AI / OpenClaw Interview Questions
Why does OpenClaw selectively inject only relevant skills instead of loading all skills into context?
If every installed skill's full instructions were injected into every single prompt, the context window would fill up quickly with mostly irrelevant information.
- A bloated context makes it harder for the model to focus on what's actually relevant to the current task
- Unused injected content still consumes tokens, adding unnecessary cost to every single turn
- Selective injection keeps the model's attention on the specific capability needed for the task at hand, rather than sorting through dozens of unrelated skill descriptions
This mirrors a broader pattern seen across agentic AI systems generally, where dumping too much tool or capability metadata into context degrades tool selection accuracy even when each individual piece of metadata is reasonable on its own.
What would happen if every skill were injected into every prompt?
What does unused injected skill content still consume?
More Related questions...
