agents: use onyx skill proactively for company-knowledge questions
This commit is contained in:
parent
8c7300e899
commit
53a11aa9f1
1 changed files with 8 additions and 0 deletions
|
|
@ -1,5 +1,13 @@
|
||||||
@./AGENTS.md
|
@./AGENTS.md
|
||||||
|
|
||||||
|
## Firmenwissen (onyx)
|
||||||
|
|
||||||
|
- For questions about internal processes, tools, or "wie machen wir X
|
||||||
|
bei Seibert", check the company knowledge first: invoke the `onyx`
|
||||||
|
skill and `search`, then answer from the passages with source links.
|
||||||
|
- Prefer `search` (answer yourself); use `answer`/`chat` only when I
|
||||||
|
explicitly want Onyx's generated answer or a persistent session.
|
||||||
|
|
||||||
## Subagents
|
## Subagents
|
||||||
|
|
||||||
Spawn subagents to (a) isolate context-heavy work from the main thread, or (b) parallelize independent subtasks. Before spawning, ask: *could `Bash`/`Grep`/`Read` do this directly?* Subagents have overhead — skip the middleman for mechanical lookups.
|
Spawn subagents to (a) isolate context-heavy work from the main thread, or (b) parallelize independent subtasks. Before spawning, ask: *could `Bash`/`Grep`/`Read` do this directly?* Subagents have overhead — skip the middleman for mechanical lookups.
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue