Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →smithersai/smithers-oneshot
Run one well-scoped goal with a strong agent in the background, with optional review and a live UI. Run `smithers oneshot --help` for usage details.
Passed 13 of 17 test cases with the skill, and 2 of 17 without it.
and 15 more in the full report
15 fixed3 passed either way5 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.
Execute a single task to update package lock files, explicitly disabling review for this run.
| Checked | Without skill | With skill |
|---|---|---|
| Includes the --review off option. | Missed | Passed |
The instructions your model reads when the skill loads.
Run one well-scoped goal with a strong agent in the background, with optional review and a live UI. The kimi seat runs Kimi K3; review runs on Sol at high effort.
| Name | Type | Required | Description |
|---|---|---|---|
goal | string | no | Goal to complete; required unless using --status or a preference setter |
| Flag | Type | Default | Description |
|---|---|---|---|
--goal-file | string | Read a long goal from a file | |
--model | string | auto | Model slot (sol, terra, luna, kimi, fable, opus, sonnet) or canonical model id |
--agent | enum | codex|kimi|claude-code|opencode | |
--review | enum | stored | Review preference for this run (on|off) |
--set-review | enum | Persist the review preference (on|off) | |
--set-trivial | enum | Persist trivial-task routing (direct|oneshot) | |
--status | boolean | false | Print usable agents, model chain, and stored preferences as JSON |
--cwd | string | . | Working directory for the task |
--preflight | enum | auto | Dirty-working-copy preflight (auto|warn|off) |
--detach | boolean | true | Run in the background; --detach false runs in the foreground |
--interactive | boolean | false | Open the full-screen TUI monitor |
--status before first use; when no usable agent is detected, use the direct or workflow route instead.--review on, "oneshot without review" adds --review off..smithers/workflows/oneshot.tsx and its dashboard with .smithers/ui/oneshot.tsx.--preflight auto warns on a dirty --cwd and asks the agent to triage it before goal work; warn omits agent instructions and off skips assessment.test cases passed, vs 2 / 17 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.