Move every app reference from an old Hubitat device onto a new one — via Settings → Swap Device where possible, a virtual-device bridge or parking slot where the swap list blocks it, and a guided manual re-select where neither works. Use when the user wants to swap, migrate, replace, or move a device's references to a different device, re-home a device to a different hub over Hub Mesh, or asks why a device does not appear in the Swap Device list.

Safely remove a Hubitat device — enumerate where it's used, warn about the blast radius before deleting, verify references cleared after, and re-wire them onto a replacement device. Use when the user wants to remove, delete, retire, or replace a device, or asks what a device is used by before deleting it.

Fire an ordered list of Hubitat devices with a timed hold on each, so you can walk the property and bind each observation to a device id — which lamp is `Kitchen 3`, which shade is `Office Left`, which valve is irrigation zone 7. Use when the user wants to map which physical thing a device controls, identify which zone/lamp/shade/valve is which, run a set of devices one at a time in sequence, or fire devices on a timer for field verification.

Update Z-Wave device firmware on a Hubitat hub via the native zwaveJS updater — discover installed versions, find vendor-latest firmware, stage it, and batch-flash safely with a radio-hang watchdog. Use when the user wants to update/flash device firmware, check which devices are behind on firmware, or fix a device whose issue a firmware update addresses.

Manage the hubs.json config that records how to reach each Hubitat hub by IP for code operations. Actions — init a config, add a hub, set the default hub, remove a hub, list hubs. Use when the user wants to configure, register, add, or list Hubitat hubs for deploy/pull/debug.

Run the Hubitat sandbox linter on app or driver Groovy and judge each finding — real defect vs. false positive — before the code goes near a hub. Use when the user wants to lint, check, or validate Hubitat code, or automatically before deploying.

Use the hub's first-party AI (MCP) Connector Integration to read hub state and drive devices over its local MCP endpoint — connect with the bearer token, discover the live tool surface, prefer read-only tools, gate sensitive actions, and verify the mutation. Use when the user wants to control or query a Hubitat hub through its MCP server / AI connector, or asks whether an operation should go through MCP or the hub_* scripts.

Diagnose Hubitat Z-Wave and Zigbee network problems — ghost/failed nodes, packet errors, weak routes, dead or unjoined Zigbee devices, devices that stopped responding to commands, a broken hub-mesh link, an unhealthy mesh. Use when the user wants to check mesh health, find ghost nodes, debug a flaky/slow/dead Z-Wave or Zigbee device, or figure out why the radio network misbehaves.

Generate a correct Hubitat app or driver skeleton from declared capabilities, with the required lifecycle callbacks, subscription/schedule idioms, and logging conventions wired in. Use when starting a new Hubitat app or driver, or when the user asks to create/scaffold/bootstrap Hubitat Groovy code.

Onboard one or more Hubitat sensors with verification at each step — pair, confirm the built-in driver auto-selected, name by function and position, raise event retention, read the real adjustable preferences, share to the mesh and confirm the mirror, add to inactivity monitoring, acceptance-test, and reconcile the inventory. Use when the user wants to onboard, install, add, or set up sensors (soil probes, contact/motion/temperature/energy sensors) on a hub, or roll out a sensor fleet.

Set up and run offline unit tests for a Hubitat app or driver — load the script under biocomp/hubitat_ci, mock the platform executor, and assert on sendEvent/log/parse output off-hub. Use when the user wants to test, unit-test, mock, or add CI for Hubitat Groovy code.

Prepare or cancel event-specific running-late delegation, inspect running-late status, or run its native three-minute poll. Triggers: 'tell them if I am running late', 'approve lateness messages for this event', 'cancel running-late approval', 'running late status'.

Daily vehicle health watch for the Tessie overlay: wakes only when an addressable vehicle has a low unplugged battery, a Tessie credential or API failure, or unreadable state, then tells the owner what was found; otherwise stays silent. Triggers: 'tesla watch', 'vehicle health check', 'tessie watch', 'monitor my Tesla', 'low battery alert'.

Flight assist for tracked flights. Its precheck polls byAir every 2 minutes, sends templated flight notices (delay, gate change, cancellation, boarding, connection risk, inbound delay, time to leave, baggage carousel, day-before check, arrival logistics) through the host itself, and reconciles the managed calendar events. The model is never woken for a notice. Use to configure or diagnose the plugin — 'diagnose flight-assist', 'set flight-assist home base', 'configure flight-assist', 'why didn't I get a flight notice'.

Travel-data refresh bundle: TripIt → Reclaim timezone sync, refresh travel-schedule.json from the TripIt iCal feed with a two-tier Gmail freshness probe, rebuild travel-db.json, log newly-appeared trips to daily memory, then check upcoming trips for booking gaps. Runs daily; precheck-gated on travel-db.json freshness and schema currency. Triggers: 'sync trips', 'sync travel', 'update travel data', 'pull trip info', 'refresh travel schedule', 'rebuild travel db', 'check my bookings'.

Adaptive scheduler for the TripIt/byAir refresh of active-flights.json. Precheck-gated to keep byAir polling responsive on flight days and idle between travel windows. Its precheck sends the sync's notices (tracked-flight changes, sync outage and recovery) through the host itself. Action: diagnose a failed precheck run. Use when active-flights.json isn't updating, byAir polling cadence isn't matching flight density, troubleshooting flight tracking / flight notifications / flight status updates / travel schedule refresh, or setting up flight-assist on a new install. The gate predicate and threshold constants live in skills/sync-tripit/precheck.py.

Shared Python library for trip itineraries, planned positions, conference attendance windows, travel schedules, lodging, airport buffers, trip identity, home addresses and operator timezones in nanoclaw-travel. Flight-assist, drive-engine and travel-booking readers import these modules at runtime. Load when maintaining their shared travel-domain behavior; background library only, never invoke as a user workflow.

Structured workflow for shipping code via GitHub pull requests: readiness checks, PR creation, version + CHANGELOG entry (a changelog fragment where the publish workflow assigns the version, a hand bump elsewhere) for publishing repos, dual-lens automated review (the Codex policy reviewer for rule compliance + an advisory Claude quality lane where the repo runs it), watching the PR to a terminal verdict, addressing feedback, merging on green without asking, and post-merge cleanup and publish verification. Use when the user wants to open a pull request, ship code, release, merge a branch, or handle post-merge cleanup.