fix: tighten model fallback + docs (#1762) (thanks @senoldogann)

docs/tools/creating-skills.md

@@ -8,7 +8,7 @@ A skill is a directory containing a `SKILL.md` file (which provides instructions
 ## Step-by-Step: Your First Skill
 
 ### 1. Create the Directory
-Skills live in your workspace, usually `~/clawd/skills/`. Create a new folder for your skill:
+Skills live in your workspace at `<workspace>/skills` (default: `~/clawd/skills`). Create a new folder for your skill:
 ```bash
 mkdir -p ~/clawd/skills/hello-world
 ```
@@ -23,18 +23,18 @@ description: A simple skill that says hello.
 ---
 
 # Hello World Skill
-When the user asks for a greeting, use the `echo` tool to say "Hello from your custom skill!".
+When the user asks for a greeting, use the `exec` tool to run `echo "Hello from your custom skill!"`.
 ```
 
 ### 3. Add Tools (Optional)
-You can define custom tools in the frontmatter or instruct the agent to use existing system tools (like `bash` or `browser`).
+You can define custom tools in the frontmatter or instruct the agent to use existing system tools (like `exec` or `web`).
 
 ### 4. Refresh Clawdbot
-Ask your agent to "refresh skills" or restart the gateway. Clawdbot will discover the new directory and index the `SKILL.md`.
+If the skills watcher is enabled (default), changes are picked up automatically. Otherwise restart the gateway or start a new session to refresh the skills snapshot.
 
 ## Best Practices
 - **Be Concise**: Instruct the model on *what* to do, not how to be an AI.
-- **Safety First**: If your skill uses `bash`, ensure the prompts don't allow arbitrary command injection from untrusted user input.
+- **Safety First**: If your skill uses `exec`, ensure the prompts don't allow arbitrary command injection from untrusted user input.
 - **Test Locally**: Use `clawdbot agent --message "use my new skill"` to test.
 
 ## Shared Skills