pleaseai · amondnet · Jun 30, 2026 · Jun 29, 2026
diff --git a/plugins/agent-browser/.agents/skills/agent-browser/SKILL.md b/plugins/agent-browser/.agents/skills/agent-browser/SKILL.md
@@ -7,24 +7,20 @@ hidden: true
 
 # agent-browser
 
-Fast browser automation CLI for AI agents. Chrome/Chromium via CDP with
-accessibility-tree snapshots and compact `@eN` element refs.
+Fast browser automation CLI for AI agents. Chrome/Chromium via CDP with accessibility-tree snapshots and compact `@eN` element refs.
 
 Install: `npm i -g agent-browser && agent-browser install`
 
 ## Start here
 
-This file is a discovery stub, not the usage guide. Before running any
-`agent-browser` command, load the actual workflow content from the CLI:
+This file is a discovery stub, not the usage guide. Before running any `agent-browser` command, load the actual workflow content from the CLI:
 
 ```bash
 agent-browser skills get core             # start here — workflows, common patterns, troubleshooting
 agent-browser skills get core --full      # include full command reference and templates
 ```
 
-The CLI serves skill content that always matches the installed version,
-so instructions never go stale. The content in this stub cannot change
-between releases, which is why it just points at `skills get core`.
+The CLI serves skill content that always matches the installed version, so instructions never go stale. The content in this stub cannot change between releases, which is why it just points at `skills get core`.
 
 ## Specialized skills
 
@@ -38,8 +34,7 @@ agent-browser skills get vercel-sandbox    # agent-browser inside Vercel Sandbox
 agent-browser skills get agentcore         # AWS Bedrock AgentCore cloud browsers
 ```
 
-Run `agent-browser skills list` to see everything available on the
-installed version.
+Run `agent-browser skills list` to see everything available on the installed version.
 
 ## Why agent-browser
 

diff --git a/plugins/agent-browser/agent/skills/agent-browser/SKILL.md b/plugins/agent-browser/agent/skills/agent-browser/SKILL.md
@@ -3,24 +3,20 @@ description: "Browser automation CLI for AI agents. Use when the user needs to i
 ---
 # agent-browser
 
-Fast browser automation CLI for AI agents. Chrome/Chromium via CDP with
-accessibility-tree snapshots and compact `@eN` element refs.
+Fast browser automation CLI for AI agents. Chrome/Chromium via CDP with accessibility-tree snapshots and compact `@eN` element refs.
 
 Install: `npm i -g agent-browser && agent-browser install`
 
 ## Start here
 
-This file is a discovery stub, not the usage guide. Before running any
-`agent-browser` command, load the actual workflow content from the CLI:
+This file is a discovery stub, not the usage guide. Before running any `agent-browser` command, load the actual workflow content from the CLI:
 
 ```bash
 agent-browser skills get core             # start here — workflows, common patterns, troubleshooting
 agent-browser skills get core --full      # include full command reference and templates
 ```
 
-The CLI serves skill content that always matches the installed version,
-so instructions never go stale. The content in this stub cannot change
-between releases, which is why it just points at `skills get core`.
+The CLI serves skill content that always matches the installed version, so instructions never go stale. The content in this stub cannot change between releases, which is why it just points at `skills get core`.
 
 ## Specialized skills
 
@@ -34,8 +30,7 @@ agent-browser skills get vercel-sandbox    # agent-browser inside Vercel Sandbox
 agent-browser skills get agentcore         # AWS Bedrock AgentCore cloud browsers
 ```
 
-Run `agent-browser skills list` to see everything available on the
-installed version.
+Run `agent-browser skills list` to see everything available on the installed version.
 
 ## Why agent-browser
 

diff --git a/plugins/agent-browser/skills-lock.json b/plugins/agent-browser/skills-lock.json
@@ -5,7 +5,7 @@
       "source": "vercel-labs/agent-browser",
       "sourceType": "github",
       "skillPath": "skills/agent-browser/SKILL.md",
-      "computedHash": "228f87d57035100d9dc6efcfc05aafd4b6e3962adacaa04b8217ab2fadb15dc8"
+      "computedHash": "ecc7641aea05f85ca3b11e7759d32aaf52fe05946ab4b63739c7bf78a41237a2"
     },
     "dogfood": {
       "source": "vercel-labs/agent-browser",

diff --git a/plugins/ai-sdk/.agents/skills/ai-sdk/SKILL.md b/plugins/ai-sdk/.agents/skills/ai-sdk/SKILL.md
@@ -5,6 +5,8 @@ description: 'Answer questions about the AI SDK and help build AI-powered featur
 
 ## Prerequisites
 
+This information is for AI SDK 7. Compare to version in `node_modules/ai/package.json`. If the versions don't match, warn the user.
+
 Before searching docs, check if `node_modules/ai/docs/` exists. If not, install **only** the `ai` package using the project's package manager (e.g., `pnpm add ai`).
 
