diff --git a/.agents/skills/tanstack-fullstack-pattern/SKILL.md b/.agents/skills/tanstack-promptable-fullstack-app-template/SKILL.md
similarity index 92%
rename from .agents/skills/tanstack-fullstack-pattern/SKILL.md
rename to .agents/skills/tanstack-promptable-fullstack-app-template/SKILL.md
index d8c2c7f..6cccc5d 100644
--- a/.agents/skills/tanstack-fullstack-pattern/SKILL.md
+++ b/.agents/skills/tanstack-promptable-fullstack-app-template/SKILL.md
@@ -1,5 +1,5 @@
 ---
-name: tanstack-fullstack-pattern
+name: tanstack-promptable-fullstack-app-template
 description: 'Use when scaffolding a new TanStack Start project, adding domain
   entities to the fullstack template, or implementing the interface-first
   repository pattern with AI-promptable tools, or nested layout routes duplicate
@@ -36,7 +36,7 @@ An interface-first fullstack architecture built on TanStack Start. The pattern d
 8. URL-as-state: filters, tabs, selections live in URL search params via `validateSearch` (Zod/ArkType). Use `loaderDeps` to feed validated search into loaders.
 9. Middleware chain: auth is global middleware, invalidation runs on mutation server functions.
 10. Mutation pattern: POST server functions chain `.middleware([requireAuthMiddleware, invalidateMiddleware])`, return domain data or throw `HttpError`. Callers normalize errors: UI via `processResponse()`, AI tools via `safeToolHandler()` / `createSafeServerTool()`.
-11. Query pattern: GET server functions throw on failure for centralized error handling.
+11. Query pattern: GET server functions throw on failure for centralized error handling. When possible, use static server functions for performance improvements.
 12. Maximize AI tool coverage: expose **every** repository method (reads and writes) via `createSafeServerTool()` so failures return `{ error, code }`. If a server function exists, it gets a tool.
 13. Router capabilities as AI client tools: expose `router.navigate()` and `router.invalidate()` as client tools via `toolDefinition()`.
 14. AI system prompt context: `buildSystemPrompt()` injects three context blocks into every AI chat request. (a) **Current User** — name, email, role from the auth middleware context (server-side; no client round-trip needed). (b) **Browser Context** — timezone, locale, and current date/time from `browserContext` sent by `ChatDrawer` (client-side). (c) **Current Location** — pathname, search params, and full URL from `browserContext`; route patterns (e.g. `/tasks/$taskId`) are matched to resolve dynamic segments. The navigation manifest mirrors `routeTree.gen.ts` and lists each route's search params. When adding routes, update `navigationManifest.ts` and add pattern-matching in `buildSystemPrompt()` for new dynamic segments.
@@ -56,11 +56,12 @@ An interface-first fullstack architecture built on TanStack Start. The pattern d
 29. Explicit agent loop depth: configure `agentLoopStrategy: maxIterations(N)` explicitly on the `chat()` call (default N=10). This caps the number of consecutive tool-calling iterations the AI can run before returning a final answer, which bounds latency, cost, and infinite-loop risk. Tune N only after measuring; do not rely on the framework default.
 30. Public runtime config bridge: expose non-secret runtime config (Sentry DSN, environment name, feature flags) via a GET server function `getPublicEnv()` and inline the result as `window.__ENV__` in the root `RootDocument` using a small `<script>` tag emitted before client JS runs. Escape `<` in the inlined JSON to avoid breaking the HTML parser. Never rely on `import.meta.env` alone for values that must differ across runtime environments built from the same bundle. See AGENTS.md section "Public Runtime Config" for the template.
 31. Router UX defaults bundle: in `src/router.tsx`, configure `defaultStaleTime` (long for read-heavy dashboards, short for mutation-heavy apps), `defaultPreload: 'intent'`, `defaultPreloadStaleTime: 0` (always-fresh preloads), `scrollRestoration: true` (with a `getScrollRestorationKey` when needed), and a `notFoundComponent` on the root route. These defaults are a single coherent bundle — do not ship a router config without them.
-32. Link wrapper preserves search: export a project-local `Link` component (e.g. `src/components/Link/Link.tsx`) that wraps TanStack Router's `Link` with `search: true` as the default. Use this wrapper for every internal link so filters, tabs, and other URL state never silently drop on navigation. Reserve raw `<a>` for external URLs.
+32. Link wrapper preserves search & styling: export a project-local `Link` component (e.g. `src/components/Link/Link.tsx`) that wraps TanStack Router's `Link` with `search: true` as the default. Use this wrapper for every internal link so filters, tabs, and other URL state never silently drop on navigation. Ensure that links are still rendered using the chosen component library's corresponding element (e.g., using `createLink` or the `component` prop) so they inherit the correct styling. Reserve raw `<a>` for external URLs.
 33. Parent layout routes deduplicate subtree work: when several child routes under the same URL prefix need the same redirect, synchronous guard, or expensive read, implement it **once** on the **parent** layout route. Use the parent's `beforeLoad` for navigation gates and synchronous checks; use the parent's `loader` (still via server functions) for shared data that every descendant needs. Child loaders fetch **only** data specific to that segment. Descendants read parent loader output with `getRouteApi('/parent/path').useLoaderData()` or `useLoaderData({ from: '/parent/path' })` — do not copy the parent's `beforeLoad` or re-fetch the parent's loader payload in each child. Structure files to match TanStack Router's layout conventions (e.g. `routes/foo/route.tsx` wrapping `routes/foo/*`).
 34. Sentry user context + feedback: when Sentry is enabled, bind the signed-in user via `Sentry.setUser({ email, username })` from the shell component as soon as the identity loads (no extra round-trip).
 35. Single markdown artifact for help + AI + suggested prompts: maintain one `docs/help.md` imported with `?raw`. Back three surfaces from it: (a) a `/help` route that renders it with `react-markdown`; (b) an AI tool that returns the content so the assistant can answer "how do I..." questions; (c) a parser that extracts `- [ ]` / `- [x]` lines as the chat's recommended-question list. Zero duplication between docs, assistant, and suggested prompts.
 36. Distinct-value filter discovery: for every enum-ish field, the repository exposes a `getDistinctValues(field)` method that flows through a GET server function into a read-only AI tool (`getDistinctStatuses`, `getDistinctCategories`, …). The AI calls these to ground filter values in real data instead of guessing. The root loader can preload the same lists for UI filter bars so UI and AI share one vocabulary.
+37. Reduce `"use client"` usage: TanStack Start supports full SSR and React Server Components. Rely on Server Components by default. Only use `"use client"` when state (`useState`), effects (`useEffect`), or browser APIs are strictly necessary. Keep client components small and at the leaf level.
 
