絕不會透過 PATH 發現這個持有憑證的用戶端。ecc ito login 執行裝置授權,且絕不會繼承 ITO_API_KEY。僅用於驗證的 auth,以及 find 和 status,會在設定 ITO_API_KEY 時直接轉發;不需要 ITO_AUTH_MODE=legacy。絕對不要將金鑰或令牌放入引數、追蹤檔案、MCP 結果、日誌或對話中。

CLI 工作流程

  1. 在首次操作之前執行 ecc ito login。ECC 將此委派給標準 CLI 的裝置授權,該授權預設會開啟 Itô 驗證頁面,並在 macOS 鑰匙圈中持久化一個裝置令牌。使用 ecc ito login --no-browser 來抑制頁面交接。ECC 本身不會進行任何瀏覽器自動化。如果發起代理無法完成已登入的瀏覽器步驟,請將確切的命令交給使用者;在批准完成後,返回原始任務並繼續執行 ecc ito auth。裝置令牌預設使用 macOS 鑰匙圈。檔案令牌回退是明確的,其目錄和令牌檔案必須保持僅擁有者可存取(0700 和 0600)。

  2. 執行 ecc ito auth 來驗證現有憑證;它絕不會啟動登入,且拒絕 --no-browser。

  3. 在 ecc ito find 之前,取得買方提交 RFQ 的明確授權。

    • 需要 gpu、count、整數 days、max-rate、nodes、 gpus-per-node、storage-tb、start-window、form-factor、 contract-type、fabric、region,以及分割填單的決定。
    • 需要 count == nodes * gpus-per-node;絕不要推導拓撲。
    • 僅在買方明確接受任何 fabric 或 region 時使用 any。
    • 省略 --allow-split 表示 false。
  4. 執行即時 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. 執行 ecc ito status 來檢查 RFQ 和採購訂單。在發生不明確的傳輸故障後,請先檢查狀態再重複執行 find。

  6. 當報價準備就緒且買方明確批准時,接受它:

    ecc ito accept rfq_<ticket-id>
    

    這會將工單轉送給專人審查。它不會移動資金或保留容量。未經明確買方授權請勿接受。

  7. 當使用者明確要求撤銷此裝置時,執行 ecc ito logout。當遠端撤銷失敗時,標準 CLI 會保留本地憑證,以便操作員可以重試;絕不要手動刪除令牌作為替代方案。

庫存價格僅供參考。RFQ 不是保留容量。僅當標準結果包含非空的確定報價時,才將費率視為固定。

即時節點驗證

ecc ito evals 將標準 CLI 的狹義即時轉接器暴露給獨立安裝的 sixtytwo-cli==0.3.33。它不會透過 ECC 暴露本地 fixture 執行。 在調用它之前,需要滿足以下所有條件:

  • 操作員授權聯絡指定的節點;
  • ITO_ENABLE_SIXTYTWO_LIVE=1;
  • --live-sixtytwo;
  • 明確的節點列表;以及
  • 一個包含 sixtytwo.yaml 的現有絕對配置目錄。
ecc ito evals \
  --cluster clu_prod_example \
  --live-sixtytwo \
  --nodes gpu-01,gpu-02 \
  --config-dir /absolute/path/to/qualification-config

標準轉接器只能執行固定的版本檢查和 sixtytwo test --full 針對明確的節點。它不能租用、啟動、恢復、修復、重置、購買或訂購資源。ECC 不會將 ITO_API_KEY 或模型/雲端憑證轉發到節點驗證中。

MCP 工作流程

建置標準套件,然後使用絕對路徑配置 stdio 伺服器:

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

伺服器僅暴露:

  • ito_auth
  • ito_find
  • ito_status
  • ito_accept

ito_auth 驗證現有憑證;它不會啟動裝置登入。使用 ito_auth,收集明確的買方授權和所有硬性限制,呼叫 ito_find,然後在需要時輪詢 ito_status。當報價準備就緒且買方明確批准時,使用工單 ID 呼叫 ito_accept。專人報價通常僅供參考,在專人確認之前不具約束力;結果中會包含 quote_class。

租用或購買語意

find 提交 RFQ 並可能返回確定報價,但它不租用、購買、保留、配置或移動資金。accept 將報價轉送給專人審查;它不移動資金或保留容量。status 是唯讀的,儘管提供者端點可能會協調現有的採購訂單。ECC 說明中被動的儀表板連結是一個單獨的使用者操作網頁路由;請勿將其作為缺少 CLI 功能的替代方案來開啟或操作。

不支援的操作

支援的用戶端表面無法鎖定報價、保留容量、執行工作負載或提供推理服務。accept 是專人交接,不是購買。MCP 伺服器不暴露驗證功能;請使用上面的明確 CLI 命令。請勿發明額外的工具或購買路徑。當本地 CLI 缺失或即時操作失敗時,請勿使用瀏覽器或 fixture 替代。請報告缺少的功能並停止。

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.

相關技能