@bonesofspring/ai-rules 0.2.13 → 0.2.14

package/presets/claude/svelte/rules/tooling-and-review/preset-no-cross-stack-leakage.md

@@ -0,0 +1,83 @@
+---
+description: Preset authoring: forbid cross-stack agent/path leakage in hooks and agents.
+paths:
+  - packages/ai-rules/presets/**/*
+  - .cursor/rules/**/*
+  - .cursor/team/tasks/**/*
+---
+
+<!-- shared-core: meta/preset-no-cross-stack-leakage.md -->
+
+
+# Preset no cross-stack leakage
+
+Запрет протекания stack-specific имён, путей и handoff stems между пресетами.
+
+## Principles
+
+- `next` must not require iOS-only agents/tooling (`xcuitest-*`, `xcodebuild` as required handoff, Keychain-only rules).
+- `nuxt` must not require iOS-only agents/tooling (`xcuitest-*`, `xcodebuild` as required handoff, Keychain-only rules).
+- `svelte` must not require iOS-only agents/tooling (`xcuitest-*`, `xcodebuild` as required handoff, Keychain-only rules).
+- `ios-swift` must not ship Playwright handoffs or Next lint recipes as required commands.
+- `go` / `java` / `php-hexagonal` / `php-laravel` / `mcp-ts` must not ship Playwright, XCUITest, Next lint recipes, or `xcodebuild`/`SwiftLint` as required handoffs.
+- `mcp-ts` must not ship Go tool commands (`go test`, `go vet`, `golangci-lint`) or `integration-test-*` agents as required delivery gates.
+- Shared core must not embed stack paths (`app/src/**`, `Features/**`, `playwright`, `xcodebuild`).
+
+## Forbidden in ios-swift hooks/agents (FAIL)
+
+In ios-swift `chain-team-phases.sh` / agent handoffs (Cursor + Claude):
+
+- `playwright-test-`, `playwright-agents`, `playwright-e2e`, `user-playwright`
+- `app/__tests__/e2e` as a required path
+- Positive yarn recipes `lint:js` / `lint:css` as commands to run (negation prose alone is weak — prefer zero occurrences)
+
+Required instead: `xcuitest-test-*` stems; build-verifier mentions `xcodebuild` or `post-change-build` / `xcode-tooling`.
+
+## Forbidden in next hooks/agents (FAIL when present as required)
+
+- `xcuitest-test-` as handoff stems
+- Requiring `xcodebuild` / SwiftLint as the default post-change gate for Next app work
+
+## Forbidden in nuxt hooks/agents (FAIL when present as required)
+
+- `xcuitest-test-` as handoff stems
+- Requiring `xcodebuild` / SwiftLint as the default post-change gate for Nuxt app work
+- Frontend profile mirrors `next`: Playwright / `lint:js` / `lint:css` allowed
+
+## Forbidden in svelte hooks/agents (FAIL when present as required)
+
+- `xcuitest-test-` as handoff stems
+- Requiring `xcodebuild` / SwiftLint as the default post-change gate for SvelteKit app work
+- Frontend profile mirrors `next` / `nuxt`: Playwright / `lint:js` / `lint:css` allowed
+
+## Forbidden in go / java / php-hexagonal / php-laravel hooks/agents (FAIL)
+
+Shared backend-stack bans (`go`, `java`, `php-hexagonal`, and `php-laravel`):
+
+- `playwright-test-`, `playwright-e2e`, `user-playwright`, `app/__tests__/e2e`
+- Positive yarn recipes `lint:js` / `lint:css`
+- `xcuitest-test-`, `xcodebuild`, `SwiftLint` as required handoffs
+- Agent file `accessibility-reviewer` (no UI surface)
+
+Required instead: `integration-test-*`; build-verifier / `post-change-test` plus stack tooling — `go-tooling` (`go test`, `go vet`), `java-tooling` (`mvn test` / `./gradlew test`), or `php-tooling` (`php artisan test` / `composer test` / `vendor/bin/phpunit`).
+
+## Forbidden in mcp-ts hooks/agents (FAIL)
+
+Same UI/mobile bans as backend stacks, plus:
+
+- `playwright-test-`, `playwright-agents`, `playwright-e2e`, `user-playwright`, `app/__tests__/e2e`
+- Positive yarn recipes `lint:js` / `lint:css` as required gates
+- `xcuitest-test-`, `xcodebuild`, `SwiftLint` as required handoffs
+- Go tool commands as required MCP delivery gates: `go test`, `go vet`, `golangci-lint`
+- Agent files: `playwright-test-*`, `xcuitest-test-*`, `integration-test-*`, `accessibility-reviewer`
+
+Required instead: package-manager–discovered typecheck/test (`mcp-ts-tooling`, `post-change-test`); Phase 1 gates `build-verifier` + `security-reviewer`.
+
+## Soft / document
+
+- Mentioning the other stack in **docs** comparing presets is OK.
+- `build-verifier` may reference other stacks when validating **preset packaging** (`scope: preset-structure-validation`).
+
+## Chain fork
+
+`hooks/chain-team-phases.sh` must differ **byte-wise** pairwise among `next`, `nuxt`, `svelte`, `ios-swift`, `go`, `java`, `mcp-ts`, `php-hexagonal`, and `php-laravel` (per platform).