 ## Schema Boundaries
 
@@ -169,6 +170,10 @@ A TanStack Start file-based route at `/api/chat` with two handlers:
 
 `buildSystemPrompt()` composes `BASE_SYSTEM_PROMPT` (rule 25) + navigation manifest + dynamic context (rule 14). When modifying: add tools to the array, update `BASE_SYSTEM_PROMPT` when the data model changes, add pattern-matching for new dynamic route segments. See AGENTS.md section 8 "System Prompt Generation" for the six-section prompt template.
 
+## Dynamic Route Schema Extraction for AI
+
+To help the AI navigate accurately using client tools, dynamically extract your TanStack Router configuration from `router.flatRoutes`. Map this array to extract `fullPath`, `staticData.description` (for page context), path params (from segments starting with `$`), and search params (by inspecting `validateSearch` keys). Passing this structured map in the system prompt allows the AI to discover available routes and required parameters without hallucinating URLs.
+
 ## Verification
 
 Testing setup (Vitest, Playwright, auth fixtures) and the full validation checklist are in [AGENTS.md](https://github.com/carlosvin/tanstack-fullstack-ai-template/blob/main/AGENTS.md) sections 10 and 12. Quick smoke test: `pnpm format && pnpm lint && pnpm test && pnpm build`.
diff --git a/AGENTS.md b/AGENTS.md
index d37c799..27fde5f 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -2,7 +2,7 @@
 
 This document is the default agent and contributor guide for projects built from this template. It covers project structure, conventions, tooling, and operational detail.
 
-The **deep architectural contract** -- rigid rules, three schema layers, cross-layer mapping, interface contracts, migration workflow, and the TanStack CLI docs tip -- lives in the [TanStack Fullstack Pattern skill](.agents/skills/tanstack-fullstack-pattern/SKILL.md) (generated from `skills/src/*.skill.yaml`; regenerate with `pnpm skills:build`).
+The **deep architectural contract** -- rigid rules, three schema layers, cross-layer mapping, interface contracts, migration workflow, and the TanStack CLI docs tip -- lives in the [TanStack Promptable Fullstack App Template skill](.agents/skills/tanstack-promptable-fullstack-app-template/SKILL.md) (generated from `skills/src/*.skill.yaml`; regenerate with `pnpm skills:build`).
 
 ## 1. General Principles
 
@@ -20,7 +20,7 @@ The **deep architectural contract** -- rigid rules, three schema layers, cross-l
 - `src/middleware`: TanStack Start middleware (auth, invalidation). Registered globally in `src/start.ts`.
 - `src/services/api`: Server functions (exported directly from `createServerFn`) and shared response utilities.
 - `src/services/repository`: Repository interface, implementations (MongoDB, seed), and the factory.
-- `src/services/schemas`: Centralized Zod schemas — tools-layer schemas in `schemas.ts`, repository-layer schemas in `repository.ts`. See the [skill](.agents/skills/tanstack-fullstack-pattern/SKILL.md) for the full three-layer model.
+- `src/services/schemas`: Centralized Zod schemas — tools-layer schemas in `schemas.ts`, repository-layer schemas in `repository.ts`. See the [skill](.agents/skills/tanstack-promptable-fullstack-app-template/SKILL.md) for the full three-layer model.
 - `src/services/ai`: AI adapter interface, implementation, and tool definitions.
 - `src/services/observability`: Observability interface with Sentry and no-op implementations.
 - `src/services/db`: Database client singleton.
@@ -90,9 +90,10 @@ If your team prefers [`@tabler/icons-react`](https://tabler.io/icons) (the Manti
 
 ## 4. TypeScript and React
 
+- **Server Components by Default**: TanStack Start supports React Server Components. Rely on Server Components by default. Reduce the usage of `"use client"` directives. Only use `"use client"` at the top of files when React hooks (`useState`, `useEffect`) or browser APIs are strictly necessary. Keep client components as small and leaf-level as possible.
 - **Functional Components**: Prefer functional components and hooks over class components.
 - **Type Safety**: Use TypeScript features like interfaces, types, and generics effectively.
-- **Zod-First Types**: All domain types are defined as Zod schemas and TypeScript types are inferred via `z.infer<>`. Tools-layer schemas live in `src/services/schemas/schemas.ts` (with `.describe()` on every field for AI JSON Schema); repository-layer schemas live in `repository.ts`. See the [skill](.agents/skills/tanstack-fullstack-pattern/SKILL.md) for the three schema layers, `loaderDeps`, and cross-layer `Schema.parse()` mapping.
+- **Zod-First Types**: All domain types are defined as Zod schemas and TypeScript types are inferred via `z.infer<>`. Tools-layer schemas live in `src/services/schemas/schemas.ts` (with `.describe()` on every field for AI JSON Schema); repository-layer schemas live in `repository.ts`. See the [skill](.agents/skills/tanstack-promptable-fullstack-app-template/SKILL.md) for the three schema layers, `loaderDeps`, and cross-layer `Schema.parse()` mapping.
 - **Type Reuse**: Import types from `src/types`. Do not redefine existing types.
 - **URL-as-State**: Page state (filters, selections, active tabs, modal open/close) **must** live in URL search params, not `useState`. This makes state shareable via URL, survives refresh, and enables deep-linking. Use `validateSearch` on routes with Zod schemas to define and validate search params.
   - **Correct**: `const { filter } = Route.useSearch()` — state comes from the URL.
@@ -160,7 +161,7 @@ When a URL scheme changes (renaming a route segment, collapsing multiple paths i
 
