Use when Spark engineering knowledge must be placed, deduplicated, migrated, or validated across AGENTS, Notes, Roles, Skills, and Workflows.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Apply one home per fact and progressive disclosure.
Use agent knowledge instructions for asset ownership and
loading rules, and CONTRIBUTING.md for public documentation ownership.
Preserve the runtime-context and public-documentation boundaries. Reconcile stale prose with verified enforced contracts; escalate a conflict only when resolving it requires a product or authority decision. Return classification, authoritativeHomes, moves, linksUpdated, validation, and blockers.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Use when adding or updating Spark AI provider models or their compact and preflight metrics, especially baidu-oneapi, Grok, Claude, GPT, DeepSeek, OneAPI, context windows, output budgets, prices, thinking maps, or transports.
中文简介正在准备中。当前显示原文说明。
Use when a Spark change needs its authoritative owner, affected boundaries, risks, acceptance criteria, and smallest verifiable slice established before implementation or review.
中文简介正在准备中。当前显示原文说明。
Use when a Spark implementation needs an evidence-based review for correctness, ownership, compatibility, failure handling, maintainability, and unnecessary complexity.
中文简介正在准备中。当前显示原文说明。
Use when designing a Spark feature or writing or materially revising a design proposal that needs repository-first research, user input on unresolved key choices, and an owner-aligned implementation plan before code changes.
中文简介正在准备中。当前显示原文说明。
Use when a working Spark implementation should be simplified without changing its observed behavior, ownership, compatibility, or public contract.
中文简介正在准备中。当前显示原文说明。
Use when a running Spark or DSH web service needs real-browser verification — page load, client-plugin boot errors, console errors, failed requests, or onboarding/dialog rendering — with the repository's own Playwright chromium.
中文简介正在准备中。当前显示原文说明。