Install any skill in seconds. Free to start, no credit card required.
Get Started Free →vellum-heartbeat
Configure periodic background checklist runs
Passed 23 of 23 test cases with the skill, and 14 of 23 without it.
and 7 more in the full report
9 fixed14 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
What is the exact internal call site name used for background heartbeat executions?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies the call site as heartbeatAgent | Missed | Passed |
The instructions your model reads when the skill loads.
The heartbeat feature runs your HEARTBEAT.md checklist periodically in a background conversation. Each run, the assistant works through the checklist and flags anything that needs attention.
Edit config.json using file_edit:
heartbeat.enabled to true.heartbeat.intervalMs (milliseconds between runs, default: 3600000 = 1 hour).heartbeat.activeHoursStart and heartbeat.activeHoursEnd (0-23) to restrict runs to certain hours. Both must be set together.Example config.json heartbeat section:
{
"heartbeat": {
"enabled": true,
"intervalMs": 1800000,
"activeHoursStart": 8,
"activeHoursEnd": 22
}
}
Then edit HEARTBEAT.md with the checklist items. The assistant will work through this file each heartbeat run.
heartbeat.enabled requires an assistant restart to take effect.HEARTBEAT.md take effect on the next heartbeat run (no restart needed).Heartbeat runs use the heartbeatAgent call site, which by default resolves to the
cost-optimized profile so background checks stay cheap. Override via
llm.callSites.heartbeatAgent in workspace config (profile, provider, model,
effort, thinking — whatever the profile supports).
test cases passed, vs 14 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.