 ## 6. Server Functions and Data Access
 
-This is a full-stack TanStack Start application. There is no separate backend API. The [skill](.agents/skills/tanstack-fullstack-pattern/SKILL.md) defines the rigid layering rules and the "every repo method gets a tool" policy.
+This is a full-stack TanStack Start application. There is no separate backend API. The [skill](.agents/skills/tanstack-promptable-fullstack-app-template/SKILL.md) defines the rigid layering rules and the "every repo method gets a tool" policy.
 
 ```
 Route Loader → Server Function (serverFns.ts) → Repository → Database / Seed Data
@@ -211,7 +212,7 @@ const result = await processResponse(() => myMutation({ data: input }))
 
 ## 8. AI Chat and Tools
 
-Server and client tool coverage expectations, the AI chat pipeline, and client-tool wiring samples are in the [skill](.agents/skills/tanstack-fullstack-pattern/SKILL.md). This section covers adapter details, file paths, and the navigation manifest.
+Server and client tool coverage expectations, the AI chat pipeline, and client-tool wiring samples are in the [skill](.agents/skills/tanstack-promptable-fullstack-app-template/SKILL.md). This section covers adapter details, file paths, and the navigation manifest.
 
 ### AI Adapter Interface
 
diff --git a/README.md b/README.md
index 3234ccc..7957916 100644
--- a/README.md
+++ b/README.md
@@ -33,10 +33,10 @@ You can install this repository's generated Agent Skill directly from GitHub:
 npx skills add carlosvin/tanstack-fullstack-ai-template --list
 
 # Install the TanStack fullstack pattern skill
-npx skills add carlosvin/tanstack-fullstack-ai-template --skill tanstack-fullstack-pattern
+npx skills add carlosvin/tanstack-fullstack-ai-template --skill tanstack-promptable-fullstack-app-template
 
 # Optional: install globally (available across projects)
-npx skills add carlosvin/tanstack-fullstack-ai-template --skill tanstack-fullstack-pattern -g
+npx skills add carlosvin/tanstack-fullstack-ai-template --skill tanstack-promptable-fullstack-app-template -g
 
 # Optional: verify installed skills
 npx skills list
@@ -44,7 +44,7 @@ npx skills list
 
 The skill is published in the standard location used by the CLI:
 
-- `.agents/skills/tanstack-fullstack-pattern/SKILL.md`
+- `.agents/skills/tanstack-promptable-fullstack-app-template/SKILL.md`
 
 ## Architecture
 
@@ -330,11 +330,11 @@ Then follow the end-to-end workflow:
 
 ### Option B: AI-Assisted via Generated Skill (New or Existing Project)
 
-The skill is defined once in a canonical YAML source and generated into the [agentskills.io](https://agentskills.io) standard at `.agents/skills/tanstack-fullstack-pattern/`. Windsurf and other compatible tools read this path directly.
+The skill is defined once in a canonical YAML source and generated into the [agentskills.io](https://agentskills.io) standard at `.agents/skills/tanstack-promptable-fullstack-app-template/`. Windsurf and other compatible tools read this path directly.
 
 The generated outputs are committed intentionally so you can copy the skill into another project or tool without running the build pipeline first. The machine-readable metadata lives in `skills/registry.json`, and the portable markdown copy lives in `skills/dist/`.
 
-**Use the skill in this repo:** clone the template — the skill is at `.agents/skills/tanstack-fullstack-pattern/`.
+**Use the skill in this repo:** clone the template — the skill is at `.agents/skills/tanstack-promptable-fullstack-app-template/`.
 
 **Install the skill globally** (available in all your projects):
 
@@ -348,13 +348,13 @@ To manually install instead:
 
 ```bash
 # Windsurf (reads .agents/skills/ when in repo; for global copy)
-cp -r .agents/skills/tanstack-fullstack-pattern ~/.codeium/windsurf/skills/
+cp -r .agents/skills/tanstack-promptable-fullstack-app-template ~/.codeium/windsurf/skills/
 
 # Cursor (copy from shared standard)
-cp -r .agents/skills/tanstack-fullstack-pattern ~/.cursor/skills/
+cp -r .agents/skills/tanstack-promptable-fullstack-app-template ~/.cursor/skills/
 
