caveman-evidence-review
Review Caveman Cloud evidence read-only: costs, Cave Score, Cave Plan, workflows, traces, latency, errors, compression, routing, and verified savings. Use when the user asks what Caveman found, where LLM spend goes, why cost or quality changed, which workflows need attention, or asks for a trace or analytics review. Prefer Caveman MCP tools; fall back to CLI JSON.
Install
git clone https://github.com/JuliusBrussee/caveman /tmp/caveman && ln -s /tmp/caveman/skills/caveman-evidence-review ~/.claude/skills/caveman-evidence-reviewFrom README
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: CLI fallback: Stop if login or project selection is missing.
More from this repo
caveman-compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
caveman-discover
Used to find every LLM workflow in the current repository and label it, so Caveman Cloud groups spend by what the code...
cavecrew
Decision guide for delegating to caveman-style subagents.