docs: clarify ask-first approach for skill/memory creation
This commit is contained in:
parent
22dbdeffef
commit
2a87dfafcf
1 changed files with 3 additions and 1 deletions
|
|
@ -160,7 +160,9 @@ Available tools:
|
||||||
- `get_context`, `get_conventions`, `get_snippets`
|
- `get_context`, `get_conventions`, `get_snippets`
|
||||||
- `get_memory`, `add_memory`, `create_skill`
|
- `get_memory`, `add_memory`, `create_skill`
|
||||||
|
|
||||||
**Auto-coaching**: The MCP server sends instructions to the AI on connection, teaching it how and when to use these tools to learn and improve over time. This means the AI will proactively call `get_context()`, `add_memory()`, and `create_skill()` without you needing to explicitly tell it each time.
|
**Auto-coaching**: The MCP server sends instructions to the AI on connection, teaching it how and when to use these tools to learn and improve over time.
|
||||||
|
|
||||||
|
**Important**: The AI will **propose** creating skills/memories when it identifies valuable patterns, but **will not execute without your permission**. You'll see suggestions like "I could create a skill for this pattern. Should I?" and you can approve or decline. This gives you full control while still building the knowledge base.
|
||||||
|
|
||||||
## Migration from v1
|
## Migration from v1
|
||||||
|
|
||||||
|
|
|
||||||
Loading…
Add table
Reference in a new issue