 # Claude Code (copy from shared standard)
-cp -r .agents/skills/tanstack-fullstack-pattern ~/.claude/skills/
+cp -r .agents/skills/tanstack-promptable-fullstack-app-template ~/.claude/skills/
 ```
 
 To regenerate after editing the canonical source:
diff --git a/scripts/skills/buildSkills.test.ts b/scripts/skills/buildSkills.test.ts
index c1801a0..5e4beb2 100644
--- a/scripts/skills/buildSkills.test.ts
+++ b/scripts/skills/buildSkills.test.ts
@@ -24,8 +24,8 @@ afterEach(async () => {
 	await Promise.all(createdDirs.splice(0).map((dir) => rm(dir, { recursive: true, force: true })))
 })
 
-const validSkill = `id: tanstack-fullstack-pattern
-title: TanStack Fullstack Pattern
+const validSkill = `id: tanstack-promptable-fullstack-app-template
+title: TanStack Promptable Fullstack App Template
 summary: Apply the TanStack Start fullstack architectural pattern with interface-first boundaries.
 projectName: TanStack AI-Promptable Full-Stack Template
 projectSummary: A production-ready TanStack Start template designed to make internal tools AI promptable by default.
@@ -61,7 +61,7 @@ examples:
   - input: Add a new domain entity to the template
     output: Update schema, repository interfaces, server functions, routes, and AI tools
 content: |
-  # TanStack Fullstack Pattern
+  # TanStack Promptable Fullstack App Template
 
   Example content.
 `
@@ -76,17 +76,17 @@ describe('buildSkills', () => {
 		const parsedRegistry = JSON.parse(registry)
 		expect(parsedRegistry.skills[0].author.name).toBe('Carlos Martin-Sanchez')
 		expect(parsedRegistry.skills[0].supportedTools[0].id).toBe('windsurf')
-		expect(parsedRegistry.skills[0].outputsByFormat.skill).toBe('.agents/skills/tanstack-fullstack-pattern/SKILL.md')
+		expect(parsedRegistry.skills[0].outputsByFormat.skill).toBe('.agents/skills/tanstack-promptable-fullstack-app-template/SKILL.md')
 
 		const agentSkill = await readFile(
-			path.join(rootDir, '.agents', 'skills', 'tanstack-fullstack-pattern', 'SKILL.md'),
+			path.join(rootDir, '.agents', 'skills', 'tanstack-promptable-fullstack-app-template', 'SKILL.md'),
 			'utf8',
 		)
-		expect(agentSkill).toContain('name: tanstack-fullstack-pattern')
+		expect(agentSkill).toContain('name: tanstack-promptable-fullstack-app-template')
 	})
 
 	it('fails with a clear error when YAML is malformed', async () => {
-		const rootDir = await createWorkspace('id: tanstack-fullstack-pattern\nsummary: [broken\n')
+		const rootDir = await createWorkspace('id: tanstack-promptable-fullstack-app-template\nsummary: [broken\n')
 
 		await expect(buildSkills({ rootDir })).rejects.toThrow(/Failed to parse YAML/)
 	})
@@ -102,7 +102,7 @@ describe('buildSkills', () => {
 		const rootDir = await createWorkspace(validSkill)
 		await buildSkills({ rootDir })
 		await writeFile(
-			path.join(rootDir, '.agents', 'skills', 'tanstack-fullstack-pattern', 'SKILL.md'),
+			path.join(rootDir, '.agents', 'skills', 'tanstack-promptable-fullstack-app-template', 'SKILL.md'),
 			'drift\n',
 			'utf8',
 		)
diff --git a/scripts/skills/install.sh b/scripts/skills/install.sh
index f6c3d10..5e2fd7c 100755
--- a/scripts/skills/install.sh
+++ b/scripts/skills/install.sh
@@ -6,8 +6,8 @@
 
 set -e
 
-SKILL_NAME="tanstack-fullstack-pattern"
-SKILL_RAW_URL="https://raw.githubusercontent.com/carlosvin/tanstack-fullstack-ai-template/main/.agents/skills/tanstack-fullstack-pattern/SKILL.md"
+SKILL_NAME="tanstack-promptable-fullstack-app-template"
+SKILL_RAW_URL="https://raw.githubusercontent.com/carlosvin/tanstack-fullstack-ai-template/main/.agents/skills/tanstack-promptable-fullstack-app-template/SKILL.md"
 
 echo "Installing $SKILL_NAME skill..."
 
diff --git a/skills/dist/tanstack-fullstack-pattern.md b/skills/dist/tanstack-promptable-fullstack-app-template.md
similarity index 92%
rename from skills/dist/tanstack-fullstack-pattern.md
rename to skills/dist/tanstack-promptable-fullstack-app-template.md
index 203e4d5..a115caa 100644
--- a/skills/dist/tanstack-fullstack-pattern.md
+++ b/skills/dist/tanstack-promptable-fullstack-app-template.md
@@ -1,4 +1,4 @@
-# TanStack Fullstack Pattern
+# TanStack Promptable Fullstack App Template
 
 - Project: `TanStack AI-Promptable Full-Stack Template`
 - Project summary: A production-ready TanStack Start template designed to make internal tools AI promptable by default.
@@ -9,8 +9,8 @@
 - Documentation: https://github.com/carlosvin/tanstack-fullstack-ai-template/blob/main/skills/README.md
 - Status: stable
 - Supported tools: Windsurf [native, tested], Cursor [copy, tested], Claude Code [copy, tested]
-- Capabilities: AI promptable application architecture, Promptable-by-default AI chat in a side drawer when credentials are present, Natural language querying through repository-backed AI tools, URL-aware AI prompt context using current location and route patterns, Swappable service implementations behind stable interfaces, Layer-specific schemas with explicit mapping between repository and tool contracts, Thin routes with extracted, testable page components, Structured server-side logging with pino and automatic Sentry error forwarding, Build-time semver version injected into observability tools for release tracking, Public runtime config exposed to the browser via window.__ENV__ without relying on import.meta.env, Consistent router UX defaults for preload, stale time, and scroll restoration, Distinct-value filter discovery tools that ground AI filter values in real data, Single markdown artifact backing the help page, an AI tool, and the chat's recommended-prompt list, Parent layout routes that centralize beforeLoad guards and shared loader data for nested child routes
-- ID: `tanstack-fullstack-pattern`
+- Capabilities: AI promptable application architecture, Promptable-by-default AI chat in a side drawer when credentials are present, Natural language querying through repository-backed AI tools, URL-aware AI prompt context using current location and route patterns, Swappable service implementations behind stable interfaces, Layer-specific schemas with explicit mapping between repository and tool contracts, Thin routes with extracted, testable page components, Structured server-side logging with pino and automatic Sentry error forwarding, Build-time semver version injected into observability tools for release tracking, Public runtime config exposed to the browser via window.__ENV__ without relying on import.meta.env, Consistent router UX defaults for preload, stale time, and scroll restoration, Distinct-value filter discovery tools that ground AI filter values in real data, Single markdown artifact backing the help page, an AI tool, and the chat's recommended-prompt list, Parent layout routes that centralize beforeLoad guards and shared loader data for nested child routes, Dynamic route schema extraction for AI tool-calling and context awareness
+- ID: `tanstack-promptable-fullstack-app-template`
 - Version: `1.10.0`
 - Tags: tanstack-start, fullstack, architecture, interface-first, repository-pattern, ai-promptable
 
@@ -55,7 +55,7 @@ An interface-first fullstack architecture built on TanStack Start. The pattern d
 8. URL-as-state: filters, tabs, selections live in URL search params via `validateSearch` (Zod/ArkType). Use `loaderDeps` to feed validated search into loaders.
 9. Middleware chain: auth is global middleware, invalidation runs on mutation server functions.
 10. Mutation pattern: POST server functions chain `.middleware([requireAuthMiddleware, invalidateMiddleware])`, return domain data or throw `HttpError`. Callers normalize errors: UI via `processResponse()`, AI tools via `safeToolHandler()` / `createSafeServerTool()`.
-11. Query pattern: GET server functions throw on failure for centralized error handling.
+11. Query pattern: GET server functions throw on failure for centralized error handling. When possible, use static server functions for performance improvements.
