Update AI feature docs and fix assistant API links

ai/llmstxt.mdx

@@ -1,6 +1,6 @@
 ---
 title: "llms.txt"
 description: "Automatically generate llms.txt and llms-full.txt files to help AI tools index and understand your documentation."
 keywords: ["llms.txt", "LLM indexing", "AEO", "GEO", "content discovery"]
 ---
 
@@ -11,14 +11,19 @@
 Mintlify automatically hosts an `llms.txt` file at the root of your project that lists all available pages in your documentation. This file is always up to date and requires zero maintenance. You can optionally add a custom `llms.txt` file to the root of your project.
 
 <Note>
   If your site requires authentication, `llms.txt` and `llms-full.txt` also require authentication to view. LLMs and AI tools that cannot authenticate into your site cannot access these files. The files exclude pages that belong to [user groups](/deploy/authentication-setup#control-access-with-groups).
 </Note>
 
-View your `llms.txt` by appending `/llms.txt` to your documentation site's URL.
+View your `llms.txt` by appending `/llms.txt` to your documentation site's URL. Mintlify also hosts the file at `/.well-known/llms.txt` for compatibility with tools that follow the `.well-known` convention.
 
 <PreviewButton href="https://mintlify.com/docs/llms.txt">Open the llms.txt for this site.</PreviewButton>
 
+Mintlify adds HTTP headers to every page response so AI tools can discover your `llms.txt` files without prior knowledge of their location:
+
+- `Link: </llms.txt>; rel="llms-txt", </llms-full.txt>; rel="llms-full-txt"`: Follows the standard HTTP `Link` header format for resource discovery.
+- `X-Llms-Txt: /llms.txt`: A convenience header for tools that check for `llms.txt` support.
+
 ## llms.txt structure
 
 An `llms.txt` file is a plain Markdown file that contains:
 
@@ -26,34 +31,37 @@
 - **Structured content sections** with links and a description of each page in your documentation.
 - **API specification links** to your OpenAPI and AsyncAPI specs, if your documentation includes them.
 
-The `llms.txt` file lists your pages alphabetically in the order they appear in your repository, starting from the root directory.
+The `llms.txt` file lists your pages alphabetically in the order they appear in your repository, starting from the root directory. Page links in the `llms.txt` file include a `.md` extension so AI tools can fetch the Markdown version of each page directly.
 
 Each page's description comes from the `description` field in its frontmatter. Descriptions truncate at 300 characters and the first line break. For API reference pages, the description also includes the specification information from the `openapi` or `api` frontmatter field. Pages without a `description` field appear in the `llms.txt` file without a description.
 
+This structured approach allows LLMs to efficiently process your documentation at a high level and locate relevant content for user queries, improving the accuracy and speed of AI-assisted documentation searches.
+
 ```mdx Example llms.txt
 # Site title
 
 ## Docs
 
-- [API](https://example.com/docs/api): Endpoint list and usage
-- [Install](https://example.com/docs/install): Setup steps
-- [Getting started](https://example.com/docs/start): Intro guide
+- [API](https://example.com/docs/api.md): Endpoint list and usage
+- [Install](https://example.com/docs/install.md): Setup steps
+- [Getting started](https://example.com/docs/start.md): Intro guide
 
-## API specifications
+## OpenAPI Specs
 
 - [openapi](https://example.com/docs/openapi.json)
+
+## AsyncAPI Specs
+
 - [asyncapi](https://example.com/docs/asyncapi.yaml)
 ```
 
-This structured approach allows LLMs to efficiently process your documentation at a high level and locate relevant content for user queries, improving the accuracy and speed of AI-assisted documentation searches.
-
 ## llms-full.txt
 
 The `llms-full.txt` file combines your entire documentation site into a single file as context for AI tools and LLM indexing.
 
 Mintlify automatically hosts an `llms-full.txt` file at the root of your project. View your `llms-full.txt` by appending `/llms-full.txt` to your documentation site's URL. Mintlify also hosts the file at `/.well-known/llms-full.txt` for compatibility with tools that follow the `.well-known` convention.
 
 <PreviewButton href="https://mintlify.com/docs/llms-full.txt">Open the llms-full.txt for this site.</PreviewButton>
 
 ## Custom files
 

ai/markdown-export.mdx

@@ -8,7 +8,7 @@
 
 Markdown provides structured text that AI tools can process more efficiently than HTML, which results in better response accuracy, faster processing times, and lower token usage.
 
 Mintlify automatically generates Markdown versions of pages that are optimized for AI tools and external integrations.
 
 ## .md URL extension
 
@@ -16,6 +16,14 @@
 
 <PreviewButton href="https://mintlify.com/docs/ai/markdown-export.md">Open this page as Markdown</PreviewButton>
 
+## Accept header
+
+Send a request with `Accept: text/markdown` or `Accept: text/plain` to any page URL to receive the Markdown version instead of HTML. This is useful for AI tools and integrations that programmatically fetch documentation content.
+
+```bash
+curl -H "Accept: text/markdown" https://mintlify.com/docs/ai/markdown-export
+```
+
 ## Keyboard shortcut
 
 Press <kbd>Command</kbd> + <kbd>C</kbd> (<kbd>Ctrl</kbd> + <kbd>C</kbd> on Windows) to copy a page as Markdown to your clipboard.

ai/skillmd.mdx

@@ -24,7 +24,7 @@
 ## Use `skill.md` files with agents
 
 <Note>
-  If you use a [reverse proxy](/deploy/reverse-proxy), configure it to forward `/skill.md` and `/.well-known/skills/*` paths (with caching disabled) to your Mintlify subdomain.
+  If you use a [reverse proxy](/deploy/reverse-proxy), configure it to forward `/skill.md` and `/.well-known/skills/*` paths to your Mintlify subdomain.
 </Note>
 
 Agents can process your `skill.md` with the [skills CLI](https://www.npmjs.com/package/skills).
@@ -43,7 +43,7 @@
 
 Mintlify generates a `skill.md` file following the [agentskills.io specification](https://agentskills.io/specification). The generated file includes:
 
 - **Metadata**: Project name, description, and version.
 - **Capabilities**: What agents can accomplish with your product.
 - **Skills**: Specific actions organized by category.
 - **Workflows**: Step-by-step procedures for common tasks.
@@ -79,4 +79,30 @@
   author: mintlify
   version: "1.0"
 ---
-```
+```
+
+## Skills discovery endpoints
+
+Mintlify hosts a skills directory at `/.well-known/skills/` that agents can use to discover and fetch your skill files programmatically.
+
+### Skills index
+
+`GET /.well-known/skills/index.json` returns a JSON manifest listing all available skills:
+
+```json
+{
+  "skills": [
+    {
+      "name": "my-product",
+      "description": "A brief description of what your skill does.",
+      "files": ["SKILL.md"]
+    }
+  ]
+}
+```
+
+The `name` field is a URL-safe slug derived from the `name` in your `skill.md` frontmatter.
+
+### Individual skill files
+
+`GET /.well-known/skills/{name}/skill.md` returns the `skill.md` file for a specific skill identified by its slugified name from the index.

api/assistant/create-assistant-message-v2.mdx

@@ -17,7 +17,7 @@ keywords:
 <Info>
   The assistant message v2 endpoint is compatible with **AI SDK v5+**. If you
   use AI SDK v4, use the [assistant message v1
-  endpoint](/api-reference/assistant/create-assistant-message) instead.
+  endpoint](/api/assistant/create-assistant-message) instead.
 </Info>
 
 ## Integration with `useChat`

api/assistant/create-assistant-message.mdx

@@ -8,7 +8,7 @@ keywords: [ "assistant message", "embed", "chat", "integrate", "ai sdk v4" ]
 <Badge color="orange">Deprecated</Badge>
 
 <Info>
-  The assistant message v1 endpoint is compatible with **AI SDK v4**. If you use AI SDK v5 or later, use the [assistant message v2 endpoint](/api-reference/assistant/create-assistant-message-v2) instead.
+  The assistant message v1 endpoint is compatible with **AI SDK v4**. If you use AI SDK v5 or later, use the [assistant message v2 endpoint](/api/assistant/create-assistant-message-v2) instead.
 </Info>
 
 ## Integration with `useChat`