一键导入
vr-rebuttal
Writes a systematic rebuttal to reviewer comments. Classifies each comment and determines accept/rebut/partial-accept to generate a persuasive response.
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。
菜单
Writes a systematic rebuttal to reviewer comments. Classifies each comment and determines accept/rebut/partial-accept to generate a persuasive response.
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
Analyzes existing experiment results and designs/executes ablation experiments to verify the contribution of each component.
Skill for writing English text that reads as naturally human-authored, and for reviewing existing English text to detect and fix AI writing tells. Use this skill whenever the user asks to "write naturally", "remove AI tone", "make it sound human", "avoid AI tells", "de-AI", "humanize", "anti-AI writing", "sound less like ChatGPT", or any variation implying they want text free of detectable AI patterns. Also trigger when the user asks to review or edit text for AI-sounding patterns, or when they paste text and ask "does this sound like AI?" Even if the user simply says "write me a blog post" or "write an essay" without explicitly mentioning AI — if this skill is available, apply its principles by default to produce more natural prose.
Brainstorm research ideas and formulate research hypotheses. When a user presents a research topic or area of interest, explore related ideas.
Create a detailed experiment plan for a selected research idea. Define experiment variables, metrics, baselines, and datasets.
Deep literature review with multi-stage search, citation graph traversal, and full-text analysis. Uses Semantic Scholar API, arXiv HTML reading, and snowball search to produce comprehensive research landscape analysis.
Analyzes experiment results and generates publication-quality figures for papers using matplotlib.
| name | vr-rebuttal |
| description | Writes a systematic rebuttal to reviewer comments. Classifies each comment and determines accept/rebut/partial-accept to generate a persuasive response. |
| user-invocable | true |
| argument-hint | ["paper-directory"] |
Writes a systematic rebuttal to reviewer comments.
$ARGUMENTS - Paper directory path (directory containing review.md)
Alternatively, the user may directly provide reviewer comment text.
papers/<dir>/review.mdClassify each comment:
Determine the response direction for each comment:
Write a persuasive response for each comment:
When building evidence for "Rebut" responses, read .claude/skills/_shared/paper-search-protocol.md
and execute a Level 2 search focused on: "papers supporting [claim being defended] or
demonstrating precedent for [methodological choice]". Cite discovered papers as evidence.
/vr-ablation-studyOrganize the revisions promised in the rebuttal in diff format:
Save the results in the paper directory.
papers/<paper-dir>/
├── rebuttal.md # Rebuttal document
└── revision_plan.md # Paper revision plan
# Rebuttal: [Paper Title]
Date: [YYYY-MM-DD]
## General Response
[Overall expression of gratitude and summary of major changes]
---
## Reviewer Comments and Responses
### [Major] Comment 1: [Comment summary]
> [Reviewer's original comment]
**Response: [Accept/Rebut/Partial Accept]**
[Detailed response]
**Revisions**: [Specific revision details, if applicable]
---
### [Major] Comment 2: [Comment summary]
> [Reviewer's original comment]
**Response: [Accept/Rebut/Partial Accept]**
[Detailed response]
---
### [Minor] Comment 3: [Comment summary]
> [Reviewer's original comment]
**Response: Accept**
[Revision details]
---
## Summary of Changes
| # | Comment | Response | Revision Location |
|---|---------|----------|-------------------|
| 1 | [Summary] | Accept | Section 3.2 |
| 2 | [Summary] | Rebut | - |
| 3 | [Summary] | Accept | Section 5 |
## Additional Experiments Needed
- [ ] [Experiment 1 description] → Recommend running `/vr-ablation-study`
- [ ] [Experiment 2 description] → Can reuse existing experiments
## Newly Cited References
[BibTeX entries for papers discovered during evidence search]