 12. Maximize AI tool coverage: expose **every** repository method (reads and writes) via `createSafeServerTool()` so failures return `{ error, code }`. If a server function exists, it gets a tool.
 13. Router capabilities as AI client tools: expose `router.navigate()` and `router.invalidate()` as client tools via `toolDefinition()`.
 14. AI system prompt context: `buildSystemPrompt()` injects three context blocks into every AI chat request. (a) **Current User** — name, email, role from the auth middleware context (server-side; no client round-trip needed). (b) **Browser Context** — timezone, locale, and current date/time from `browserContext` sent by `ChatDrawer` (client-side). (c) **Current Location** — pathname, search params, and full URL from `browserContext`; route patterns (e.g. `/tasks/$taskId`) are matched to resolve dynamic segments. The navigation manifest mirrors `routeTree.gen.ts` and lists each route's search params. When adding routes, update `navigationManifest.ts` and add pattern-matching in `buildSystemPrompt()` for new dynamic segments.
@@ -75,11 +75,12 @@ An interface-first fullstack architecture built on TanStack Start. The pattern d
 29. Explicit agent loop depth: configure `agentLoopStrategy: maxIterations(N)` explicitly on the `chat()` call (default N=10). This caps the number of consecutive tool-calling iterations the AI can run before returning a final answer, which bounds latency, cost, and infinite-loop risk. Tune N only after measuring; do not rely on the framework default.
 30. Public runtime config bridge: expose non-secret runtime config (Sentry DSN, environment name, feature flags) via a GET server function `getPublicEnv()` and inline the result as `window.__ENV__` in the root `RootDocument` using a small `<script>` tag emitted before client JS runs. Escape `<` in the inlined JSON to avoid breaking the HTML parser. Never rely on `import.meta.env` alone for values that must differ across runtime environments built from the same bundle. See AGENTS.md section "Public Runtime Config" for the template.
 31. Router UX defaults bundle: in `src/router.tsx`, configure `defaultStaleTime` (long for read-heavy dashboards, short for mutation-heavy apps), `defaultPreload: 'intent'`, `defaultPreloadStaleTime: 0` (always-fresh preloads), `scrollRestoration: true` (with a `getScrollRestorationKey` when needed), and a `notFoundComponent` on the root route. These defaults are a single coherent bundle — do not ship a router config without them.
-32. Link wrapper preserves search: export a project-local `Link` component (e.g. `src/components/Link/Link.tsx`) that wraps TanStack Router's `Link` with `search: true` as the default. Use this wrapper for every internal link so filters, tabs, and other URL state never silently drop on navigation. Reserve raw `<a>` for external URLs.
+32. Link wrapper preserves search & styling: export a project-local `Link` component (e.g. `src/components/Link/Link.tsx`) that wraps TanStack Router's `Link` with `search: true` as the default. Use this wrapper for every internal link so filters, tabs, and other URL state never silently drop on navigation. Ensure that links are still rendered using the chosen component library's corresponding element (e.g., using `createLink` or the `component` prop) so they inherit the correct styling. Reserve raw `<a>` for external URLs.
 33. Parent layout routes deduplicate subtree work: when several child routes under the same URL prefix need the same redirect, synchronous guard, or expensive read, implement it **once** on the **parent** layout route. Use the parent's `beforeLoad` for navigation gates and synchronous checks; use the parent's `loader` (still via server functions) for shared data that every descendant needs. Child loaders fetch **only** data specific to that segment. Descendants read parent loader output with `getRouteApi('/parent/path').useLoaderData()` or `useLoaderData({ from: '/parent/path' })` — do not copy the parent's `beforeLoad` or re-fetch the parent's loader payload in each child. Structure files to match TanStack Router's layout conventions (e.g. `routes/foo/route.tsx` wrapping `routes/foo/*`).
 34. Sentry user context + feedback: when Sentry is enabled, bind the signed-in user via `Sentry.setUser({ email, username })` from the shell component as soon as the identity loads (no extra round-trip).
 35. Single markdown artifact for help + AI + suggested prompts: maintain one `docs/help.md` imported with `?raw`. Back three surfaces from it: (a) a `/help` route that renders it with `react-markdown`; (b) an AI tool that returns the content so the assistant can answer "how do I..." questions; (c) a parser that extracts `- [ ]` / `- [x]` lines as the chat's recommended-question list. Zero duplication between docs, assistant, and suggested prompts.
 36. Distinct-value filter discovery: for every enum-ish field, the repository exposes a `getDistinctValues(field)` method that flows through a GET server function into a read-only AI tool (`getDistinctStatuses`, `getDistinctCategories`, …). The AI calls these to ground filter values in real data instead of guessing. The root loader can preload the same lists for UI filter bars so UI and AI share one vocabulary.
+37. Reduce `"use client"` usage: TanStack Start supports full SSR and React Server Components. Rely on Server Components by default. Only use `"use client"` when state (`useState`), effects (`useEffect`), or browser APIs are strictly necessary. Keep client components small and at the leaf level.
 
 ## Schema Boundaries
 
@@ -188,6 +189,10 @@ A TanStack Start file-based route at `/api/chat` with two handlers:
 
 `buildSystemPrompt()` composes `BASE_SYSTEM_PROMPT` (rule 25) + navigation manifest + dynamic context (rule 14). When modifying: add tools to the array, update `BASE_SYSTEM_PROMPT` when the data model changes, add pattern-matching for new dynamic route segments. See AGENTS.md section 8 "System Prompt Generation" for the six-section prompt template.
 
+## Dynamic Route Schema Extraction for AI
+
+To help the AI navigate accurately using client tools, dynamically extract your TanStack Router configuration from `router.flatRoutes`. Map this array to extract `fullPath`, `staticData.description` (for page context), path params (from segments starting with `$`), and search params (by inspecting `validateSearch` keys). Passing this structured map in the system prompt allows the AI to discover available routes and required parameters without hallucinating URLs.
+
 ## Verification
 
 Testing setup (Vitest, Playwright, auth fixtures) and the full validation checklist are in [AGENTS.md](https://github.com/carlosvin/tanstack-fullstack-ai-template/blob/main/AGENTS.md) sections 10 and 12. Quick smoke test: `pnpm format && pnpm lint && pnpm test && pnpm build`.
diff --git a/skills/registry.json b/skills/registry.json
index b19e338..80b87a0 100644
--- a/skills/registry.json
+++ b/skills/registry.json
@@ -2,8 +2,8 @@
   "$schema": "./spec/skill.schema.json",
   "skills": [
     {
-      "id": "tanstack-fullstack-pattern",
-      "title": "TanStack Fullstack Pattern",
+      "id": "tanstack-promptable-fullstack-app-template",
+      "title": "TanStack Promptable Fullstack App Template",
       "summary": "Use when scaffolding a new TanStack Start project, adding domain entities to the fullstack template, or implementing the interface-first repository pattern with AI-promptable tools, or nested layout routes duplicate beforeLoad checks or loaders that should live on a parent route, or TanStack Router, Start, or AI behavior must be verified against current documentation instead of training data.",
       "projectName": "TanStack AI-Promptable Full-Stack Template",
       "projectSummary": "A production-ready TanStack Start template designed to make internal tools AI promptable by default.",