package/presets/claude/svelte/rules/tooling-and-review/preset-pr-checklist.md

@@ -0,0 +1,39 @@
+---
+description: Preset authoring: PR checklist for twin sync, budget, leakage, README. Use on preset PRs.
+paths:
+  - packages/ai-rules/presets/**/*
+  - .cursor/rules/**/*
+  - .cursor/team/tasks/**/*
+---
+
+<!-- shared-core: meta/preset-pr-checklist.md -->
+
+
+# Preset PR checklist
+
+Чеклист для PR, затрагивающих `packages/ai-rules/presets/**` (и dogfood `.cursor/` sync).
+
+## Before merge
+
+- [ ] **SoT:** правки в `packages/…` (не только root `.cursor/`)
+- [ ] **Core:** если менялся `_shared/core/**` — обновлены все `<!-- shared-core: … -->` consumers (или documented intentional fork)
+- [ ] **Twin:** Cursor change → Claude twin **same PR** (**FAIL** if missing on next, nuxt, svelte, ios-swift, go, java, mcp-ts, php-hexagonal, and php-laravel — см. `preset-twin-sync`)
+- [ ] **Mapping:** `claude/<stack>/rules/README.md` mapping table актуален
+- [ ] **Token budget:** alwaysApply / session-start ≤ 3; meta rules not always-on
+- [ ] **Leakage:** нет чужих stack agent stems / handoff strings (`preset-no-cross-stack-leakage`)
+- [ ] **Twin depth:** domain ≥15 lines; thin aliases documented
+- [ ] **README:** stack `rules/README.md` core→stack mapping / catalog updated if stems added
+- [ ] **CHANGELOG / package README:** note when public preset paths or install surface change
+- [ ] **Dogfood:** run `packages/ai-rules/scripts/sync-dogfood-cursor.sh` (or document intentional skip) when maintaining this monorepo
+- [ ] **shared-core drift:** for embed-mode stems, run `packages/ai-rules/scripts/check-shared-core-drift.sh` (or document intentional fork)
+
+## Pointers
+
+- Layering: `preset-layering`
+- Sync: `preset-twin-sync`
+- Budget: `preset-token-budget`
+- Leakage: `preset-no-cross-stack-leakage`
+- Validation: stack `agents/build-verifier.md` → preset-structure section
+- Dogfood script: `packages/ai-rules/scripts/sync-dogfood-cursor.sh`
+- Drift script: `packages/ai-rules/scripts/check-shared-core-drift.sh`
+- Orchestrator: when editing presets, load this checklist + twin-sync

