ワンクリックで
red-teaming-attacks
Guidance for attack-algorithm work across PAIR, TAP, MCTS, and Crescendo in RedThread.
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 attack-algorithm work across PAIR, TAP, MCTS, and Crescendo in RedThread.
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
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.
Guidance for JudgeAgent scoring, guardrail synthesis, and anti-hallucination validation work.
Full research-plan-implement workflow for new features, architectural updates, multi-file changes, or any task with non-trivial blast radius in RedThread.
| name | red-teaming-attacks |
| description | Guidance for attack-algorithm work across PAIR, TAP, MCTS, and Crescendo in RedThread. |
Use this skill when building or modifying attack-generation logic.
docs/algorithms.mddocs/PHASE_REGISTRY.mddocs/AGENT_ARCHITECTURE.mddocs/TECH_STACK.md