菜单
Use when the user asks for a deep code review, adversarial review, multi-agent review, risk-ranked review, PR review, security-sensitive review, or implementation verification with concrete file and line evidence.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Use when the user asks to debug a failing test, runtime error, regression, flaky behavior, production-like failure, root-cause analysis, or loop-until-done repair workflow.
Use when the user asks for source-backed research, official-documentation lookup, technical comparison, dependency evaluation, repository investigation plus synthesis, or fan-out research with ranked conclusions.
Use when the user asks for a dynamic workflow, multi-agent workflow, task-specific harness, complex task orchestration, fan-out synthesis, adversarial verification, generate-and-filter exploration, tournament-style solution search, or loop-until-done execution in Codex.
Wireframe workflow for low-fidelity structure, hierarchy, and information layout exploration.
Animation workflow for motion-heavy artifacts, scene timing, and browser playback review.
Canva-oriented handoff workflow for asset packaging, layout notes, and transfer readiness.
基于 SOC 职业分类
| name | dynamic-code-review |
| description | Use when the user asks for a deep code review, adversarial review, multi-agent review, risk-ranked review, PR review, security-sensitive review, or implementation verification with concrete file and line evidence. |
| metadata | {"short-description":"Adversarial code review workflow"} |
Use this skill for rigorous code review with explicit evidence and independent challenge.
Start by identifying:
Findings lead the response. Order them by severity and include file and line references.
explore for independent codebase lookup when subagent review is requested.critic for adversarial challenge when subagent review is requested.Return:
For each finding include: