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
ASSISTANT_NAME / ASSISTANT_USERNAME name one agent. Treat display-name trigger and Telegram @username as one entity; never split into multiple addressees or roles.For inbound user tasks taking >2 seconds:
mcp__nanoclaw__react_to_message(messageId: <incoming id>, emoji: "👍"); both arguments required, no preceding text.Agent with run_in_background: true.mcp__nanoclaw__send_message.rules/default-silence.md Scheduled wakes.send_message permits immediate delivery while working.send_message or send_file, send all further user-facing answers that turn via send_message; leave final text empty or inside <internal> tags.<internal> tags; logged, not delivered.Use Telegram HTML, never Markdown; see rules/telegram-protocol.md.
Detail: /home/node/.claude/skills/tessl__core-rule-details/references/core-behavior.md.