 Do not install other packages at this stage. Provider packages (e.g., `@ai-sdk/openai`) and client packages (e.g., `@ai-sdk/react`) should be installed later when needed based on user requirements.

diff --git a/plugins/ai-sdk/.agents/skills/ai-sdk/references/common-errors.md b/plugins/ai-sdk/.agents/skills/ai-sdk/references/common-errors.md
@@ -169,24 +169,26 @@ const result = await generateText({
 });
 ```
 
-## `toDataStreamResponse` → `toUIMessageStreamResponse`
+## `toDataStreamResponse` → `createUIMessageStreamResponse`
 
-When using `useChat` on the frontend, use `toUIMessageStreamResponse()` instead of `toDataStreamResponse()`. The UI message stream format is designed to work with the chat UI components and handles message state correctly.
+When using `useChat` on the frontend, use `createUIMessageStreamResponse()` with `toUIMessageStream()` instead of `toDataStreamResponse()`. The UI message stream format is designed to work with the chat UI components and handles message state correctly.
 
 ```typescript
 // ❌ Incorrect (when using useChat)
 const result = streamText({
   // config
 });
 
-return result.toDataStreamResponse(); // deprecated for useChat: use toUIMessageStreamResponse
+return result.toDataStreamResponse(); // deprecated for useChat: use createUIMessageStreamResponse
 
 // ✅ Correct
 const result = streamText({
   // config
 });
 
-return result.toUIMessageStreamResponse();
+return createUIMessageStreamResponse({
+  stream: toUIMessageStream({ stream: result.stream }),
+});
 ```
 
 ## Removed managed input state in `useChat`

diff --git a/plugins/ai-sdk/agent/skills/ai-sdk/SKILL.md b/plugins/ai-sdk/agent/skills/ai-sdk/SKILL.md
@@ -3,6 +3,8 @@ description: "Answer questions about the AI SDK and help build AI-powered featur
 ---
 ## Prerequisites
 
+This information is for AI SDK 7. Compare to version in `node_modules/ai/package.json`. If the versions don't match, warn the user.
+
 Before searching docs, check if `node_modules/ai/docs/` exists. If not, install **only** the `ai` package using the project's package manager (e.g., `pnpm add ai`).
 
 Do not install other packages at this stage. Provider packages (e.g., `@ai-sdk/openai`) and client packages (e.g., `@ai-sdk/react`) should be installed later when needed based on user requirements.

diff --git a/plugins/ai-sdk/agent/skills/ai-sdk/references/common-errors.md b/plugins/ai-sdk/agent/skills/ai-sdk/references/common-errors.md
@@ -169,24 +169,26 @@ const result = await generateText({
 });
 ```
 
-## `toDataStreamResponse` → `toUIMessageStreamResponse`
+## `toDataStreamResponse` → `createUIMessageStreamResponse`
 
-When using `useChat` on the frontend, use `toUIMessageStreamResponse()` instead of `toDataStreamResponse()`. The UI message stream format is designed to work with the chat UI components and handles message state correctly.
+When using `useChat` on the frontend, use `createUIMessageStreamResponse()` with `toUIMessageStream()` instead of `toDataStreamResponse()`. The UI message stream format is designed to work with the chat UI components and handles message state correctly.
 
 ```typescript
 // ❌ Incorrect (when using useChat)
 const result = streamText({
   // config
 });
 
-return result.toDataStreamResponse(); // deprecated for useChat: use toUIMessageStreamResponse
+return result.toDataStreamResponse(); // deprecated for useChat: use createUIMessageStreamResponse
 
 // ✅ Correct
 const result = streamText({
   // config
 });
 
-return result.toUIMessageStreamResponse();
+return createUIMessageStreamResponse({
+  stream: toUIMessageStream({ stream: result.stream }),
+});
 ```
 
