rubric-writer
使用提取的主张和证据差距(新颖性/健全性/清晰度/影响)编写基于标题的同行评审报告(`output/REVIEW.md`)。**触发**:标题评审,审稿报告,同行评审撰写,审稿报告,REVIEW.md。**使用时间**:同行评审流程的最后阶段(C3),已经`output/CLAIMS.md` + `output/MISSING_EVIDENCE.md`(以及可选新颖性矩阵)。**跳过如果**:上游产品未就绪(索赔/证据缺口)或你不打算输出完整审稿报告。**网络**:无。**Guardrail**:给出行动建议(可操作的反馈),并覆盖新颖性/健全性/清晰度/影响;避免泛泛而谈。
📖 中文导读:使用提取的主张和证据差距(新颖性/健全性/清晰度/影响)编写基于标题的同行评审报告(`output/REVIEW.md`)。**触发**:标题评审,审稿报告,同行评审撰写,审稿报告,REVIEW.md。**使用时间**:同行评审流程的最后阶段(C3),已经`output/CLAIMS.md` + `output/MISSING_EVIDENCE.md`(以及可选新颖性矩阵)。**跳过如果**:上游产品未就绪(索赔/证据缺口)或你不打算输出完整审稿报告。**网络**:无。**Guardrail**:给出行动建议(可操作的反馈),并覆盖新颖性/健全性/清晰度/影响;避免泛泛而谈。 以下正文为该技能的原始 SKILL.md 内容(英文),上方安装命令可直接使用。
name: rubric-writer
description: |
Write a rubric-based peer review report (output/REVIEW.md) using extracted claims and evidence gaps (novelty/soundness/clarity/impact).
Trigger: rubric review, referee report, peer review write-up, 审稿报告, REVIEW.md.
Use when: peer-review pipeline 的最后阶段(C3),已有 output/CLAIMS.md + output/MISSING_EVIDENCE.md(以及可选 novelty matrix)。
Skip if: 上游产物未就绪(claims/evidence gaps 缺失)或你不打算输出完整审稿报告。
Network: none.
Guardrail: 给可执行建议(actionable feedback),并覆盖 novelty/soundness/clarity/impact;避免泛泛而谈。
Rubric Writer (referee report)
Goal: write a complete review that is grounded in extracted claims and evidence gaps.
Inputs
Required:
output/CLAIMS.mdoutput/MISSING_EVIDENCE.md
Optional:
output/NOVELTY_MATRIX.mdDECISIONS.md(if you have reviewer constraints/format)
Outputs
output/REVIEW.md
Workflow
If
DECISIONS.mdexists, follow any required reviewer format/constraints.One-paragraph summary (bounded)
- Summarize the paper’s goal + main contributions using
output/CLAIMS.md.
- Summarize the paper’s goal + main contributions using
Rubric sections
- Novelty: reference
output/NOVELTY_MATRIX.md(if present) and/or the related work discussion. - Soundness: reference the concrete gaps from
output/MISSING_EVIDENCE.md. - Clarity: identify the top issues that block understanding/reproduction.
- Impact: discuss likely relevance if the issues were fixed.
- Novelty: reference
Actionable feedback
- Major concerns: each with “problem → why it matters → minimal fix”.
- Minor comments: clarity, presentation, missing details.
Final recommendation
- Choose a decision label and justify it primarily via soundness + evidence quality.
Definition of Done
-
output/REVIEW.mdcovers novelty/soundness/clarity/impact. - Major concerns are actionable (each has a minimal fix).
- Critiques are traceable to
output/CLAIMS.md/output/MISSING_EVIDENCE.md(not free-floating).
Troubleshooting
Issue: review turns into a rewrite of the paper
Fix:
- Cut; keep to critique + actionable fixes and avoid adding new content.
Issue: review is generic (“needs more experiments”)
Fix:
- Replace with concrete gaps from
output/MISSING_EVIDENCE.md(which baseline, which dataset, which ablation).