@@ -62,7 +62,8 @@
         "Consistent router UX defaults for preload, stale time, and scroll restoration",
         "Distinct-value filter discovery tools that ground AI filter values in real data",
         "Single markdown artifact backing the help page, an AI tool, and the chat's recommended-prompt list",
-        "Parent layout routes that centralize beforeLoad guards and shared loader data for nested child routes"
+        "Parent layout routes that centralize beforeLoad guards and shared loader data for nested child routes",
+        "Dynamic route schema extraction for AI tool-calling and context awareness"
       ],
       "triggers": [
         "fullstack template",
@@ -96,11 +97,13 @@
         "App version is extracted from package.json at build time and injected into all observability tools",
         "Dependencies are kept at latest compatible versions; exact pins are avoided unless a known incompatibility exists",
         "Non-secret runtime config is exposed via a GET server function and inlined into the document as window.__ENV__ before client JS runs",
-        "Internal navigation uses a project-local Link wrapper that preserves search params by default",
+        "Internal navigation uses a project-local Link wrapper that preserves search params by default and renders using the chosen component library's elements",
         "Shared route gates and expensive reads are implemented on the parent layout route (beforeLoad + loader); child routes avoid duplicating the same work",
-        "TanStack Router, Start, Query, Table, and AI guidance follows the official docs surfaced via npx @tanstack/cli, not memorized APIs",
+        "TanStack Router, Start, Query, Table, and AI guidance follows the official docs. Always leverage the CLI via `npx @tanstack/cli --help` to check the current docs, rather than relying on memorized APIs.",
+        "Actively ask the skill user for clarifications when needed, especially when making choices about movable pieces or architectural decisions.",
         "Every enum-ish field exposes a distinct-values AI tool so the assistant grounds filter arguments in real data",
-        "Router configures defaultStaleTime, defaultPreload, defaultPreloadStaleTime, scrollRestoration, and a root notFoundComponent"
+        "Router configures defaultStaleTime, defaultPreload, defaultPreloadStaleTime, scrollRestoration, and a root notFoundComponent",
+        "Reduce the usage of \"use client\". Rely on Server Components by default. Only use \"use client\" when state, effects, or browser APIs are strictly necessary."
       ],
       "steps": [
         "Define schemas as source of truth and infer types",
@@ -130,10 +133,10 @@
           "output": "Implement repository interface and switch factory without app-level changes"
         }
       ],
-      "source": "skills/src/tanstack-fullstack-pattern.skill.yaml",
+      "source": "skills/src/tanstack-promptable-fullstack-app-template.skill.yaml",
       "outputsByFormat": {
-        "skill": ".agents/skills/tanstack-fullstack-pattern/SKILL.md",
-        "markdown": "skills/dist/tanstack-fullstack-pattern.md"
+        "skill": ".agents/skills/tanstack-promptable-fullstack-app-template/SKILL.md",
+        "markdown": "skills/dist/tanstack-promptable-fullstack-app-template.md"
       }
     }
   ]
diff --git a/skills/src/tanstack-fullstack-pattern.skill.yaml b/skills/src/tanstack-promptable-fullstack-app-template.skill.yaml
similarity index 92%
rename from skills/src/tanstack-fullstack-pattern.skill.yaml
rename to skills/src/tanstack-promptable-fullstack-app-template.skill.yaml
index 99709a4..492eb6e 100644
--- a/skills/src/tanstack-fullstack-pattern.skill.yaml
+++ b/skills/src/tanstack-promptable-fullstack-app-template.skill.yaml
@@ -1,5 +1,5 @@
-id: tanstack-fullstack-pattern
-title: TanStack Fullstack Pattern
+id: tanstack-promptable-fullstack-app-template
+title: TanStack Promptable Fullstack App Template
 summary: >-
   Use when scaffolding a new TanStack Start project, adding domain entities to
   the fullstack template, or implementing the interface-first repository pattern
@@ -65,6 +65,7 @@ capabilities:
     recommended-prompt list
   - Parent layout routes that centralize beforeLoad guards and shared loader
     data for nested child routes
+  - Dynamic route schema extraction for AI tool-calling and context awareness
 triggers:
   - fullstack template
   - TanStack Start project
@@ -102,15 +103,17 @@ constraints:
   - Non-secret runtime config is exposed via a GET server function and inlined
     into the document as window.__ENV__ before client JS runs
   - Internal navigation uses a project-local Link wrapper that preserves search
-    params by default
+    params by default and renders using the chosen component library's elements
   - Shared route gates and expensive reads are implemented on the parent layout
     route (beforeLoad + loader); child routes avoid duplicating the same work
   - TanStack Router, Start, Query, Table, and AI guidance follows the official
-    docs surfaced via npx @tanstack/cli, not memorized APIs
+    docs. Always leverage the CLI via `npx @tanstack/cli --help` to check the current docs, rather than relying on memorized APIs.
+  - Actively ask the skill user for clarifications when needed, especially when making choices about movable pieces or architectural decisions.
   - Every enum-ish field exposes a distinct-values AI tool so the assistant
     grounds filter arguments in real data
   - Router configures defaultStaleTime, defaultPreload, defaultPreloadStaleTime,
     scrollRestoration, and a root notFoundComponent
+  - Reduce the usage of "use client". Rely on Server Components by default. Only use "use client" when state, effects, or browser APIs are strictly necessary.
 steps:
   - Define schemas as source of truth and infer types
   - "Split schemas by layer: repository input/output schemas and tool-facing
@@ -166,7 +169,7 @@ content: |
   8. URL-as-state: filters, tabs, selections live in URL search params via `validateSearch` (Zod/ArkType). Use `loaderDeps` to feed validated search into loaders.
   9. Middleware chain: auth is global middleware, invalidation runs on mutation server functions.
   10. Mutation pattern: POST server functions chain `.middleware([requireAuthMiddleware, invalidateMiddleware])`, return domain data or throw `HttpError`. Callers normalize errors: UI via `processResponse()`, AI tools via `safeToolHandler()` / `createSafeServerTool()`.
-  11. Query pattern: GET server functions throw on failure for centralized error handling.
+  11. Query pattern: GET server functions throw on failure for centralized error handling. When possible, use static server functions for performance improvements.
   12. Maximize AI tool coverage: expose **every** repository method (reads and writes) via `createSafeServerTool()` so failures return `{ error, code }`. If a server function exists, it gets a tool.
   13. Router capabilities as AI client tools: expose `router.navigate()` and `router.invalidate()` as client tools via `toolDefinition()`.
   14. AI system prompt context: `buildSystemPrompt()` injects three context blocks into every AI chat request. (a) **Current User** — name, email, role from the auth middleware context (server-side; no client round-trip needed). (b) **Browser Context** — timezone, locale, and current date/time from `browserContext` sent by `ChatDrawer` (client-side). (c) **Current Location** — pathname, search params, and full URL from `browserContext`; route patterns (e.g. `/tasks/$taskId`) are matched to resolve dynamic segments. The navigation manifest mirrors `routeTree.gen.ts` and lists each route's search params. When adding routes, update `navigationManifest.ts` and add pattern-matching in `buildSystemPrompt()` for new dynamic segments.