package/presets/claude/svelte/rules/tooling-and-review/preset-token-budget.md

@@ -0,0 +1,41 @@
+---
+description: Preset authoring: ≤3 always-on / session-start; meta rules never alwaysApply.
+paths:
+  - packages/ai-rules/presets/**/*
+  - .cursor/rules/**/*
+  - .cursor/team/tasks/**/*
+---
+
+<!-- shared-core: meta/preset-token-budget.md -->
+
+
+# Preset token budget
+
+Инварианты загрузки правил в **установленном** пресете (consumer app).
+
+## Hard caps
+
+| Platform | Always-on | Cap |
+|----------|-----------|-----|
+| Cursor | `alwaysApply: true` | **≤ 3** |
+| Claude | rules **without** `paths:` | **ровно 3** |
+
+**Claude Option A (README exclusion):** when counting Claude rules without `paths:` / session-start, **exclude `**/README.md`** (topic indexes are not session-start rules). The intended session-start trio remains **exactly 3**; body budget sums **only those 3** rules.
+
+Session-start body budget (где задокументировано): ≤140 строк суммарно (stretch ≤120).
+
+## Meta / author rules
+
+Rules for preset authors (`preset-layering`, `preset-twin-sync`, …):
+
+- **Never** `alwaysApply: true` on consumer installs.
+- Cursor: `globs` limited to `packages/ai-rules/presets/**` (and dogfood `.cursor/**` where useful).
+- Claude: `paths:` limited to `packages/ai-rules/presets/**` (and `.claude/**` dogfood if present).
+
+## Heavy workflows
+
+Orchestrator, feature-delivery, code-review, post-change gates, domain globs — **requestable / paths**, not always-on.
+
+## Verifier
+
+build-verifier **FAIL** if alwaysApply / session-start count exceeds 3 (Claude count **excludes `**/README.md`**), or if a `preset-*` meta rule is marked always-on.

