Passed 10 of 15 test cases with the skill, and 4 of 15 without it.
Without skill27%
With skill64%
Checks it passed that the model alone missed
Uses caveman cloud traces show tr-883912 --spans
Identifies caveman_plan as the MCP tool for daily headroom
Specifies the --workflow flag for caveman cloud traces search
and 7 more in the full report
9 fixed5 passed either way7 still failing1 broke
Pass-rate lift
+36 pp
Tokens
+6%
Agent turns
0%
Response time
-35%
Model gemini-3.6-flashMeasured 9/4/2026v114 of 22 cases passed with skill · 15 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 9
Prompt
When searching traces via the Caveman CLI to find the highest spending requests, which command-line flag orders the results by total expense?
What was checked, without and with the skill
Checked
Without skill
With skill
Uses --sort total_cost_usd with --dir desc in the CLI trace search command
Missed
Passed
case-10 · gemini-3.6-flash · 9/4/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md134 linessingle file
Review Caveman evidence
Act as a read-only operator. Build conclusions from current Caveman data, not
from repository guesses. Never start, approve, cancel, or roll back an
experiment from this skill.
Hard rules
Keep these buckets separate:
measured provider-complete list-price cost;
inferred daily headroom;
verified ledger savings;
evidence cost.
Never add or relabel them.
Do not fetch prompt, completion, tool, or artifact payloads unless the user
explicitly asks for payload review. Metadata, spans, timing, models, token
counts, status, and optimizer attribution are enough for the default review.
Scope every read to the project selected by Caveman context. Never supply an
organization id.
Empty results are evidence of no current signal, not zero cost or zero risk.
Cite trace ids and exact time windows used. Do not claim a cause from an
aggregate alone.
Step 1 — Load context
Prefer MCP:
caveman_context {}
CLI fallback:
caveman cloud whoami
caveman cloud projects list
Stop if login or project selection is missing. Ask the user to run
caveman login or select a project; never guess.