無料GitHub で公開

caveman-manage

Inspect Caveman Cloud's eval-gated experiment lifecycle and block unsafe execution. Use when the user asks to start, approve, cancel, promote, or roll back a Caveman experiment, or asks what action an experiment's evidence supports. Read evidence first; do not execute lifecycle mutations until server-authoritative transition and evidence gates ship.

vaila-multimodaltoolbox/vaila

インストール方法を見る

含まれるファイル（1）

SKILL.md4.0 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。

Manage eval-gated experiments

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.

Non-negotiable gates

A request to review, inspect, explain, or recommend authorizes reads only.
Never approve an experiment whose results are pending, whose required guardrails are absent, or whose evidence reports a breach.
Never convert experiment lift into verified_savings. Only active real traffic plus provider-causal, provider-complete ledger evidence can do that.
Never supply an organization id. Project and tenant scope come from the logged-in Caveman identity and server RBAC.
Never execute a lifecycle mutation, even after user approval. Exact <action>:<experiment_id> strings are agent-generatable and are not proof of human intent.
Unknown states and server errors fail closed. Report exact cave_snake_code.

Step 1 — Load project and experiment

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>

Stop if login, project, experiment, or results are unavailable.

Step 2 — Evaluate evidence

Report:

current lifecycle state and safety class;
control and candidate sample sizes;
quality or eval result;
latency, error, cost, retry, drop, and escalation guardrails when present;
evidence cost;
rollback or hold reason;
whether result is pending, failed, promotable, or active.

Absence is not a pass. If a required field is absent, state evidence incomplete and do not propose approval.

Step 3 — Propose one action

Allowed actions:

start — only from a startable draft or queued state with configured graders;
approve — only with complete passing evidence and a safety class the current role may approve;
cancel — stop a non-active experiment the user no longer wants;
rollback — revert an active or harmful change through the server's linked policy path. Current deployments may reject this honestly with cave_not_implemented; never describe that response as a rollback.

Show recommendation and id:

Proposed action: approve experiment 7f...
Reason: candidate passed quality and every configured guardrail.
Execution: blocked until server-authoritative lifecycle and evidence gates ship.

Do not treat earlier generic statements such as "manage it" or "do what is best" as mutation approval.

Step 4 — Block unsafe execution

Do not emit or run an executable lifecycle command. Explain that current server does not yet enforce every evidence/state transition atomically. CLI and MCP agent surfaces therefore expose experiment reads only.

Step 5 — Re-read after external operator action

If operator says they executed command, read detail and results again. Report server-observed post-state, audit or result response, and any policy-delivery status returned. Never infer success from operator intent alone.

Use this close:

Action: <action> <experiment-id>
Before: <state>
Server response: <status and cave_snake_code if any>
After: <re-read state>
Basis: experiment evidence only. Verified savings unchanged unless the signed
ledger independently records active, provider-causal real-traffic 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。