 ## Removed managed input state in `useChat`

diff --git a/plugins/ai-sdk/skills-lock.json b/plugins/ai-sdk/skills-lock.json
@@ -5,7 +5,7 @@
       "source": "vercel/ai",
       "sourceType": "github",
       "skillPath": "skills/use-ai-sdk/SKILL.md",
-      "computedHash": "2249889eb47ef0f61c4dba4cf2afe01c1c8dd793bb4c24230347c1ab909bb7dd"
+      "computedHash": "2fdbb3c2c9c0e19c64f03f2febd4fec134473e2fe7443f7ebe67870eba5b3c75"
     }
   }
 }
diff --git a/plugins/antfu/.agents/skills/antfu/SKILL.md b/plugins/antfu/.agents/skills/antfu/SKILL.md
@@ -3,7 +3,7 @@ name: antfu
 description: Anthony Fu's opinionated tooling and conventions for JavaScript/TypeScript projects. Use when setting up new projects, configuring ESLint/Prettier alternatives, monorepos, library publishing, or when the user mentions Anthony Fu's preferences.
 metadata:
   author: Anthony Fu
-  version: "2026.05.01"
+  version: "2026.06.22"
 ---
 
 ## Coding Practices
@@ -30,6 +30,13 @@ metadata:
 - **Explicit return types**: Declare return types explicitly when possible
 - **Avoid complex inline types**: Extract complex types into dedicated `type` or `interface` declarations
 
+### Explicitness
+
+Favor explicit, traceable code over implicit "magic". A reader (human or agent) should be able to follow where every name comes from without running tooling.
+
+- **Explicit imports**: Prefer explicit `import` statements. Avoid auto-imports — when a framework provides them (e.g. Nuxt/Nitro), turn them off for new projects (see [app-development](references/app-development.md)).
+- **No path aliases by default**: Use relative imports (`./foo`, `../bar`). Only use path aliases (`@/`, `~/`, `#imports`, etc.) when they are *already* configured in the project; don't introduce new ones for greenfield code.
+
 ### Comments
 
 - **Avoid unnecessary comments**: Code should be self-explanatory
@@ -139,6 +146,6 @@ Avoid the default catalog. Catalog names can be adjusted per project needs.
 |-------|-------------|-----------|
 | ESLint Config | Framework support, formatters, rule overrides, VS Code settings | [antfu-eslint-config](references/antfu-eslint-config.md) |
 | Project Setup | .gitignore, GitHub Actions, VS Code extensions | [setting-up](references/setting-up.md) |
-| App Development | Vue/Nuxt/UnoCSS conventions and patterns | [app-development](references/app-development.md) |
+| App Development | Vue/Nuxt/UnoCSS conventions, auto-import control, Storybook component testing | [app-development](references/app-development.md) |
 | Library Development | tsdown bundling, pure ESM publishing | [library-development](references/library-development.md) |
 | Monorepo | pnpm workspaces, centralized alias, Turborepo | [monorepo](references/monorepo.md) |
diff --git a/plugins/antfu/.agents/skills/antfu/references/app-development.md b/plugins/antfu/.agents/skills/antfu/references/app-development.md
@@ -12,6 +12,45 @@ description: Vue/Nuxt/UnoCSS application conventions. Use when building web apps
 | SPA, client-only, library playgrounds | Vite + Vue |
 | SSR, SSG, SEO-critical, file-based routing, API routes | Nuxt |
 
+## Nuxt Conventions
+
+### Disable Auto-imports (new projects)
+
+Prefer explicit imports over auto-imports so every symbol is traceable. For new Nuxt projects, turn off both app-side (Nuxt) and server-side (Nitro) auto-imports in `nuxt.config.ts`:
+
+```ts
+// nuxt.config.ts
+export default defineNuxtConfig({
+  imports: {
+    autoImport: false, // disable composable/util auto-imports
+  },
+  components: {
+    dirs: [], // disable component auto-imports
+  },
+  nitro: {
+    imports: false, // disable server-side (Nitro) auto-imports
+  },
+})
+```
+
+Framework helpers stay available through the `#imports` alias — import them explicitly:
+
+```ts
+import { computed, ref } from '#imports'
+```
+
+| Option | Effect |
+|--------|--------|
+| `imports.autoImport: false` | Stops auto-importing `~/composables` and `~/utils` (and framework APIs like `ref`) |
+| `components.dirs: []` | Stops auto-importing components from `~/components` |
+| `nitro.imports: false` | Stops auto-importing in the server (`server/utils`, etc.) |
+
+> Standalone Nitro projects already default to `imports: false` — leave server auto-imports off rather than enabling them.
+
+### Path Aliases
+
+Nuxt's built-in aliases (`~/`, `@/`, `#imports`) are already configured, so they're fine to use. Don't add custom path aliases for new code — prefer relative imports otherwise.
+
 ## Vue Conventions
 
