據 AlphaMoat 統計,截至 2026-09,Academic Research Conflict 累計下載 1,227 次、獲 0 個星標,在全部 5,078 個 AI 技能中排名第 4,923 位,在「專業領域」分類(465 個)中排名第 450 位。

累計安裝

143

累計下載

1227

星標

全站排名

#4,923

全站前 97% · 「專業領域」前 97%

平台	累計安裝	累計下載	星標	評論
ClawHub ↗	22	932	-	-
SkillHub ↗	143	1227	-	—

各平台的計數口徑不同,統計時間不一致。

這個技能是做什麼的

可返回論文標題、作者、摘要、引用數、DOI 和開放獲取連結，並在可用時獲取全文。綜述由自動化流程綜合生成，引用、摘要和綜合結論必須對照原論文人工核驗後再用於學術或專業交付。呼叫會向 OpenAlex/Unpaywall 等服務傳送請求，可能附帶寫入的聯絡電子郵件；結果會快取到臨時目錄，也可能寫入使用者指定路徑。Markdown 報告預設帶有 Topanga 署名，分發前應檢查署名與披露要求。文件所列命令需要 Python。

資料釋出於 2026-10-29

可以用來做什麼

按主題、作者或 DOI 查詢學術論文
檢視論文引用鏈和開放獲取全文連結
生成按主題聚類並綜合論文資訊的綜述草稿

什麼時候用

需要學術論文發現或文獻綜述初稿時
可以核對論文來源、引用和結論時
允許相關 API 外聯、快取行為和指定路徑檔案寫入時

示例提示詞

以下是根據技能文件生成的示例,不代表實際執行結果。

為這個研究主題規劃檢索詞和綜述核驗清單，要求逐條檢查原論文與引用；不要呼叫學術 API 或寫入檔案。

月度資料趨勢

累計下載1227

星標-

2026-09 起統計方法調整:同名技能按作者分別統計,並覆蓋全部技能。圖中虛線為調整前的月份,與之後的資料不直接比較,也不計算跨越調整的增長。

月份	累計下載	環比	星標
2026-09	1227	—	-
2026-08	1005	+16.9%	-
2026-07	860	+37.8%	-
2026-06	624	+22.8%	-
2026-05	508	—	-
2026-03	282	—	-

SKILL.md 原文

以下是作者釋出的原始檔案,按純文字顯示,本站未做修改或稽核;其中的連結不可點選,命令請核實後再執行。抓取於 2026-10-23。

2.7 KB · ClawHub v1.0.0

---
name: academic-research
version: 1.0.0
description: Search academic papers and conduct literature reviews using OpenAlex API (free, no key needed). Use when the user needs to find scholarly papers by topic/author/DOI, explore citation chains, get structured paper metadata (title, authors, abstract, citations, DOI, open access URL), fetch full text of open access papers, or conduct automated literature reviews with theme identification and synthesis. Triggers on requests involving academic search, paper lookup, citation analysis, literature review, research synthesis, or scholarly reference gathering.
---

# Academic Research

Search 250M+ academic works via OpenAlex. No API key required.

展開全部(共 82 行)

Built by [Topanga](https://topanga.ludwitt.com) — AI Research Consultant

## Quick Start

### Search papers by topic
```bash
python3 scripts/scholar-search.py search "transformer architectures" --limit 10
```

### Search by author
```bash
python3 scripts/scholar-search.py author "Yann LeCun" --limit 5
```

### Look up by DOI
```bash
python3 scripts/scholar-search.py doi "10.1038/s41586-021-03819-2"
```

### Get citation chain (papers that cite a work)
```bash
python3 scripts/scholar-search.py citations "10.1038/s41586-021-03819-2" --direction both
```

### Deep read (fetch abstract + full text when available)
```bash
python3 scripts/scholar-search.py deep "10.1038/s41586-021-03819-2"
```

### JSON output for programmatic use
```bash
python3 scripts/scholar-search.py search "CRISPR" --json
```

## Literature Review Workflow

Automated multi-step literature review:

```bash
python3 scripts/literature-review.py "algorithmic literacy in education" --papers 30 --output review.md
```

This will:
1. Search for papers across multiple query variations
2. Deduplicate and rank by relevance + citations
3. Identify thematic clusters
4. Generate a structured synthesis in markdown

Options:
- `--papers N` — Target number of papers (default: 20)
- `--output FILE` — Write review to file (default: stdout)
- `--years 2020-2025` — Restrict publication year range
- `--json` — Output structured JSON instead of markdown

## Output Format

All search commands return structured data per paper:
- **Title** and publication year
- **Authors** (up to 5)
- **Abstract** (when available)
- **Citation count**
- **DOI**
- **Open access URL** (when available)
- **Source journal/venue**

## Tips

- OpenAlex sorts by relevance by default; use `--sort citations` for most-cited
- Combine `search` + `deep` for quick triage: search first, deep-read promising hits
- The literature review script caches results in `/tmp/litreview_cache/` to avoid re-fetching
- For full-text PDFs, pipe DOIs to your PDF extraction tool