Agent skill · juliusbrussee
caveman-evidence-review
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.
What it needs
About 2k tokens when loaded.
What this skill does
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 1. Keep these buckets separate: measured provider-complete list-price cost; inferred daily headroom; verified ledger savings; evidence cost. Never add or relabel them. 2. 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. 3. Scope every read to the project selected by Caveman context. Never supply an organization id. 4. Empty results are evidence of no current signal, not zero cost or zero risk. 5. Cite trace ids and exact time windows used. Do not claim a cause from an aggregate alone. Step 1 — Load context Prefer MCP: CLI fallback: Stop if login or project selection is missing. Ask the user to run caveman login or select a project; never guess. Step 2 — Establish baseline Use cavemanreport for: overview costs score workflows verifiedsavings Then use cavemanplan for ranked daily headroom. If question is narrow, skip unrelated reports. Read shortest set that can answer it. CLI fallback: State report window and basis before interpreting direction. Step 3 — Test the leading explanation with traces Use cavemantracesearch. Choose a bounded window and closed filters: workflow, agent, model, provider, error code, runtime mode, cache status, optimization id, status class, token/cost/latency bounds, compression, or monitor verdict. Useful groupings: workflow — find jobs driving cost or failures; model — compare model mix; session — isolate retry or loop behavior; ungrouped — identify exact traces. Compare a suspect cohort with a control cohort or earlier bounded window. Do not infer causality from one expensive trace. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills juliusbrussee/caveman-evidence-review