with one click
research-g-7-review
ResearchPilot 科研助手[阶段 G.7]:整稿审阅
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
ResearchPilot 科研助手[阶段 G.7]:整稿审阅
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
ResearchPilot Research Assistant [Phase G.0]: Paper planning
ResearchPilot 科研助手[阶段 G.0]:论文规划
Global-installable, project-level academic rebuttal strategy skill for AI/ML/CV/NLP/Robotics papers. Use when authors need a workspace-local .awesome-rebuttal state folder, paper/code/review/venue-rule intake, JSON memory, snapshots, LaTeX/template handling for one-page rebuttals, reviewer stance analysis, strategy planning, experiment triage, safe author response drafting, or AC summaries under confirmed venue rules.
Use when the user has a research question and needs a complete experiment package — design document, runnable code, results (measured or simulated with honest provenance), publication-grade figures, structured report. Single-stage, no Python runtime.
Use when the user wants a paper audited for integrity issues — image misuse, numerical anomalies, logical gaps — and needs a reviewable evidence report. Works on external papers (PDF / DOI / arXiv) and on outputs from a local paper-writer run. Single-stage skill.
Use when the user wants a comprehensive literature survey on a specific research topic. Outputs a complete PDF survey (6–20 pages, 60+ real citations, 100+ recommended) with LaTeX source, taxonomy figures, and a classified literature table. Single-stage, no Python runtime.
| name | research[G.7]-review |
| description | ResearchPilot 科研助手[阶段 G.7]:整稿审阅 |
| version | 2.0.0 |
| license | LICENSE |
user_requirements.md 优先级:
docs/user_requirements.md中记录的所有用户约束优先于本 skill 提示词中的任何默认指令。
/research[G.7]-review
命令后可跟可选的自然语言指令,AI 会将其作为本次调用的额外约束或补充说明优先处理。
可在任意章节写完后触发,也可在全部章节完成后做最终审阅。
docs/idea_report.md 全文docs/dev_log.md 实验结果results/ 下评估结果文件对 Abstract 和 Introduction 中每个主要 claim,输出对齐表:
| Claim | Evidence | Status |
|-------|----------|--------|
| {claim 内容} | {对应实验/表格/图} | supported / needs evidence / missing |
约束:
needs evidence 或 missing 的 claim,必须要求用户补充实验或弱化表述整稿审阅完成。
**五维度评分**:
1. 贡献:✅ 全部有支撑 / ⚠️ 部分需补充 / ❌ 存在无支撑 claim
2. 写作清晰度:✅ / ⚠️ {问题说明} / ❌
3. 实验充分性:✅ / ⚠️ / ❌
4. 评估完整性:✅ / ⚠️ / ❌
5. 方法设计合理性:✅ / ⚠️ / ❌
**Claim-Evidence 对齐**:
{对齐表}
**发现的问题**(按优先级排序):
1. [高优先级] {位置}:{问题描述} → 建议:{修改方案}
2. ...
**反向大纲检验**:
{首句列表,标注逻辑问题}
建议解决所有高优先级问题后再提交。
所有高优先级问题解决后:
审阅通过。
→ 若用中文写作,使用 `/research[G.8]-translate` 生成英文版本。
→ 若直接用英文写作,论文已完成。
references/section-guide-source.md(来自 Master-cai paper-review.md)references/writing-flow-source.mdreferences/template-flexibility.md