scenario

スター16

フォーク6

更新日2026年2月12日 16:28

Create and execute scenario YAML files for architecture what-if predictions.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

brainqub3

brainqub3/agent-labs

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

scenario

Steps

Resolve the SAS empirical baseline first:
- Use SAS architecture run metrics (derived_metrics.json -> P) from the relevant comparison batch.
- If multiple SAS runs exist in the batch, pick one deterministic baseline and state which run id was used.
- Do not use a hypothetical/model-predicted SAS point as the comparison baseline.
Collect model intelligence I, tool count, and candidate architectures.
Populate YAML with priors or explicit overrides, setting P_SA from the resolved SAS run baseline.
Run brainqub3 scenario run --scenario <path>.
Report scenario results relative to the SAS run baseline:
- delta_vs_sas = P_architecture - P_SAS_run_baseline
Save comparison outputs for dashboard/report consumption.

このリポジトリの他の Skills

同じリポジトリ

arena

brainqub3/agent-labs

Prepare and run evaluator-gated SAS and MAS experiments with explicit batch control and mandatory elasticity calibration for scenario scaling.

2026-02-1116

cleanup-reset

brainqub3/agent-labs

Reset local experiment state to a fresh slate by clearing runs, prediction outputs, scaling snapshots, and database index files under data/.

2026-02-1116

task-author

brainqub3/agent-labs

Create or repair Brainqub3 task packages that must pass evaluator tests before runs, including both fabricated instances and user-provided data workflows.

2026-02-1016

eval-builder

brainqub3/agent-labs

Build or repair task evaluators and evaluator tests with deterministic-first strategy.

2026-02-0916

report

brainqub3/agent-labs

Generate markdown reports with observed metrics, predicted metrics, and architecture recommendations.

2026-02-0916

name	scenario
description	Create and execute scenario YAML files for architecture what-if predictions.
allowed-tools	["Read","Edit","Bash"]

scenario

Steps

Resolve the SAS empirical baseline first:
- Use SAS architecture run metrics (derived_metrics.json -> P) from the relevant comparison batch.
- If multiple SAS runs exist in the batch, pick one deterministic baseline and state which run id was used.
- Do not use a hypothetical/model-predicted SAS point as the comparison baseline.
Collect model intelligence I, tool count, and candidate architectures.
Populate YAML with priors or explicit overrides, setting P_SA from the resolved SAS run baseline.
Run brainqub3 scenario run --scenario <path>.
Report scenario results relative to the SAS run baseline:
- delta_vs_sas = P_architecture - P_SAS_run_baseline
Save comparison outputs for dashboard/report consumption.