ワンクリックで
defense-and-eval
Guidance for JudgeAgent scoring, guardrail synthesis, and anti-hallucination validation work.
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
Guidance for JudgeAgent scoring, guardrail synthesis, and anti-hallucination validation work.
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。
Instructions for triggering external Context7 connections
Lightweight research-plan-implement workflow for small tweaks, isolated bugfixes, copy edits, and low-blast-radius polish in this repo. Use when the change can be understood from 1-3 files and stays inside one subsystem without changing shared data flow.
Implements tree-based attack branching and prompt refinement optimization.
Fetch external library or framework documentation only when local docs are insufficient.
Full research-plan-implement workflow for new features, architectural updates, multi-file changes, or any task with non-trivial blast radius in RedThread.
Audit a plan for missing architecture, evaluation, safety, or verification coverage before implementation.
SOC 職業分類に基づく
| name | defense-and-eval |
| description | Guidance for JudgeAgent scoring, guardrail synthesis, and anti-hallucination validation work. |
Use this skill when touching scoring, judging, telemetry, or defense synthesis.
docs/ANTI_HALLUCINATION_SOP.mddocs/DEFENSE_PIPELINE.mddocs/PHASE_REGISTRY.mddocs/TECH_STACK.md