Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →smithersai/smithers-what
Summarize what happened in a run or node: a cheap fast agent narrates the recorded facts (deterministic recap when no agent is available). Run `smithers what --help` for usage details.
Passed 16 of 21 test cases with the skill, and 4 of 21 without it.
and 10 more in the full report
13 fixed4 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
I want to explain why step 'build-docker' failed in our workflow run 'run-881'. What CLI invocation scopes the recap to just that step?
| Checked | Without skill | With skill |
|---|---|---|
| The command specifies smithers what run-881 --node build-docker. | Missed | Passed |
The instructions your model reads when the skill loads.
Summarize what happened in a run or node: a cheap fast agent narrates the recorded facts (deterministic recap when no agent is available).
| Name | Type | Required | Description |
|---|---|---|---|
runId | string | no | Run ID to explain (default: latest run) |
| Flag | Type | Default | Description |
|---|---|---|---|
--node | string | Node ID: explain one node instead of the whole run | |
--iteration | number | Loop iteration number (default: latest iteration) | |
--json | boolean | false | Output structured JSON (summary, agentId, source, facts) |
--timeout | number | Narrator agent timeout in seconds (default 60) |
test cases passed, vs 4 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.