메뉴
Use when a claim, plan, spec, doc, or design must be attacked against source evidence before implementation or approval. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when debugging a failing test, broken build, runtime error, or unexpected system behavior. Drives hypothesis-based investigation, root-cause fixes, verification, and reusable learning capture.
Use when fixing broken behavior and the priority is reproduce, root cause, regression proof, and the smallest safe repair. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when reviewing code changes with explicit stage, target, and focus so own-code checks and others’ PR reviews stay distinct but share one contract. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when the deliverable is docs or reference material and every claim must stay tied to observed behavior or cited source evidence. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when adding or changing product behavior that must ship with explicit purpose, scenarios, and verification. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when improving structure without changing behavior, with explicit invariants and verification that the contract stays the same. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
| name | adversarial-review |
| description | Use when a claim, plan, spec, doc, or design must be attacked against source evidence before implementation or approval. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true. |
| status | draft |
Start when a proposal, claim, workflow, spec, architecture note, or support statement needs skeptical review before implementation or adoption.
artifact_type — plan, spec, doc, code diff, design, workflow, or claim setclaim_or_goal — what is being testedsources — evidence allowed for reviewstrictness — normal | adversarialvalidate — required review output shapeStress the artifact against repo principles, source evidence, and explicit constraints before it hardens into code or policy.
n/a — read-only review workflow.
n/a — no behavior change is implemented in this workflow.
Stop only when the artifact has a concrete verdict, evidence-backed findings, and unresolved disagreements are local and explicit.
Stop and report when the review lacks enough source material, the baseline principles are unclear, or the requested verdict would require speculation.