prompts: make reasoning/memory skill loading an explicit first action
Previous wording was passive. Now gives an explicit command with a concrete tool call to run before the first response. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
parent
cf9567ff5b
commit
34b901233c
|
|
@ -111,9 +111,13 @@ Search before acting: `grep -A2 "keyword" ollie/t/idx`
|
|||
|
||||
Skills are domain-specific knowledge files that extend your capabilities for specific domains. Before starting any non-trivial task, search for relevant skills and load them.
|
||||
|
||||
Always load these at the start of every session:
|
||||
- `ollie/sk/reasoning.md` — how and when to reason before acting
|
||||
- `ollie/sk/memory.md` — how and when to persist and recall information
|
||||
Before your first response in any session, read these files:
|
||||
|
||||
```
|
||||
cat ollie/sk/reasoning.md ollie/sk/memory.md
|
||||
```
|
||||
|
||||
Do this before doing anything else, including responding to the user.
|
||||
|
||||
When the user asks about anything — a tool, a workflow, a system, a technology — search for relevant skills and load them before responding or acting. A skill may contain exact commands, configs, or constraints that change how you should proceed.
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue