Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →smithersai/smithers-optimize
Run GEPA prompt optimization over a workflow eval suite and write an optimized prompt artifact. Run `smithers optimize --help` for usage details.
Passed 17 of 19 test cases with the skill, and 2 of 19 without it.
and 23 more in the full report
17 fixed3 passed either way3 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.
We want to optimize workflow `src/gen_docs.tsx` with cases `evals/docs.json`. Limit overall case evaluation concurrency to 2, and cap the per-workflow task concurrency to 1. Provide the CLI command.
| Checked | Without skill | With skill |
|---|---|---|
| Includes --concurrency 2 | Missed | Passed |
| Includes --maxConcurrency 1 | Missed | Passed |
The instructions your model reads when the skill loads.
Run GEPA prompt optimization over a workflow eval suite and write an optimized prompt artifact.
| Name | Type | Required | Description |
|---|---|---|---|
workflow | string | yes | Workflow ID (from smithers workflow list) or path to a .tsx workflow file |
| Flag | Type | Default | Description |
|---|---|---|---|
--cases | string | JSON or JSONL eval case file | |
--suite | string | Stable suite ID used in run IDs and report paths | |
--provider | string | openai-api | GEPA patch generator provider |
--model | string | Optimizer model for provider-backed GEPA | |
--artifact | string | Write the optimized prompt artifact to this path | |
--reportDir | string | Directory for baseline and optimized eval reports | |
--minImprovement | number | 0.000001 | Minimum required absolute score improvement |
--maxCases | number | Run only the first N cases | |
--concurrency | number | 1 | Number of eval cases to run at once |
--maxConcurrency | number | Per-workflow max task concurrency | |
--root | string | Tool sandbox root directory | |
--log | boolean | true | Enable NDJSON event log file output |
--logDir | string | NDJSON event logs directory | |
--allowNetwork | boolean | false | Allow bash tool network requests |
--maxOutputBytes | number | Max bytes a single tool call can return | |
--toolTimeoutMs | number | Max wall-clock time per tool call in ms |
test cases passed, vs 2 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.