 | Convention | Preference |
@@ -43,3 +82,9 @@ const props = withDefaults(defineProps<Props>(), {
 const emit = defineEmits<Emits>()
 </script>
 ```
+
+### Storybook for Components
+
+Set up Storybook for component development. Expressing each state as a story keeps components side-effect-free and their states predictable.
+
+Run the story tests in CI. Prefer the Vitest addon (`@storybook/addon-vitest`) so stories run as part of the existing `vitest` run (see [setting-up](setting-up.md)).
diff --git a/plugins/antfu/.agents/skills/antfu/references/monorepo.md b/plugins/antfu/.agents/skills/antfu/references/monorepo.md
@@ -62,6 +62,8 @@ See the dedicated Turborepo skill for detailed configuration.
 
 ## Centralized Alias
 
+Path aliases should be explicit and centralized — this is the deliberate "already set up" case. Outside of these configured aliases, prefer relative imports; don't sprinkle ad-hoc aliases across the codebase.
+
 For better DX across Vite, Nuxt, Vitest configs, create a centralized `alias.ts` at project root:
 
 ```ts

diff --git a/plugins/antfu/.agents/skills/antfu/references/setting-up.md b/plugins/antfu/.agents/skills/antfu/references/setting-up.md
@@ -45,7 +45,7 @@ on: [pull_request]
 
 jobs:
   autofix:
-    uses: sxzz/workflows/.github/workflows/autofix.yml@v1
+    uses: sxzz/workflows/.github/workflows/autofix.yml@main
     permissions:
       contents: read
 ```
@@ -67,7 +67,7 @@ permissions: {}
 
 jobs:
   unit-test:
-    uses: sxzz/workflows/.github/workflows/unit-test.yml@v1
+    uses: sxzz/workflows/.github/workflows/unit-test.yml@main
 ```
 
 ### Release Workflow
@@ -84,7 +84,7 @@ on:
 
 jobs:
   release:
-    uses: sxzz/workflows/.github/workflows/release.yml@v1
+    uses: sxzz/workflows/.github/workflows/release.yml@main
     with:
       publish: true
     permissions:

diff --git a/plugins/antfu/agent/skills/antfu/SKILL.md b/plugins/antfu/agent/skills/antfu/SKILL.md
@@ -1,6 +1,6 @@
 ---
 description: "Anthony Fu's opinionated tooling and conventions for JavaScript/TypeScript projects. Use when setting up new projects, configuring ESLint/Prettier alternatives, monorepos, library publishing, or when the user mentions Anthony Fu's preferences."
-metadata: {"author":"Anthony Fu","version":"2026.05.01"}
+metadata: {"author":"Anthony Fu","version":"2026.06.22"}
 ---
 ## Coding Practices
 
@@ -26,6 +26,13 @@ metadata: {"author":"Anthony Fu","version":"2026.05.01"}
 - **Explicit return types**: Declare return types explicitly when possible
 - **Avoid complex inline types**: Extract complex types into dedicated `type` or `interface` declarations
 
+### Explicitness
+
+Favor explicit, traceable code over implicit "magic". A reader (human or agent) should be able to follow where every name comes from without running tooling.
+
+- **Explicit imports**: Prefer explicit `import` statements. Avoid auto-imports — when a framework provides them (e.g. Nuxt/Nitro), turn them off for new projects (see [app-development](references/app-development.md)).
+- **No path aliases by default**: Use relative imports (`./foo`, `../bar`). Only use path aliases (`@/`, `~/`, `#imports`, etc.) when they are *already* configured in the project; don't introduce new ones for greenfield code.
+
 ### Comments
 