package/presets/claude/svelte/rules/tooling-and-review/preset-twin-sync.md

@@ -0,0 +1,54 @@
+---
+description: Preset authoring: Cursor SoT → Claude twin same PR. Use when editing preset rules.
+paths:
+  - packages/ai-rules/presets/**/*
+  - .cursor/rules/**/*
+  - .cursor/team/tasks/**/*
+---
+
+<!-- shared-core: meta/preset-twin-sync.md -->
+
+
+# Preset twin sync
+
+Cursor `.mdc` — **SoT per stack**. Claude topic `.md` — derived twin.
+
+## Matrix
+
+| Stack | Cursor SoT | Claude derive | Mapping table |
+|-------|------------|---------------|---------------|
+| `next` | `presets/cursor/next/rules/*.mdc` | `presets/claude/next/rules/<topic>/` | **Required** in `claude/next/rules/README.md` |
+| `nuxt` | `presets/cursor/nuxt/rules/*.mdc` | `presets/claude/nuxt/rules/<topic>/` | **Required** in `claude/nuxt/rules/README.md` |
+| `svelte` | `presets/cursor/svelte/rules/*.mdc` | `presets/claude/svelte/rules/<topic>/` | **Required** in `claude/svelte/rules/README.md` |
+| `ios-swift` | `presets/cursor/ios-swift/rules/*.mdc` | `presets/claude/ios-swift/rules/<topic>/` | Keep in `claude/ios-swift/rules/README.md` |
+| `go` | `presets/cursor/go/rules/*.mdc` | `presets/claude/go/rules/<topic>/` | Keep in `claude/go/rules/README.md` |
+| `java` | `presets/cursor/java/rules/*.mdc` | `presets/claude/java/rules/<topic>/` | Keep in `claude/java/rules/README.md` |
+| `mcp-ts` | `presets/cursor/mcp-ts/rules/*.mdc` | `presets/claude/mcp-ts/rules/<topic>/` | Keep in `claude/mcp-ts/rules/README.md` |
+| `php-hexagonal` | `presets/cursor/php-hexagonal/rules/*.mdc` | `presets/claude/php-hexagonal/rules/<topic>/` | Keep in `claude/php-hexagonal/rules/README.md` |
+| `php-laravel` | `presets/cursor/php-laravel/rules/*.mdc` | `presets/claude/php-laravel/rules/<topic>/` | Keep in `claude/php-laravel/rules/README.md` |
+
+## Same-PR checklist
+
+1. Edit Cursor rule first (body + frontmatter).
+2. Update Claude twin: body + `paths:` (from Cursor `globs:` / requestable triggers); drop `alwaysApply`.
+3. Update mapping table row if stem/path changed.
+4. If body embeds core (`<!-- shared-core: … -->`), sync core consumers across stacks when core changed.
+
+## Twin depth
+
+- **Domain** rules: ≥15 body lines (FAIL if thin without documented alias reason).
+- **Thin aliases** (`agent-team-intake`, `technical-retro`): may be shorter (soft) if they only point to a command/skill.
+
+## Severity (build-verifier)
+
+- **next:** missing Claude twin for a changed Cursor rule → **FAIL** (mapping table required).
+- **nuxt:** missing Claude twin for a changed Cursor rule → **FAIL** (mapping table required).
+- **svelte:** missing Claude twin for a changed Cursor rule → **FAIL** (mapping table required).
+- **ios-swift:** missing Claude twin for a changed Cursor rule → **FAIL**.
+- **go:** missing Claude twin for a changed Cursor rule → **FAIL** (same as next / ios-swift; mapping table required).
+- **java:** missing Claude twin for a changed Cursor rule → **FAIL** (same as next / ios-swift / go; mapping table required).
+- **mcp-ts:** missing Claude twin for a changed Cursor rule → **FAIL** (same as next / ios-swift / go / java; mapping table required).
+- **php-hexagonal:** missing Claude twin for a changed Cursor rule → **FAIL** (same as next / ios-swift / go / java / mcp-ts; mapping table required).
+- **php-laravel:** missing Claude twin for a changed Cursor rule → **FAIL** (same as next / ios-swift / go / java / mcp-ts / php-hexagonal; mapping table required).
+
+Dogfood: sync packages → root `.cursor/` after Cursor SoT changes (not the reverse). Use `packages/ai-rules/scripts/sync-dogfood-cursor.sh`.

package/presets/claude/svelte/rules/tooling-and-review/security-sveltekit.md

@@ -0,0 +1,41 @@
+---
+description: SvelteKit security — env, SSR secrets, CSRF, XSS, hooks, +server
+paths:
+  - src/routes/**/*
+  - src/hooks.server.ts
+  - src/hooks.client.ts
+  - src/lib/**/*
+---
+
+# Security (SvelteKit)
+
+## Secrets & env
+
+- Private secrets: `$env/static/private` / server-only modules — **never** import into client `.svelte` / universal modules that ship to browser.
+- Public config: `$env/static/public` (prefixed per project convention).
+- Do not commit `.env` with secrets; do not log tokens.
+
+## Server boundaries
+
+- `+server.ts`, `+page.server.ts`, `hooks.server.ts` may touch private env and privileged backends.
+- Do not import `.svelte` UI into server handlers by default.
+- Prefer `$lib/api` for domain client services; keep BFF thin.
+
+## XSS / HTML
+
+- Prefer text interpolation; `{@html …}` only with sanitized/trusted content.
+- Follow `svelte-a11y-coding` and eslint-plugin-svelte a11y where configured.
+
+## CSRF / forms
+
+- Prefer Kit form actions + progressive enhancement patterns already in the repo.
+- Validate/authorize on the server; never trust client-only checks for authz.
+
+## HTTP client
+
+- Use project `fetch` wrapper (`http-client`); forward cookies via `load`/`event.fetch` for same-origin SSR when required.
+- Do not put credentials in public env or client bundles.
+
+## Agent discipline
+
+- If unsure whether a module is server-only, check filename (`.server.ts`), imports, and siblings — mark `// VERIFY` rather than guessing.

