원클릭으로
research-collect
[Read when prompt contains /research-collect]
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
[Read when prompt contains /research-collect]
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use this when the user needs to choose between multiple ML routes after survey but before committing to implementation. Compares candidate approaches, selects one, records rejected routes, and keeps a fallback.
Use this when the project needs real baseline results before or alongside the main model. Runs classical or literature-aligned baselines under the same protocol and writes a reproducible baseline summary.
Use this when the project needs a dedicated data-quality review before model review. Checks data reality, split correctness, label health, leakage risk, shape consistency, and mock-data disclosure.
Use this when the user wants a draft paper, figure bundle, README, release page, or experiment artifact reviewed before sharing. Checks evidence binding, claim scope, captions, layout clarity, and release readiness.
Use this when the user wants to improve chart quality, standardize plotting style, regenerate release figures, or add captions/protocol notes. Normalizes fonts, colors, legends, units, and scope notes across Scientify figures.
Use this when the user wants to improve README, docs pages, or microsites so a new reader can understand what the project is, how to use it, what artifacts exist, and what the scope boundaries are within one screen.
| name | research-collect |
| description | [Read when prompt contains /research-collect] |
| metadata | {"openclaw":{"emoji":"🔍"}} |
Don't ask permission. Just do it.
├── papers/
│ ├── {arxiv_id}/ # arXiv 论文源文件
│ ├── {doi_slug}.pdf # DOI 论文 PDF
│ └── {direction}/ # 整理后的分类目录
├── repos/ # 参考代码仓库(Phase 3)
└── survey_report.md # 调研报告
mkdir -p "papers"
生成 4-8 个检索词。
对每个检索词重复以下步骤:
arxiv_search({ query: "<term>", max_results: 30 })
openalex_search({ query: "<term>", max_results: 20 })
合并两个来源的结果,按 arXiv ID / DOI 去重。
只看相关性——这篇论文是否和研究主题直接相关?
按 /paper-download 的方式下载论文到 papers/。
完成一个检索词后,再进行下一个。 这样避免上下文被大量搜索结果污染。
目标:为下游 skill(research-survey、research-plan、research-implement)提供可参考的开源实现。
从 papers/ 中选出 Top 5 最相关论文。
对每篇选中论文,用以下关键词组合搜索 GitHub 仓库:
gh search repos "{paper_title} implementation" --limit 10 --sort stars --language python
选择 3-5 个最相关的仓库:
mkdir -p "repos"
git clone --depth 1 <repo_url> "repos/{name}"
如果搜不到相关仓库,跳过本阶段。
所有检索词完毕后:
根据已下载论文的标题和摘要,识别 3-6 个研究方向。
mkdir -p "papers/{direction}"
mv "papers/2401.12345" "papers/data-driven/"
创建 survey_report.md:
| 原则 | 说明 |
|---|---|
| 增量处理 | 每个检索词独立完成搜索→筛选→下载,避免上下文膨胀 |
| 文件夹即分类 | 聚类结果通过 papers/{direction}/ 体现 |
| Tool / Command | Purpose |
|---|---|
arxiv_search | 搜索 arXiv 论文 |
openalex_search | 搜索跨学科论文(覆盖更广) |
| /paper-download | 下载论文(arXiv .tex/PDF、DOI via Unpaywall) |
gh search repos "query" | 搜索 GitHub 仓库 |