ワンクリックで
orca-eval
Evaluate ORCA Framework workflows by scoring trajectories, artifact quality, and final usefulness.
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。
メニュー
Evaluate ORCA Framework workflows by scoring trajectories, artifact quality, and final usefulness.
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。
SOC 職業分類に基づく
Create a host-native `/goal` prompt for bounded ORCA plan work, especially when the user wants an agent to keep working through ready ORCA plans, delegate blocker fixes to subagents, record true blockers, and move on without stalling.
Implement planned changes with scoped edits, verification, and respect for existing project patterns.
Create bounded delegation briefs and structured executor returns for ORCA Framework workflows.
Prepare release readiness checks, release notes, rollback guidance, and handoff.
Record time, retries, and optional token, cache, and cost metrics for ORCA Framework workflows without fabricating precision.
Provide lightweight, skill-sensitive coaching without slowing down normal ORCA Framework execution.
| name | orca-eval |
| description | Evaluate ORCA Framework workflows by scoring trajectories, artifact quality, and final usefulness. |
A trajectory-based evaluation workflow for judging how well ORCA Framework behaved, not just what it produced.
Use when validating a workflow, comparing changes to ORCA Framework, or reviewing whether a command or skill is trustworthy.
Do not use as a substitute for product QA or security review.
templates/eval-report.mdThe report should explain why a workflow passed or failed and what to improve next.
Works with orca-trace, orca-spec, orca-plan, QA skills, and orca-ship.