package/presets/claude/svelte/rules/tooling-and-review/technical-retro.md

@@ -0,0 +1,17 @@
+---
+description: Роль агента для проведения технического ретроспективы (retro) команды / спринта. On-demand — предпочтительнее slash-команда /technical-retro.
+paths:
+  - .claude/team/**
+---
+
+<!-- shared-core: review/technical-retro.md -->
+
+# Техническое ретро — rule alias
+
+Полный сценарий (включая блок **«Работа агентов»** для slug из team tasks) — в slash-команде:
+
+**`commands/technical-retro.md`** → `/technical-retro`
+
+When a task has `metrics.json`, use the local aggregation script and state the cohort, sample size, incomplete artifacts, attribution confidence, active attempt duration, and human-gate wait separately. Do not score malformed artifacts or gate wait as agent work.
+
+Используй rule только если command недоступен. Не дублируй содержимое command в ответе — следуй command-файлу и skill `technical-retro`.

package/presets/claude/svelte/rules/ui-and-accessibility/README.md

@@ -0,0 +1,12 @@
+# UI and accessibility
+
+Компоненты, стили, пропсы.
+
+| Файл | Содержание | Загрузка |
+|------|------------|----------|
+| `no-rest-props-spread.md` | Явные пропсы, без `{...props}` / `$$restProps` | `paths: **/*.svelte` |
+| `css-property-order.md` | Порядок CSS (Stylelint idiomatic-order) | `paths: **/*.{css,scss,svelte}` |
+| `svelte-ui.md` | Структура SFC, стили, lib facades | `paths: src/lib/components/**,src/routes/**` |
+| `svelte-a11y-coding.md` | A11y при написании UI | `paths: src/lib/components/**,src/routes/**` |
+
+Deprecated stub `component-styles.md` **removed** — styles colocation lives in `svelte-ui.md`.

package/presets/claude/svelte/rules/ui-and-accessibility/css-property-order.md

@@ -0,0 +1,12 @@
+---
+description: CSS property order via Stylelint (Svelte SFC styles included)
+paths:
+  - "**/*.{css,scss,svelte}"
+---
+
+# CSS property order
+
+- Follow the repo Stylelint config (property order plugin if present).
+- Applies to plain CSS/SCSS and `<style>` blocks in `.svelte` SFCs.
+- Do not hand-resort entire files unrelated to the task; fix order in touched rulesets.
+- Run via **`post-change-lint`** (`lint:css`).

package/presets/claude/svelte/rules/ui-and-accessibility/no-rest-props-spread.md

@@ -0,0 +1,32 @@
+---
+description: Ban undisciplined rest props / $$restProps bulk spread in Svelte
+paths:
+  - **/*.svelte
+---
+
+# No rest-props spread
+
+- Prefer **explicit props** via `$props()` (Svelte 5) or typed props — name what the component accepts.
+- Do **not** default to `{...props}` / `$$restProps` / bulk forwarding of unknown bags onto DOM or child components.
+- Narrow exceptions OK when following an established neighbor pattern (e.g. design-system polymorphic wrapper) — document why in a short comment.
+- Analogue of next `no-props-spread` / nuxt `no-v-bind-spread` — **do not** ship those stems in this preset.
+
+## Incorrect
+
+```svelte
+<script lang="ts">
+  let props = $props()
+</script>
+
+<button {...props}>…</button>
+```
+
+## Correct
+
+```svelte
+<script lang="ts">
+  let { label, onclick }: { label: string; onclick?: () => void } = $props()
+</script>
+
+<button type="button" {onclick}>{label}</button>
+```

