Claude Skills by zendev-lab

Use when Spark engineering knowledge must be placed, deduplicated, migrated, or validated across AGENTS, Notes, Roles, Skills, and Workflows.

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.

Use when a Spark change needs its authoritative owner, affected boundaries, risks, acceptance criteria, and smallest verifiable slice established before implementation or review.

Use when a Spark implementation needs an evidence-based review for correctness, ownership, compatibility, failure handling, maintainability, and unnecessary complexity.

Use when a Spark feature needs repository-first research, explicit option selection, and an owner-aligned implementation plan before code changes.

Use when a working Spark implementation should be simplified without changing its observed behavior, ownership, compatibility, or public contract.

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.

Use when a Spark branch or pull request needs final diff hygiene, validation selection, commit scope, remote topology, and readiness checked before publication.