Core behavioral rules and skills for NanoClaw personal assistant agents. Always-on rules for communication, verification, memory, and formatting.
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
LLMs synthesize plausible answers from prior context, which can produce confident wrong reports. Memory of what should be installed is not evidence of what is installed. Recalled file paths, task state, deploy freezes and config flags can all go stale.
Tool-call success means the tool ran; it does not establish that the outcome matches the intent.