package/presets/claude/svelte/rules/ui-and-accessibility/svelte-a11y-coding.md

@@ -0,0 +1,28 @@
+---
+description: Accessibility conventions for Svelte components and routes
+paths:
+  - src/lib/components/**/*
+  - src/routes/**/*
+---
+
+# Svelte a11y coding
+
+- Prefer semantic HTML (`button`, `a`, `label`, landmarks) over clickable `div`/`span`.
+- Interactive elements need keyboard support and visible focus — follow neighbors and design system.
+- Images: meaningful `alt` (or empty alt for decorative).
+- Forms: associate labels; surface errors accessibly.
+- Respect `eslint-plugin-svelte` a11y rules when configured; do not blanket-disable without why.
+- Dynamic UI (dialogs, menus): focus trap / restore patterns already used in the repo — do not invent a second a11y stack.
+- Pair with `svelte-ui` and `architecture-boundaries-ui`.
+
+## Incorrect
+
+```svelte
+<div onclick={submit}>Save</div>
+```
+
+## Correct
+
+```svelte
+<button type="submit">Save</button>
+```

package/presets/claude/svelte/rules/ui-and-accessibility/svelte-ui.md

@@ -0,0 +1,38 @@
+---
+description: Svelte SFC UI conventions (components, routes)
+paths:
+  - src/lib/components/**/*
+  - src/routes/**/*
+---
+
+# Svelte UI (SvelteKit)
+
+- Предпочитать **`.svelte` SFC** с `<script lang="ts">` (`svelte-script-conventions`).
+- Явные props (`$props()` / typed props); без массового `{...props}` / `$$restProps` (`no-rest-props-spread`).
+- Svelte 5: snippets / `{@render …}` preferred for new code; legacy slots OK when following neighbors.
+- Стили: scoped `<style>` / tokens — как у соседей; порядок свойств — `css-property-order-stylelint`.
+- Данные: читать stores / runes / `load` data; **не** вызывать HTTP из `.svelte` — только через `$lib/api` / store actions.
+- Навигация: `<a href>`, `goto`, `invalidate`, `$app/navigation` — не `next/link`, не `<NuxtLink>`, не `navigateTo`.
+- A11y: `svelte-a11y-coding`.
+- Границы UI: `architecture-boundaries-ui` — no DTO in markup; map in `src/lib/api/**`.
+
+## Incorrect
+
+```svelte
+<script lang="ts">
+  const data = await fetch('/api/items').then((r) => r.json())
+</script>
+```
+
+## Correct
+
+```svelte
+<script lang="ts">
+  import { onMount } from 'svelte'
+  import { loadItems } from '$lib/stores/items'
+
+  onMount(() => {
+    void loadItems()
+  })
+</script>
+```

package/presets/claude/svelte/skills/README.md

@@ -0,0 +1,17 @@
+# `.claude/skills` (preset svelte)
+
+[Skills](https://code.claude.com/docs/en/skills) в Claude Code — сценарии, которые подгружаются по необходимости, а не в каждой сессии целиком. Они синхронизированы по смыслу с `.cursor/skills` из Cursor-пресета.
+
+| Skill | Когда использовать |
+|-------|--------------------|
+| `feature-delivery` | End-to-end feature work across types, API, store, UI, tests |
+| `code-review` | MR/diff review using project architecture and test standards |
+| `debug-investigation` | Reproducing and fixing bugs with root-cause evidence |
+| `ci-investigation` | Diagnosing and fixing failing CI checks on PRs/branches |
+| `unit-testing` | Planning, generating, or healing unit test coverage |
+| `playwright-e2e` | Planning, generating, or healing Playwright e2e coverage |
+| `technical-retro` | Technical retrospective for a task, sprint, incident, or agent pipeline |
+| `write-adr` | Author an Architecture Decision Record (context / decision / consequences) |
+| `svelte-performance` | Implementer checklist: bundle, SSR/payload/client, memo, waterfalls, CWV (not a perf audit agent) |
+
+Папка копируется в `.claude/skills/` при `ai-rules init claude --preset svelte`, если существует.

