diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
new file mode 100644
index 0000000..0f5c3ff
--- /dev/null
+++ b/.claude-plugin/marketplace.json
@@ -0,0 +1,18 @@
+{
+  "metadata": {
+    "description": "Agent Skills for visual AI tasks including image understanding, video processing, document extraction, and multi-modal generation using VLM Run's Orion agent",
+    "version": "1.0.0"
+  },
+  "name": "vlmrun-cli-skill",
+  "owner": {
+    "name": "VLM Run"
+  },
+  "plugins": [
+    {
+      "description": "Use the VLM Run CLI to interact with Orion visual AI agent. Process images, videos, and documents with natural language. Supports image understanding/generation, object detection, OCR, video summarization, document extraction, and visual AI chat.",
+      "name": "vlmrun-cli-skill",
+      "skills": "./",
+      "source": "../.claude/skills/vlmrun-cli-skill"
+    }
+  ]
+}
diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json
new file mode 100644
index 0000000..48dedfb
--- /dev/null
+++ b/.claude-plugin/plugin.json
@@ -0,0 +1,22 @@
+{
+  "author": {
+    "name": "VLM Run"
+  },
+  "description": "Agent Skills for visual AI tasks including image understanding, video processing, document extraction, and multi-modal generation using VLM Run's Orion agent",
+  "homepage": "https://vlm.run",
+  "keywords": [
+    "vlmrun",
+    "visual-ai",
+    "image-understanding",
+    "video-processing",
+    "document-extraction",
+    "ocr",
+    "image-generation",
+    "video-generation",
+    "multi-modal"
+  ],
+  "license": "Apache-2.0",
+  "name": "vlmrun-cli-skill",
+  "repository": "https://github.com/vlm-run/vlmrun-python-sdk",
+  "version": "1.0.0"
+}
diff --git a/.claude/SKILL.md b/.claude/skills/vlmrun-cli-skill/SKILL.md
similarity index 100%
rename from .claude/SKILL.md
rename to .claude/skills/vlmrun-cli-skill/SKILL.md
diff --git a/README.md b/README.md
index b923e2d..c1e4b90 100644
--- a/README.md
+++ b/README.md
@@ -136,6 +136,36 @@ vlmrun chat "Analyze this invoice" -i invoice.pdf -k ./accounting-skills/ -k ./i
 
 To create a persistent server-side skill, use `vlmrun skills upload ./my-skill/`.
 
+### Claude Code
+
+Install the VLM Run CLI skill directly in [Claude Code](https://docs.anthropic.com/en/docs/claude-code) via the plugin marketplace:
+
+1. Register the repository as a plugin marketplace:
+
+```
+/plugin marketplace add vlm-run/vlmrun-python-sdk
+```
+
+2. Install the skill:
+
+```
+/plugin install vlmrun-cli-skill@vlm-run/vlmrun-python-sdk
+```
+
+3. Configure your API key and base URL using the CLI (get your key from [app.vlm.run](https://app.vlm.run)):
+
+```bash
+vlmrun config init
+vlmrun config set --api-key <your-api-key>
+vlmrun config show
+```
+
+4. Verify the skill is loaded by asking Claude Code (requires restart):
+
+```
+What skills are available in the /vlmrun-cli-skill?
+```
+
 ## 🔗 Quick Links
 
 * 💬 Need help? Email us at [support@vlm.run](mailto:support@vlm.run) or join our [Discord](https://discord.gg/AMApC2UzVY)
diff --git a/vlmrun/cli/_cli/chat.py b/vlmrun/cli/_cli/chat.py
index 4b178b5..026f183 100644
--- a/vlmrun/cli/_cli/chat.py
+++ b/vlmrun/cli/_cli/chat.py
@@ -499,7 +499,8 @@ def chat(
     ),
     skill_dirs: Optional[List[Path]] = typer.Option(
         None,
-        "--skill", "-k",
+        "--skill",
+        "-k",
         help=(
             "Path to a skill directory (must contain SKILL.md). Repeatable. "
             "The skill is sent inline with the request (no server-side upload). "