fubits1

MSW 2 (Mock Service Worker) mocking in Svelte: Storybook, Vitest browser tests, SvelteKit dev/SSR. Use when writing handlers or fixtures, when a story renders blank or errors Failed to fetch, or when migrating msw-storybook-addon v2 to v3.

Vitest test.projects, browser mode with playwright(), optimizeDeps, separate vitest.config from vite.config. Use when editing vitest config, debugging flaky browser tests, upgrading @vitest/*, or splitting node vs browser projects.

Svelte CSF (@storybook/addon-svelte-csf) + @storybook/addon-vitest: .stories.svelte as Vitest browser tests with play functions and tags. Use when wiring or debugging Svelte Storybook tests in Vitest/CI, not for React/Vue/CSF3 .ts story files.

Validation discipline for all code changes, testing, baselines, browser checks, CSS screenshots. Auto-invoke whenever making code changes, running tests, or declaring a task done.

Storybook workflow, MCP tools, fixtures, CSS import chains. Auto-invoke when working with Storybook stories or components.

Fix and create Svelte 5 tests with vitest-browser-svelte and Playwright. Use when fixing broken tests, debugging failures, writing unit/SSR/e2e tests, or working with vitest/Playwright.

Code style rules for all languages: variable naming, brace style, HTML data attributes, CSS nesting. Auto-invoke when editing code files, writing new functions, or naming variables.

Validate edited files, lint .svelte/.ts/.js, test stories, lint markdown. Auto-invoke after ANY file edit before declaring done. User-invocable as /validate-file [files].

Use fff MCP / Grep / Read / Glob — never Bash grep/cat/find/head/tail/sed/awk/rg/wc — for file search and read. Use jq for JSON parsing/shaping (not node -e / python -c). A hook hard-blocks the banned Bash calls, and the dedicated tools return clean, cacheable, line-numbered results. Auto-invoke when searching, reading, or counting in files.

Planning and problem-solving discipline: enter plan mode first, write plans in the plan file (not chat), structured research, validation, implementation. Auto-invoke when the user says "plan", "make a plan", or when fixing issues or implementing features.

Use before any action: five-question self-check that catches destructive ops, scope creep, fabrication, premature completion, and ignored instructions. Auto-invoke before executing commands, editing files, or answering factual questions.

Reconcile skill collections, backport from ~/.claude/skills into a marketplace plugins tree, scrubbing proprietary refs. Use when local has diverged from upstream, or when promoting local-only skills to a marketplace.

Communication and scope discipline: how to interact with the user, handle rejection, stay in scope. Always active.

Final checklist before declaring any task complete. Auto-invoke before saying "done", "ready", "complete", or asking to commit/push.

Research discipline: how to investigate before acting, verify claims. Auto-invoke when researching, answering questions, or planning migrations.

Use when the user corrects you, hands you a diagnosis, or gives a directive to decide, conclude, or carry out a stated action ("it just needs X", "decide whether Y", "update the docs"); also when your own fix keeps failing on the same theory.