package/presets/claude/svelte/skills/ci-investigation/SKILL.md

@@ -0,0 +1,36 @@
+---
+name: ci-investigation
+description: Investigates failing CI checks on PRs and branches — lint, typecheck, unit, e2e — with local reproduction and minimal fixes. Use when CI is red or for ci-fix pipeline tasks.
+---
+
+# CI Investigation
+
+## Workflow
+
+1. Identify the **first failing check** (lint, typecheck, unit, e2e, build).
+2. Capture error output — ignore cascading failures until root cause is found.
+3. Reproduce locally with the same commands CI uses from repository root:
+   - `lint:js`, `lint:css`, `check`
+   - targeted unit test file or suite
+   - affected Playwright spec if e2e failed
+4. Inspect git diff for changed files related to the failure.
+5. Apply **minimal fix** — no unrelated refactors.
+
+## Artifact
+
+Write `ci-report.md` under the task slug folder:
+
+- Failed check name and link/log excerpt
+- Root cause classification
+- Fix applied (or handoff to feature-developer)
+- Validation commands and results
+
+## Handoff Rules
+
+- Config-only or one-line fixes → fix in place, re-run check.
+- Missing tests or architecture work → document and route to `feature-developer` or `qa-tester`.
+- Flaky e2e → prefer `playwright-test-healer` after ci-investigator identifies the spec.
+
+## Validation
+
+Always re-run the failing command locally before marking complete. If environment blocks execution, state the exact command and blocker.

package/presets/claude/svelte/skills/code-review/SKILL.md

@@ -0,0 +1,38 @@
+---
+name: code-review
+description: Reviews pull requests, merge requests, git diffs, and branch changes using the preset's architecture, import, UI, API, and testing standards. Use when the user asks for review or when code-reviewer runs in an agent pipeline.
+---
+
+# Code Review
+
+## Inputs
+
+Use the local repository as the source of truth: `git status`, `git diff`, task artifacts under `.claude/team/tasks/<slug>/` when present, and opened files. Do not invent hosting metadata such as labels, CI status, or reviewers.
+
+## Review Order
+
+1. Understand the intent and affected layers.
+2. Check correctness and regressions first.
+3. Verify architecture boundaries: UI does not know DTO/transport, store does not depend on UI, API services do not pull UI/store.
+4. Check public imports through `@/types` and `@/api`, plus barrel updates for new public symbols.
+5. Review UI consistency, styling conventions, and prop shape.
+6. Check tests: unit for mapper/domain logic, behavior tests for HTTP client changes, e2e plan/spec updates for user flows.
+7. **Reuse lens:** flag new helpers that duplicate existing utilities; prefer adjacent shared modules over copy-paste.
+8. **Efficiency lens:** unnecessary work, sequential ops that should be parallel, hot-path bloat, no-op store updates, overly broad reads.
+9. Report validation gaps: lint, stylelint, typecheck, or relevant tests not run.
+
+## Output
+
+Lead with findings ordered by severity. Required shape (also in `code-review-mr`):
+
+- Each finding: **`path:line`** — problem — impact — concrete fix direction.
+- Severity: **`blocker` | `important` | `nit`** (list blocker → nit).
+- Vague («looks risky») is not a finding — cite evidence or ask for surrounding context.
+- End with a verdict line: **`Safe to merge | needs changes | reject`**.
+- If there are no findings, say so and call out remaining test or validation risk.
+
+For agent team tasks, write `.claude/team/tasks/<slug>/review.md` and set `status.json` to `completed` or `changes_requested`.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

package/presets/claude/svelte/skills/debug-investigation/SKILL.md

@@ -0,0 +1,32 @@
+---
+name: debug-investigation
+description: Investigates bugs, failing tests, crashes, and incorrect behavior with runtime evidence before applying minimal fixes. Use for bugfix tasks, debugger agent runs, regressions, and flaky test diagnosis.
+---
+
+# Debug Investigation
+
+## Process
+
+1. Reproduce the issue or collect the closest available evidence: error output, failing test, browser snapshot, logs, or user steps.
+2. Define expected vs actual behavior in one sentence.
+3. Trace the failing path through the smallest relevant slice of the codebase.
+4. Identify the root cause before editing. Avoid broad refactors during bugfixes.
+5. Apply the smallest fix that preserves existing architecture and public contracts.
+6. Add or update a regression test when the behavior is user-facing or likely to recur.
+7. Run the narrow failing check first, then relevant lint/type/test validation.
+
+## Artifacts
+
+For agent team tasks, write `.claude/team/tasks/<slug>/debug-report.md` with:
+
+- Reproduction steps or evidence source.
+- Root cause.
+- Fix scope.
+- Regression coverage.
+- Remaining risk.
+
+Update `status.json` when complete.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

