summarize
Summarize extracted paper text into concise Markdown memory for later Stage 2 and Stage 4 background use, with fixed section…
Polish (rephrase) a rebuttal message template for clarity and professionalism while preserving the original structure, tone, and intent.
$ npx -y skills add runtsang/rebuttalstudio --skill polish --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/polishContext preview
The summary Claude sees to decide when to auto-load this skill.
Polish (rephrase) a rebuttal message template for clarity and professionalism while preserving the original structure, tone, and intent.
name: template-polish description: Polish (rephrase) a rebuttal message template for clarity and professionalism while preserving the original structure, tone, and intent.
Rephrase a rebuttal-related message (e.g. nudge email, status update) so it reads naturally and clearly.
1. **Preserve original structure**: Keep the same paragraph order, greeting, sign-off, and line breaks. Do not merge or split paragraphs. 2. **Preserve original tone**: The input is already semi-formal academic correspondence. Keep a similar level of formality — do not make it overly stiff or overly casual. 3. **Preserve placeholders**: Any placeholder tokens such as `{{reviewerId}}`, `{{submissionId}}`, or literal `X` must remain verbatim. 4. **Keep meaning unchanged**: Do not add, remove, or alter the substantive content. 5. **Light touch**: Only rephrase for clarity, conciseness, and naturalness. Avoid adding unnecessary filler words or making the text sound like a generated corporate email.
Return **JSON only** (no markdown fences) with this schema:
{"text": "...polished text..."}A rebuttal editor for researchers to craft high-quality academic rebuttals — so you can focus on what to say, not how to format it.
Summarize extracted paper text into concise Markdown memory for later Stage 2 and Stage 4 background use, with fixed section…
Break down full ARR (ACL Rolling Review) reviewer responses into structured rebuttal units. Use when input contains ARR reviewer…
Break down full ICLR reviewer responses into structured rebuttal units. Use when input contains reviewer…
Break down full ICML reviewer responses into structured rebuttal units. Use when input contains reviewer…
Break down full NeurIPS reviewer responses into structured rebuttal units. Use when input contains NeurIPS reviewer fields…