Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →smithersai/smithers-events
Query run event history with filters, grouping, and NDJSON output. Run `smithers events --help` for usage details.
Passed 20 of 22 test cases with the skill, and 4 of 22 without it.
and 21 more in the full report
17 fixed4 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
I want to inspect scorer events for run 'run-eval-77' using the Smithers event query tool. What is the exact event category name?
| Checked | Without skill | With skill |
|---|---|---|
| Uses '--type scorer' for filtering. | Missed | Passed |
The instructions your model reads when the skill loads.
Query node/run lifecycle history by default; pass --raw for raw agent chunks and all event types.
| Name | Type | Required | Description |
|---|---|---|---|
runId | string | yes | Run ID to query |
| Flag | Type | Default | Description |
|---|---|---|---|
--node | string | Filter events by node ID | |
--type | string | Filter by event category (agent, approval, frame, memory, node, openapi, output, revert, run, sandbox, scorer, snapshot, supervisor, timer, token, tool-call, workflow) | |
--since | string | Filter to a recent duration window (e.g. 5m, 2h; a bare number is milliseconds, and logs --since is an event sequence number instead) | |
--limit | number | Maximum events to display (default 1000, max 100000) | |
--json | boolean | false | Output NDJSON for piping |
--groupBy | string | Group output by "node" or "attempt" | |
--watch | boolean | false | Watch mode: append new events as they arrive |
--interval | number | 2 | Watch poll interval in seconds |
--raw | boolean | false | Include raw agent chunk/tool history instead of the default lifecycle-only view |
test cases passed, vs 4 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.