// Break down full ICLR reviewer responses into structured rebuttal units. Use when input contains reviewer summary/presentation/contribution/strength/weakness/question text and the goal is to split weaknesses/questions into granular R-style response items while preserving original wording for quoted issues.
Multi-stage rebuttal analysis skill for RebuttalStudio. Use when organizing reviewer comments into stage-specific conference workflows, including stage1 breakdown, stage2 refinement, stage4 multi-round follow-up, and stage5 final remarks generation.
Condense rebuttal prose into fewer words without changing the original meaning. Use when a response block, paragraph, or selected passage is too long but all technical content, citations, and commitments must stay intact. Supports academic English.
Summarize extracted paper text into concise Markdown memory for later Stage 2 and Stage 4 background use, with fixed section headings and no fabricated claims.
Break down full NeurIPS reviewer responses into structured rebuttal units. Use when input contains NeurIPS reviewer fields (Summary, Strengths and Weaknesses, Questions, Limitations) and numeric scores (Rating, Confidence, Quality, Clarity, Significance, Originality). Splits questions and limitations into granular response items while preserving original wording for quoted issues.
Refine a Stage2 NeurIPS rebuttal draft into polished, reviewer-facing prose in the author's style; preserve factual grounding, optionally prepend a courteous opening phrase, and normalize tables/code/formulas into Markdown.
Break down full ARR (ACL Rolling Review) reviewer responses into structured rebuttal units. Use when input contains ARR reviewer fields (Paper Summary, Strengths, Weaknesses, Comments/Suggestions) and numeric scores (Confidence, Soundness, Excitement, Overall Assessment, Reproducibility). Splits weaknesses and comments/suggestions into granular response items while preserving original wording for quoted issues.
| name | stage1-iclr-breakdown |
| description | Break down full ICLR reviewer responses into structured rebuttal units. Use when input contains reviewer summary/presentation/contribution/strength/weakness/question text and the goal is to split weaknesses/questions into granular R-style response items while preserving original wording for quoted issues. |
Apply the shared template first:
skills/stage1/template/SKILL.mdThen apply only the ICLR-specific overrides below.
Extract exactly these five keys (numbers only):
rating <- ICLR ratingconfidence <- ICLR confidencesoundness <- ICLR soundnesspresentation <- ICLR presentationcontribution <- ICLR contributionsummary <- summarystrength <- strengthweaknessquestion# Stage1 ICLR Breakdown## Scores must contain exactly the five keys above.If reviewer text mixes free-form paragraphs and bullets, keep template splitting rules unchanged and split only by independent concerns.