 - **Avoid unnecessary comments**: Code should be self-explanatory
@@ -135,6 +142,6 @@ Avoid the default catalog. Catalog names can be adjusted per project needs.
 |-------|-------------|-----------|
 | ESLint Config | Framework support, formatters, rule overrides, VS Code settings | [antfu-eslint-config](references/antfu-eslint-config.md) |
 | Project Setup | .gitignore, GitHub Actions, VS Code extensions | [setting-up](references/setting-up.md) |
-| App Development | Vue/Nuxt/UnoCSS conventions and patterns | [app-development](references/app-development.md) |
+| App Development | Vue/Nuxt/UnoCSS conventions, auto-import control, Storybook component testing | [app-development](references/app-development.md) |
 | Library Development | tsdown bundling, pure ESM publishing | [library-development](references/library-development.md) |
 | Monorepo | pnpm workspaces, centralized alias, Turborepo | [monorepo](references/monorepo.md) |
diff --git a/plugins/antfu/agent/skills/antfu/references/app-development.md b/plugins/antfu/agent/skills/antfu/references/app-development.md
@@ -12,6 +12,45 @@ description: Vue/Nuxt/UnoCSS application conventions. Use when building web apps
 | SPA, client-only, library playgrounds | Vite + Vue |
 | SSR, SSG, SEO-critical, file-based routing, API routes | Nuxt |
 
+## Nuxt Conventions
+
+### Disable Auto-imports (new projects)
+
+Prefer explicit imports over auto-imports so every symbol is traceable. For new Nuxt projects, turn off both app-side (Nuxt) and server-side (Nitro) auto-imports in `nuxt.config.ts`:
+
+```ts
+// nuxt.config.ts
+export default defineNuxtConfig({
+  imports: {
+    autoImport: false, // disable composable/util auto-imports
+  },
+  components: {
+    dirs: [], // disable component auto-imports
+  },
+  nitro: {
+    imports: false, // disable server-side (Nitro) auto-imports
+  },
+})
+```
+
+Framework helpers stay available through the `#imports` alias — import them explicitly:
+
+```ts
+import { computed, ref } from '#imports'
+```
+
+| Option | Effect |
+|--------|--------|
+| `imports.autoImport: false` | Stops auto-importing `~/composables` and `~/utils` (and framework APIs like `ref`) |
+| `components.dirs: []` | Stops auto-importing components from `~/components` |
+| `nitro.imports: false` | Stops auto-importing in the server (`server/utils`, etc.) |
+
+> Standalone Nitro projects already default to `imports: false` — leave server auto-imports off rather than enabling them.
+
+### Path Aliases
+
+Nuxt's built-in aliases (`~/`, `@/`, `#imports`) are already configured, so they're fine to use. Don't add custom path aliases for new code — prefer relative imports otherwise.
+
 ## Vue Conventions
 
 | Convention | Preference |
@@ -43,3 +82,9 @@ const props = withDefaults(defineProps<Props>(), {
 const emit = defineEmits<Emits>()
 </script>
 ```
+
+### Storybook for Components
+
+Set up Storybook for component development. Expressing each state as a story keeps components side-effect-free and their states predictable.
+
+Run the story tests in CI. Prefer the Vitest addon (`@storybook/addon-vitest`) so stories run as part of the existing `vitest` run (see [setting-up](setting-up.md)).
diff --git a/plugins/antfu/agent/skills/antfu/references/monorepo.md b/plugins/antfu/agent/skills/antfu/references/monorepo.md
@@ -62,6 +62,8 @@ See the dedicated Turborepo skill for detailed configuration.
 
 ## Centralized Alias
 
+Path aliases should be explicit and centralized — this is the deliberate "already set up" case. Outside of these configured aliases, prefer relative imports; don't sprinkle ad-hoc aliases across the codebase.
+
 For better DX across Vite, Nuxt, Vitest configs, create a centralized `alias.ts` at project root:
 
 ```ts
-Original file line number
+Diff line change
@@ Expand Up / @@ -62,6 +62,8 @@ See the dedicated Turborepo skill for detailed configuration. @@
     ## Centralized Alias
+    Path aliases should be explicit and centralized — this is the deliberate "already set up" case. Outside of these configured aliases, prefer relative imports; don't sprinkle ad-hoc aliases across the codebase.
     For better DX across Vite, Nuxt, Vitest configs, create a centralized `alias.ts` at project root:
     ```ts
@@ Expand Down @@