package/presets/claude/svelte/skills/feature-delivery/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: feature-delivery
+description: Delivers SvelteKit frontend features end-to-end across domain types, API services, store, UI, mocks, tests, and validation. Use when implementing or extending a feature, especially through /task or feature-developer.
+---
+
+# Feature Delivery
+
+1. Read task brief, acceptance criteria, and decomposition if present.
+2. Read **`feature-delivery-workflow`** and **`reference-features`** — follow layer order and mirror closest reference feature.
+3. Add or update focused tests for changed behavior.
+4. Validation from SvelteKit root: **invoke** **`post-change-lint`** after code edits (requestable, not always-on — but mandatory when code changed). Pipeline: scoped lint OK if next step is `build-verifier`.
+
+## Scope discipline
+
+Implement only the current AC / decomposition task. Clarify ambiguity before coding; do not add unrelated hardening, polish, or refactors. See `feature-developer` → **Zero improvisation**.
+
+## Handoff
+
+Summarize by layer, validation results, and known gaps. Agent team: update `.cursor/team/tasks/<slug>/status.json`.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.
+
+## Anti-hallucination
+
+- When editing Svelte/TS under `src/**`, load `svelte-sveltekit-anti-hallucination` (phantom Kit/Svelte/React/Vue imports).
+
+## Stack notes (SvelteKit)
+
+- Layers: `src/routes` / `src/lib/components` → facades → `src/lib/stores` (store-svelte) → `src/lib/api` → `src/lib/clients`; server via `+server.ts` / hooks.
+- Anti-hallucination: `svelte-sveltekit-anti-hallucination`.
+- Scripts cwd: SvelteKit root (`svelte.config.*`); gates: `lint:js`, `lint:css`, `check`.
+- E2E: `tests/e2e/` (Playwright).

package/presets/claude/svelte/skills/playwright-e2e/SKILL.md

@@ -0,0 +1,37 @@
+---
+name: playwright-e2e
+description: Plans, generates, and heals Playwright e2e tests using this preset's tests/e2e layout, *.cases.md plans, page objects, and shared helpers. Use for e2e planning, test generation, or fixing failing browser tests.
+---
+
+# Playwright E2E
+
+## Project Layout
+
+- Test root: `tests/e2e`.
+- Test plans: `*.cases.md` files under the matching feature folder.
+- Executable specs: `*.spec.ts` files in the same folder.
+- Seed/setup reference: `tests/e2e/seed.spec.ts`.
+
+Do not introduce top-level `specs/` or `tests/` folders for real coverage unless the user explicitly asks for a sandbox.
+
+## Planner
+
+Create or update the relevant `*.cases.md` file. Each scenario should include title, preconditions, steps, and expected result. Cover happy path, important edge cases, validation, and error states.
+
+## Generator
+
+Generate specs from `*.cases.md` into the same folder. Reuse existing page objects and `_shared/` helpers. Keep test names aligned with scenario names.
+
+## Healer
+
+Fix selectors, waits, setup, or page-object details without weakening business assertions. Use the matching `*.cases.md` file as the behavior contract.
+
+## Validation
+
+Run the affected spec when feasible. If the environment blocks execution, report the command that should be run and the blocker.
+
+
+## Stack notes (SvelteKit)
+
+- E2E root: `tests/e2e/`.
+- Default baseURL `http://localhost:3000`; prefer `webServer` → `svelte dev` or `svelte preview`.