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。
zendev-lab/spark22026年10月19日 更新
免费在 GitHub 公开
spark-change-scope
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。
查看安装方法包含的文件（1）
- SKILL.md1.3 KB
SKILL.md（原文）
安装前可以查看交给 AI 代理的指令内容。
Spark change scope
Establish the change boundary from live repository evidence before recommending edits.
Procedure
- Read the nearest
AGENTS.md,architecture/packages.json, the owning specification, package README, and nearby tests. - Identify one authoritative owner for every state transition, protocol, policy, and persisted field in scope.
- Trace callers and consumers far enough to find cross-package, compatibility, public-documentation, and migration effects.
- Separate required behavior from adjacent cleanup. Choose the smallest slice that can prove the requested outcome.
- Turn the request into observable acceptance criteria, including failure and compatibility cases.
Do not choose an owner from directory names or prompt prose when an enforced inventory or runtime path contradicts it. Resolve ambiguity from those sources first. If a new state owner or unresolved product choice requires an architecture decision, report the specific decision and continue independent scoped work.
Return owner, surfaces, invariants, risks, acceptanceCriteria, outOfScope, and blockers, citing paths and symbols.
评价
还没有评价。欢迎分享你的使用感受。
评论
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。
同一仓库的技能
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。
zendev-lab/spark22026年10月19日 更新
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。
zendev-lab/spark22026年10月19日 更新
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。
zendev-lab/spark22026年10月19日 更新
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。
zendev-lab/spark22026年10月19日 更新
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。
zendev-lab/spark22026年10月19日 更新