Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →juliusbrussee/caveman-manage
Inspect Caveman Cloud's eval-gated experiment lifecycle and block unsafe execution.
Passed 7 of 12 test cases with the skill, and 7 of 12 without it.
and 1 more in the full report
4 fixed8 passed either way5 still failing5 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need to inspect experiment exp-1102 state and results. Which interface protocol should be attempted first before falling back to CLI commands?
| Checked | Without skill | With skill |
|---|---|---|
| Prefers MCP read tool over CLI commands for initial data load. | Missed | Passed |
The instructions your model reads when the skill loads.
Treat every lifecycle change as a production control action. Read current state and results, then report one supported recommendation or block. Current agent MCP is intentionally read-only: control-api does not yet enforce a complete lifecycle transition table and evidence gate atomically.
verified_savings. Only active real
traffic plus provider-causal, provider-complete ledger evidence can do that.<action>:<experiment_id> strings are agent-generatable and are not proof of
human intent.cave_snake_code.Prefer MCP:
caveman_context {}
caveman_experiment_get {"action":"get","experiment_id":"<id>"}
caveman_experiment_get {"action":"results","experiment_id":"<id>"}
Use {"action":"list"} when the user has not named an id.
CLI fallback:
caveman cloud experiments list
caveman cloud experiments show <id>
caveman cloud experiments results <id>
test cases passed, vs 7 / 12 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.