Install any skill in seconds. Free to start, no credit card required.
Get Started Free →juliusbrussee/caveman-optimize
Turn Caveman's exact report-only repository observations into an operator-chosen optimization candidate with a paired baseline/candidate evaluation.
Passed 9 of 15 test cases with the skill, and 3 of 15 without it.
and 11 more in the full report
9 fixed4 passed either way8 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
The command JSON response contains both a data array with active lifecycle items and a report_only_observations array. Which array should we select candidates from for diagnostic profile evaluation?
| Checked | Without skill | With skill |
|---|---|---|
| Reads exclusively from the report_only_observations array. | Missed | Passed |
| Ignores entries in the lifecycle data array. | Missed | Passed |
The instructions your model reads when the skill loads.
Use Caveman's report-only observations as diagnostic input. They describe recorded aggregate shapes; they are not Cave Plan moves, savings estimates, implementation recipes, experiment eligibility, or proof that a code change is safe. Keep the workflow operator-chosen and evidence-first.
Require a logged-in Caveman CLI session and run:
caveman opportunities list
Read only the report_only_observations array. Do not select from the lifecycle
data array. Preserve each server-provided title and observation verbatim.
Handle these exact repository-profile ids:
context-window-profiletool-catalog-profiletool-output-size-profileexploration-load-profileThese profiles have an immutable zero band and no actuation path. Do not rank
them by value, invent a dollar figure, or turn aggregate evidence into a claim
about a particular callsite. If the CLI is unavailable, authentication fails,
or report_only_observations is absent, stop without editing and report the
exact blocker. Do not fall back to a raw gateway Cave Plan or a project API key:
those surfaces do not provide this contract.
Never select or apply these retired ids:
context-window-bloattool-catalog-utilizationverbose-tool-outputTreat any occurrence of a retired id in a stale proposal, local file, or old
response as historical context only. Never revive its money, recipe, or
lifecycle claim. If the only actionable-looking item is unlabeled-traffic,
test cases passed, vs 3 / 15 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.