@@ -186,11 +189,12 @@ content: |
   29. Explicit agent loop depth: configure `agentLoopStrategy: maxIterations(N)` explicitly on the `chat()` call (default N=10). This caps the number of consecutive tool-calling iterations the AI can run before returning a final answer, which bounds latency, cost, and infinite-loop risk. Tune N only after measuring; do not rely on the framework default.
   30. Public runtime config bridge: expose non-secret runtime config (Sentry DSN, environment name, feature flags) via a GET server function `getPublicEnv()` and inline the result as `window.__ENV__` in the root `RootDocument` using a small `<script>` tag emitted before client JS runs. Escape `<` in the inlined JSON to avoid breaking the HTML parser. Never rely on `import.meta.env` alone for values that must differ across runtime environments built from the same bundle. See AGENTS.md section "Public Runtime Config" for the template.
   31. Router UX defaults bundle: in `src/router.tsx`, configure `defaultStaleTime` (long for read-heavy dashboards, short for mutation-heavy apps), `defaultPreload: 'intent'`, `defaultPreloadStaleTime: 0` (always-fresh preloads), `scrollRestoration: true` (with a `getScrollRestorationKey` when needed), and a `notFoundComponent` on the root route. These defaults are a single coherent bundle — do not ship a router config without them.
-  32. Link wrapper preserves search: export a project-local `Link` component (e.g. `src/components/Link/Link.tsx`) that wraps TanStack Router's `Link` with `search: true` as the default. Use this wrapper for every internal link so filters, tabs, and other URL state never silently drop on navigation. Reserve raw `<a>` for external URLs.
+  32. Link wrapper preserves search & styling: export a project-local `Link` component (e.g. `src/components/Link/Link.tsx`) that wraps TanStack Router's `Link` with `search: true` as the default. Use this wrapper for every internal link so filters, tabs, and other URL state never silently drop on navigation. Ensure that links are still rendered using the chosen component library's corresponding element (e.g., using `createLink` or the `component` prop) so they inherit the correct styling. Reserve raw `<a>` for external URLs.
   33. Parent layout routes deduplicate subtree work: when several child routes under the same URL prefix need the same redirect, synchronous guard, or expensive read, implement it **once** on the **parent** layout route. Use the parent's `beforeLoad` for navigation gates and synchronous checks; use the parent's `loader` (still via server functions) for shared data that every descendant needs. Child loaders fetch **only** data specific to that segment. Descendants read parent loader output with `getRouteApi('/parent/path').useLoaderData()` or `useLoaderData({ from: '/parent/path' })` — do not copy the parent's `beforeLoad` or re-fetch the parent's loader payload in each child. Structure files to match TanStack Router's layout conventions (e.g. `routes/foo/route.tsx` wrapping `routes/foo/*`).
   34. Sentry user context + feedback: when Sentry is enabled, bind the signed-in user via `Sentry.setUser({ email, username })` from the shell component as soon as the identity loads (no extra round-trip).
   35. Single markdown artifact for help + AI + suggested prompts: maintain one `docs/help.md` imported with `?raw`. Back three surfaces from it: (a) a `/help` route that renders it with `react-markdown`; (b) an AI tool that returns the content so the assistant can answer "how do I..." questions; (c) a parser that extracts `- [ ]` / `- [x]` lines as the chat's recommended-question list. Zero duplication between docs, assistant, and suggested prompts.
   36. Distinct-value filter discovery: for every enum-ish field, the repository exposes a `getDistinctValues(field)` method that flows through a GET server function into a read-only AI tool (`getDistinctStatuses`, `getDistinctCategories`, …). The AI calls these to ground filter values in real data instead of guessing. The root loader can preload the same lists for UI filter bars so UI and AI share one vocabulary.
+  37. Reduce `"use client"` usage: TanStack Start supports full SSR and React Server Components. Rely on Server Components by default. Only use `"use client"` when state (`useState`), effects (`useEffect`), or browser APIs are strictly necessary. Keep client components small and at the leaf level.
 
   ## Schema Boundaries
 
@@ -299,6 +303,10 @@ content: |
 
   `buildSystemPrompt()` composes `BASE_SYSTEM_PROMPT` (rule 25) + navigation manifest + dynamic context (rule 14). When modifying: add tools to the array, update `BASE_SYSTEM_PROMPT` when the data model changes, add pattern-matching for new dynamic route segments. See AGENTS.md section 8 "System Prompt Generation" for the six-section prompt template.
 
+  ## Dynamic Route Schema Extraction for AI
+
+  To help the AI navigate accurately using client tools, dynamically extract your TanStack Router configuration from `router.flatRoutes`. Map this array to extract `fullPath`, `staticData.description` (for page context), path params (from segments starting with `$`), and search params (by inspecting `validateSearch` keys). Passing this structured map in the system prompt allows the AI to discover available routes and required parameters without hallucinating URLs.
+
   ## Verification
 
   Testing setup (Vitest, Playwright, auth fixtures) and the full validation checklist are in [AGENTS.md](https://github.com/carlosvin/tanstack-fullstack-ai-template/blob/main/AGENTS.md) sections 10 and 12. Quick smoke test: `pnpm format && pnpm lint && pnpm test && pnpm build`.
diff --git a/skills/tanstack-fullstack-pattern/SKILL.md b/skills/tanstack-fullstack-pattern/SKILL.md
deleted file mode 100644
index 1701731..0000000
--- a/skills/tanstack-fullstack-pattern/SKILL.md
+++ /dev/null
@@ -1,161 +0,0 @@
----
-name: tanstack-fullstack-pattern
-description: 'Use when scaffolding a new TanStack Start project, adding domain
-  entities to the fullstack template, or implementing the interface-first
-  repository pattern with AI-promptable tools. Project: TanStack AI-Promptable
-  Full-Stack Template. Triggers on "fullstack template", "TanStack Start
-  project", "repository pattern", "interface-first", "new app scaffold".'
----
-
-> This file is generated from `skills/src/*.skill.yaml`. Do not edit manually.
-# TanStack Fullstack Pattern
-
-An interface-first fullstack architecture built on TanStack Start. The pattern defines clear interface boundaries between layers -- interfaces are rigid, implementations are swappable.
-
-## Pattern Overview
-
-- Zero-config development with seed implementations and swappable service layers
-- AI promptability by exposing every repository method (reads and writes) as tools
-- End-to-end type safety from schema-first definitions with explicit layer boundaries
-
-## Rigid Rules (Must Follow)
-
-1. Interface-first services: every external service (database, AI, observability) is accessed through an interface.
-2. End-to-end type safety via schemas: every boundary uses a Zod/ArkType schema as the type source (`z.infer<>`). Never hand-write `type` for wire data. Service interfaces (`ReadRepository`, `AIAdapterService`, etc.) are hand-written contracts -- they define behaviour, not wire shapes.
-3. Three schema layers: repository (DB-shaped), server-function / AI-tool (API-shaped, shared), router search-param (URL-shaped). Mappers translate between layers.
-4. Repository contracts use repository-layer schemas only.
-5. Server functions and AI tools share the same tools-layer schemas (`.inputValidator(Schema)` / `toolDefinition({ inputSchema })`). Both parse with `Schema.parse(args)`.
-6. AI and UI interact only with tools-layer schemas; they must not depend directly on repository schemas.
-7. Loaders-first data fetching: fetch route data in loaders through server functions.
-8. URL-as-state: filters, tabs, selections live in URL search params via `validateSearch` (Zod/ArkType). Use `loaderDeps` to feed validated search into loaders.
-9. Middleware chain: auth is global middleware, invalidation runs on mutation server functions.
-10. Mutation pattern: POST server functions chain `.middleware([requireAuthMiddleware, invalidateMiddleware])` and return normalized `{ data, error }`.
-11. Query pattern: GET server functions throw on failure for centralized error handling.
-12. Maximize AI tool coverage: expose **every** repository method (reads and writes) via `createSafeServerTool()` so failures return `{ error, code }`. If a server function exists, it gets a tool.
-13. Router capabilities as AI client tools: expose `router.navigate()` and `router.invalidate()` as client tools via `toolDefinition()`.
-14. AI chat context is URL-aware: pass current location to `/api/chat`; keep the navigation manifest aligned with routes.
-15. JSDoc on exports: every exported function, interface, type, and constant gets a JSDoc comment stating *what* and *why*.
-16. Chat persists across navigation: render `ChatDrawer` at the root layout level so messages survive route changes.
-17. AI renders rich markdown: use `react-markdown` + `remark-gfm` for tables, code blocks, links. Internal paths render as Router `Link` components; the AI uses markdown links (e.g. `[Pending tasks](/tasks?status=pending)`) for in-app navigation.
-
-## Schema Boundaries
-
-`Route search schema -> loader -> tools schema -> server fn -> mapping -> repo schema -> repo impl`
-
-`repo output -> mapping -> tools schema -> AI or UI`
-
-**Layer 1 — Repository schemas (DB-shaped):** internal to the repository, no `.describe()` needed. Define in `src/services/schemas/repository.ts` (target pattern -- currently all schemas live in `schemas.ts`). Infer types with `z.infer<>`.
-
-**Layer 2 — Server-function / AI-tool schemas (API-shaped):** shared by `createServerFn` and `toolDefinition`. Add `.describe()` on every field -- descriptions flow into JSON Schema for the AI.
-
-```typescript
-// src/services/schemas/schemas.ts
-const TaskInputSchema = z.object({
-  title: z.string().min(1).describe('Short title'),
-  status: TaskStatusSchema.default('pending').describe('Current status'),
-  assignee: z.string().optional().describe('Assignee email'),
-})
-```
-
-**Layer 3 — Router search-param schemas (URL-shaped):** defined locally in route files via `validateSearch`. Fields are always optional.
-
-```typescript
-// src/routes/tasks/index.tsx
-const TasksSearchSchema = z.object({
-  status: z.enum(TASK_STATUSES).optional(),
-  priority: z.enum(TASK_PRIORITIES).optional(),
-  search: z.string().optional(),
-})
-export const Route = createFileRoute('/tasks/')({
-  validateSearch: TasksSearchSchema,
-  loaderDeps: ({ search }) => search,
-  loader: ({ deps }) => getTasks({ data: deps }),
-})
-```
-
-**Type-safe mapping:** use `Schema.parse()` between layers so mismatches are caught at runtime (e.g. `TaskRepoInputSchema.parse(toolInput)`).
-
-## Interface Contracts
-
-Repository interfaces use repository-layer types only (never tools-layer schemas). `AIAdapterService` and `ObservabilityService` follow the same interface-first pattern -- see their `types.ts` files.
-
-```typescript
-interface ReadRepository {
-  getTasks(filter?: TaskRepoFilter): Promise<TaskRepoOutput[]>
-  getTask(id: string): Promise<TaskRepoOutput | null>
-  getDistinctValues(field: string): Promise<string[]>
-  getUserProfile(email: string): Promise<UserProfile | null>
-}
-interface WritableRepository {
-  createTask(input: TaskRepoInput, createdBy?: string): Promise<TaskRepoOutput>
-  updateTask(id: string, input: Partial<TaskRepoInput>): Promise<TaskRepoOutput | null>
-  deleteTask(id: string): Promise<boolean>
-}
-```
-
-## Styling and UI (Mantine)
-
-- Use Mantine components and styling props (`c`, `fw`, `size`, `variant`, responsive object syntax) before custom CSS.
-- Design tokens (colors, fonts, spacing, radius) go in `createTheme()` at `__root.tsx`.
-- CSS Modules only when Mantine props cannot express the style; use `--mantine-color-*` variables. All components must support light and dark schemes.
-
-## Auth and Middleware
-
-- `authMiddleware` (global) extracts JWT from configurable header (`AUTH_HEADER_NAME`) and provides typed `context.user` / `context.userProfile`.
-- `requireAuthMiddleware` chains auth; POST mutations require it, GET queries stay unauthenticated. Guards: `requireAuth(context)` throws 401, `requireGroup(context, group)` throws 403.
-- Custom authorization: composable middleware chaining `authMiddleware` + `invalidateMiddleware` on POST server functions.
-
-## Migration / Build Workflow
-
-1. **Schemas**: repo-layer schemas in `repository.ts`, tools-layer in `schemas.ts` (with `.describe()`), mappers via `Schema.parse()`.
-2. **Repository**: interfaces in `types.ts` (repo-layer types only), seed + production implementations.
-3. **Server functions**: GET queries + POST mutations in `serverFns.ts` with `.inputValidator(ToolSchema)`.
-4. **AI tools**: every server function gets a `toolDefinition` + `createSafeServerTool()`; client tools (`navigate`, `invalidateRouter`) wired in `ChatDrawer.tsx`.
-5. **Middleware + manifest**: register auth + invalidation in `start.ts`; keep `navigationManifest.ts` aligned with routes.
-6. **Routes**: `validateSearch` (Zod/ArkType), `loaderDeps`, loaders calling server functions.
-7. **Chat + tests**: pass `browserContext` location to `/api/chat`; E2E specs in `e2e/` against seed repository.
-
-## Looking Up TanStack Documentation
-
-Use `npx @tanstack/cli` to fetch up-to-date docs instead of relying on training data. Run `--help` for all commands.
-
-## AI Chat Pipeline
-
-- Server tools use `toolDefinition` from `@tanstack/ai` and call the same exported server functions as route loaders. Args typed via `Schema.parse(args)` since `.server()` types args as `unknown`.
-- `POST /api/chat` (`src/routes/api/chat.ts`) uses SSE streaming and the auth middleware context.
-- Keep the system prompt updated when the data model or routes change.
-
-### Client Tools (Router Capabilities for AI)
-
-Client tools are definition-only in `tools.ts` (no `.server()`) and wired in the browser via `.client()` and `clientTools()` from `@tanstack/ai-client`:
-
-```typescript
-// tools.ts — definition only
-export const navigateToolDef = toolDefinition({
-  name: 'navigate',
-  inputSchema: NavigateInputSchema, // mirrors route search schemas
-  outputSchema: z.object({ success: z.boolean() }),
-})
-// ChatDrawer.tsx — browser wiring
-const navigateClient = navigateToolDef.client((args) => {
-  const input = NavigateInputSchema.parse(args)
-  router.navigate({ to: input.to, search: input.search ?? undefined })
-  return { success: true }
-})
-const tools = clientTools(navigateClient, invalidateClient)
-```
-
-## Observability
-
-- `ObservabilityService` interface in `src/services/observability/types.ts`; Sentry and no-op implementations with factory.
-- Server init: `instrument.server.mjs`; client init: `src/router.tsx`. Usage: `getObservability().startSpan('name', fn)`.
-- To swap providers: implement `ObservabilityService`, update factory, replace `instrument.server.mjs`.
-
-## Post-Setup Verification
-
-Run in order: `pnpm install && pnpm update` (latest compatible versions), `pnpm format && pnpm lint` (Biome, zero errors), `pnpm test` (at least one passing), `pnpm build` (production build succeeds).
-
-## Testing
-
-- **Unit**: Vitest + jsdom + Testing Library; `renderWithProviders()` wraps MantineProvider. Co-located as `*.test.ts(x)`.
-- **E2E**: Playwright (Chromium), `REPOSITORY_TYPE=seed`, specs in `e2e/*.spec.ts`. Auth fixture provides `authedPage` / `authedContext` via unsigned JWTs.