無料GitHub で公開

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.

vaila-multimodaltoolbox/vaila

インストール方法を見る

含まれるファイル（1）

SKILL.md3.8 KB

SKILL.md（原文）

インストールする前に、エージェントに与えられる指示の中身を確認できます。

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.

Step 2 — Establish baseline

Use caveman_report for:

overview
costs
score
workflows
verified_savings

Then use caveman_plan for ranked daily headroom. If question is narrow, skip unrelated reports. Read shortest set that can answer it.

CLI fallback:

caveman cloud costs
caveman cloud score
caveman cloud plan --json

State report window and basis before interpreting direction.

Step 3 — Test the leading explanation with traces

Use caveman_trace_search. 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.

CLI fallback:

caveman cloud traces search \
  --workflow <slug> \
  --from <RFC3339> \
  --to <RFC3339> \
  --sort total_cost_usd \
  --dir desc \
  --limit 25

Step 4 — Inspect representative traces

Call caveman_trace_get for a small number of high-signal trace ids. Inspect request and span metadata, latency, status, token counts, cache state, applied optimizers, and model route. Keep payload retrieval off.

CLI fallback:

caveman cloud traces show <trace-id> --spans

Step 5 — Report

Use this shape:

## Caveman evidence review

Scope: <project> · <from> to <to>
Measured cost: <value and basis>
Verified savings: <ledger value, kept separate>
Inferred headroom: <per-day band, kept separate>

Findings:
1. <finding> — <aggregate evidence> — traces <ids>
2. <finding> — <aggregate evidence> — traces <ids>

Unproven:
- <plausible explanation lacking a control, trace, or eval>

Next read-only check:
- <one bounded query>

Possible action:
- <proposal only; use caveman-manage for read-only lifecycle review and safety gate>

If data is missing, name missing signal and stop at strongest supported statement. Never turn a catalog subtotal into an invoice or an experiment result into verified savings.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

ログインしてレビューを書く

同じリポジトリのスキル

概要と使いどころ

agent-platform-alert-configuration

無料

Configures best-practice alerting policies for AI agents using OpenTelemetry (OTel) metrics, generating output as Terraform (.tf) configuration files. Use when analyzing, writing, or deploying alerting policies to monitor agent latency, error rates, token usage, and quality metrics. Don't use for standard infrastructure monitoring unrelated to AI agents, or when the agent is not instrumented with OpenTelemetry (for Reliability, Cost, Safety, Security alerts). NOTE: Reliability, Cost, Safety, and Security alerts use generic OTel metrics and work across runtimes (such as Cloud Run, Vertex AI). Quality alerts rely on Vertex AI Online Monitors and are strictly bound to Vertex AI deployments.

日本語の概要は準備中です。原文の説明を表示しています。