Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →optim-agent/mini-plan
Use mini-plan for subtle low-risk repo changes needing one alignment question before execution; exclude direct implementation-only, factual/explanation, trivial, or explicit no-plan requests.
Passed 9 of 22 test cases with the skill, and 3 of 22 without it.
and 10 more in the full report
9 fixed0 passed either way10 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need a plan to introduce token-bucket rate limiting on public endpoints. Apply a minimal planning flow asking 1 initial question, defaulted to Reviewer but allowing direct execution jump.
| Checked | Without skill | With skill |
|---|---|---|
| Asks a single initial planning question. | Passed | Passed |
| Recommends Reviewer. | Passed | Passed |
| Includes the exact choice label Jump to executor. | Missed | Passed |
The instructions your model reads when the skill loads.
Read and follow ../optim-plans/SKILL.md, treating the request as if it named mini-plan.
Depth: mini-plan means 1 planning question and zero or one refinement round. The refinement choice still recommends Reviewer; choosing Jump to executor records skip-refinement-execute and directly approves execution.
test cases passed, vs 3 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.