Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →smithersai/smithers-scores
View scorer results for a specific run. Run `smithers scores --help` for usage details.
Passed 19 of 21 test cases with the skill, and 6 of 21 without it.
and 12 more in the full report
14 fixed7 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
When checking scorer outputs for run run_00123, I need to isolate node node_llm_step. Should I use --node-id or --node or --filter-node? Give me the exact CLI command.
| Checked | Without skill | With skill |
|---|---|---|
| Uses the --node flag rather than --node-id or --filter-node. | Passed | Passed |
| Executes smithers scores with run_00123. | Missed | Passed |
The instructions your model reads when the skill loads.
View scorer results for a specific run.
| Name | Type | Required | Description |
|---|---|---|---|
runId | string | yes | Run ID to inspect |
| Flag | Type | Default | Description |
|---|---|---|---|
--node | string | Filter scores to a specific node ID |
test cases passed, vs 6 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.