Communitygithub.com

Itô 運算資源管理

查詢即時 GPU 庫存、提交經過身分驗證的 Itô 固定費率詢價單 (RFQ)、檢查 RFQ 或採購狀態、撤銷裝置憑證,並透過獨立安裝的官方 CLI 執行明確受控的節點資格驗證。

Itô 運算資源管理 是什麼?

此技能提供與 Itô 運算平台的完整互動能力,包含即時 GPU 庫存查詢(如 H100/H200)、固定費率詢價單提交與接受、採購狀態監控,以及節點資格驗證。它支援 CLI 與 MCP(Model Context Protocol)兩種工作流程,CLI 流程透過 `ecc ito` 命令列工具進行裝置授權登入、查詢、接受與登出,而 MCP 則以 stdio 伺服器形式提供 `ito_auth`、`ito_find`、`ito_status` 與 `ito_accept` 四項工具作為唯⼀操作介面。使用者需明確取得買方授權後才能提交 RFQ 或接受報價,且所有動作皆不涉及資金轉移、容量保留或工作負載執行;任何超出此範圍的操作(如鎖定報價、保留容量)均不被支援。價格僅供參考,固定費率僅在 canonical CLI 回傳非空 firm quote 時確立。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/everything-claude-code/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 運算資源管理 是做什麼的?

請使用官方 Itô 運算 CLI 或 MCP 伺服器。ECC 本身不實作平行客戶端、本機模擬、預約、工作負載執行或推理伺服器。ECC 亦不執行任何瀏覽器自動化。

安裝官方本機套件

ito-compute-cli 目前尚未發佈。請從其官方儲存庫建置,而非使用 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 發現此持有憑證的客戶端。 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 與 status,在配置時會直接轉發 ITO_API_KEY;不需要 ITO_AUTH_MODE=legacy。 切勿將金鑰或令牌放入參數、追蹤檔案、MCP 結果、日誌或聊天中。

CLI 工作流程

  1. 在首次操作前執行 ecc ito login。ECC 將此委派給官方 CLI 的裝置授權,該授權預設會開啟 Itô 驗證頁面,並將裝置令牌儲存在 macOS 鑰匙圈中。使用 ecc ito login --no-browser 可抑制頁面切換。ECC 本身不執行瀏覽器自動化。如果發起代理無法完成已登入的瀏覽器步驟,請將確切命令交給使用者;待授權完成後,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。檔案令牌備用方案需明確指定,且其目錄與令牌檔案必須保持僅擁有者可存取(0700 與 0600)。

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

  3. 在 ecc ito find 之前,需取得明確的買方授權以提交 RFQ。

    • 需要 gpu、count、整數 days、max-rate、nodes、 gpus-per-node、storage-tb、start-window、form-factor、 contract-type、fabric、region,以及是否允許分段成交的決定。
    • 需要 count == nodes * gpus-per-node;絕不要自行推導拓撲。
    • 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 以檢視 RFQ 與採購訂單。 在發生不明確的傳輸失敗後,請在重複執行 find 前先檢查狀態。

  6. 當報價就緒且買方明確核准時,接受該報價:

    ecc ito accept rfq_<ticket-id>
    

    此操作會將工單提交至後台進行人工審核。它不會轉移資金或保留容量。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。 官方 CLI 會在遠端撤銷失敗時保留本機憑證,以便操作者重試;切勿手動刪除令牌作為替代方案。

庫存價格僅供參考。RFQ 不等於保留容量。僅在官方結果包含非空 firm quote 時,方可將費率視為固定。

即時節點資格驗證

ecc ito evals 將官方 CLI 的狹義即時適配器暴露給獨立安裝的 sixtytwo-cli==0.3.33。 它不透過 ECC 暴露本機測試執行。 在呼叫前需滿足以下所有條件:

  • 操作者授權聯絡指定的節點;
  • ITO_ENABLE_SIXTYTWO_LIVE=1;
  • --live-sixtytwo;
  • 明確的節點清單;以及
  • 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

官方適配器僅能對指定節點執行固定版本檢查與 sixtytwo test --full。它無法租用、啟動、復原、修復、重設、購買或訂購資源。ECC 不會將 ITO_API_KEY 或模型/雲端憑證轉發至節點資格驗證。

MCP 工作流程

建置官方套件,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"
      ]
    }
  }
}

伺服器僅暴露以下工具:

  • 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與所有必要條件,呼叫 ito_find,然後在需要時輪詢 ito_status。當報價就緒且買方明確核准時,使用工單 ID 呼叫 ito_accept。後台報價通常僅供參考,且不具約束力,直到後台確認;結果中會包含 quote_class。

租賃或購買語意

find 提交 RFQ 並可能回傳 firm quote,但不等於租用、購買、保留、佈建或轉移資金。accept 將報價提交至後台進行人工審核;它不會轉移資金或保留容量。status 為唯讀取向,但提供者端點可能會協調現有的採購訂單。ECC 說明中的被動儀表板連結為獨立的使用者操作網頁;請勿將其作為遺失 CLI 功能的替代方案來開啟或操作。

不支援的操作

此支援的客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 是後台轉交,而非購買。MCP 伺服器不暴露資格驗證;請使用上述明確的 CLI 命令。請勿發明額外的工具或購買路徑。當本機 CLI 遺失或即時操作失敗時,請勿使用瀏覽器或本機測試作為替代。請回報遺失的功能並停止操作。

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/claude-api

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

affaan-m/everything-claude-code

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

affaan-m/everything-claude-code

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/everything-claude-code-conventions

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality.

affaan-m/gget

gget CLI and Python workflow for quick genomic database queries, sequence lookup, BLAST-style searches, enrichment checks, and reproducible bioinformatics evidence logs.

affaan-m/literature-review

Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.

affaan-m/motion-ui

Production-ready UI motion system for React/Next.js. Use when implementing animations, transitions, or motion patterns.

affaan-m/project-guidelines-example

Example project-specific skill template based on a real production application.

affaan-m/pubmed-database

Direct PubMed and NCBI E-utilities search workflows for biomedical literature, MeSH queries, PMID lookup, citation retrieval, and API-backed literature monitoring.

affaan-m/scholar-evaluation

Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.

affaan-m/uspto-database

USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.

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.

相關技能