菜单
Assume the plan failed — then explain why. Three pessimists write failure narratives, two optimists rebut, a risk assessor weighs which failure modes are real.
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。
基于 SOC 职业分类
Generate a wide field of ideas, then pressure-test them. Five generators diverge, two challengers prune the weak ones, three synthesizers rank what survives.
Three-agent adversarial bug finder. Hunter overclaims every issue it can find, Skeptic disproves what it can, Referee arbitrates what survives. Scoring incentives force each role to behave honestly.
Dialectic process for reviewing, brainstorming, comparing tradeoffs, or stress-testing plans. Configurable modes, agent counts, and expert lenses.
Execute a pre-defined plan using implementation agents (no design changes)
Capture structured learnings (gotcha, pattern, decision, bug-fix) as JSONL per project. Cross-project searchable.
Adversarial stress-test of code, a plan, or an argument. Three critics attack, one defender rebuts, a referee judges, then a hostile auditor attacks the synthesis itself.
| name | premortem |
| description | Assume the plan failed — then explain why. Three pessimists write failure narratives, two optimists rebut, a risk assessor weighs which failure modes are real. |
Run /dialectic-review --premortem $ARGUMENTS
Read ~/.claude/skills/dialectic-review/SKILL.md for argument parsing, then read ~/.claude/skills/dialectic-review/premortem-prompts.md for the phase prompts. Follow the full three-phase process defined there. Any /dialectic-review flag is valid here — it passes straight through.
