brainstorming
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).
core-engineManage core engine lifecycle via core/bin/tool-cli commands for engine-restart and engine-reload. Only use this skill when the user explicitly asks to restart or reload the engine; never trigger it automatically from another agent skill.
Independent GitHub snapshot · Automated classification · Original documentation governs
Control core engine restart/reload through socket-driven commands.
config/.env and apply changesDo not use this skill automatically from another agent skill or as an inferred follow-up action. If engine control seems helpful but the user did not ask for it, ask first instead of invoking this skill.
As an expert in your assigned roles, you must announce your actions before performing them using the following format:
As a {Role, and Role-XYZ if have more roles}, I will {action description}
This communication pattern ensures transparency and allows for human-in-the-loop oversight at key decision points.
Follow these steps in order:
Map user intent:
engine-restart: restart engine process from in-memory environment only to reload config json/json5 files if user has updated these file manuallyengine-reload: read latest .env and config into memory, then restart engine process if user has updated .env manuallyFrom repo root:
core/bin/tool-cli engine-restart
core/bin/tool-cli engine-reload
engine-restart: does not re-read .envengine-reload: re-reads .env first, then restarts--reload) and direct main.py executionReturn command output and note that active sessions may reconnect during restart.
.env was re-readengine-reload after key changes in config/.env manually