google-scholar-guide

本条目面向文献与学术工具场景,提供“google-scholar-guide”技能的目录入口。公开标签:learning、谷歌学术、文献检索、布尔搜索。请通过固定上游版本核对实际功能、依赖与权限;此页为 Skillπ 独立编写的用途介绍和原站链接,不代表运行安全保证。原文与附件依各自许可开放。

仓库
brycewang-stanford/Auto-Empirical-Research-Skills
仓库最近推送
Stars
5,023
Forks
578
Issues / PRs
0

安装方式

先用 Prompt 核对来源,也可切换到安装命令或下载可用的安装包。

安装方式

用 AI 助手安装

复制提示词,让助手先核对固定版本和依赖。

查看 Prompt收起 Prompt
先检查当前 Agent 是否已安装 SkillPI Skill Finder。如果尚未安装,请按官方仓库的说明安装并启用:https://github.com/Findskills/skillpi。然后使用 Skill Finder 打开此 SkillPI 详情页并定位 "google-scholar-guide":https://skillpi.com/zh/skills/deepskill-a29962fbefd0a7ea5921f09b5f4da4894968902ff53e82d7fec259d9ec55acf0。安装前核对上游来源和版本:https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba/skills/43-wentorai-research-plugins/skills/literature/search/google-scholar-guide/SKILL.md。来源不一致时停止并说明差异。核对通过后,用 Skill Finder 安装目标 Skill,并报告安装路径和来源版本。

此命令从 GitHub 来源仓库获取指定技能。运行前请先查看源文件。

运行工具
npx skills add https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba/skills/43-wentorai-research-plugins/skills/literature/search/google-scholar-guide --skill google-scholar-guide
许可协议: —

来源与配置

查看 GitHub 源码

brycewang-stanford/Auto-Empirical-Research-Skills固定提交 bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba

配置方式待核实

请查看原始来源中的适用工具、依赖和权限要求。

安装实测待补充

本条目面向文献与学术工具场景,提供“google-scholar-guide”技能的目录入口。公开标签:learning、谷歌学术、文献检索、布尔搜索。请通过固定上游版本核对实际功能、依赖与权限;此页为 Skillπ 独立编写的用途介绍和原站链接,不代表运行安全保证。原文与附件依各自许可开放。

↓ 0 下载 ↗ 0 分享点击

文件浏览

在原站浏览文件 ↗

原始 SKILL.md

打开原文 ↗
---
name: google-scholar-guide
description: "Advanced Google Scholar search techniques for comprehensive literature discovery"
metadata:
  openclaw:
    emoji: "🔎"
    category: "literature"
    subcategory: "search"
    keywords: ["academic database search", "search strategy", "Boolean search", "advanced search", "Google Scholar"]
    source: "wentor"
---

# Google Scholar Guide

A skill for leveraging Google Scholar's full capabilities for academic literature search. Covers advanced search operators, citation tracking, alert configuration, and strategies for systematic and comprehensive retrieval.

## Advanced Search Operators

### Core Operators

| Operator | Syntax | Example | Effect |
|----------|--------|---------|--------|
| Exact phrase | `"..."` | `"machine learning"` | Matches exact phrase |
| OR | `OR` | `"deep learning" OR "neural network"` | Matches either term |
| Exclude | `-` | `transformer -electrical` | Excludes term |
| Author | `author:` | `author:"Y LeCun"` | Filter by author |
| Source | `source:` | `source:"Nature"` | Filter by journal |
| Title only | `intitle:` | `intitle:"attention mechanism"` | Search in title only |
| Date range | Custom range | Via Advanced Search UI | Limit publication years |
| File type | `filetype:` | `filetype:pdf` | Specific file formats |

### Constructing Effective Queries

```python
def build_scholar_query(concepts: list[list[str]], exclude: list[str] = None,
                         title_only: bool = False, author: str = None,
                         source: str = None) -> str:
    """
    Build a structured Google Scholar query from concept groups.

    Args:
        concepts: List of concept groups, each a list of synonyms
                  Groups are ANDed together, synonyms are ORed
        exclude: Terms to exclude
        title_only: Search in title only
        author: Author name filter
        source: Journal/source filter
    Returns:
        Formatted Google Scholar query string
    """
    # Build concept groups with OR
    groups = []
    for concept_group in concepts:
        if len(concept_group) == 1:
            groups.append(f'"{concept_group[0]}"')
        else:
            terms = ' OR '.join(f'"{term}"' for term in concept_group)
            groups.append(f'({terms})')

    # AND the concept groups together
    query = ' '.join(groups)

    # Apply title restriction
    if title_only:
        query = f'intitle:{query}'

    # Add exclusions
    if exclude:
        for term in exclude:
            query += f' -{term}'

    # Add author filter
    if author:
        query += f' author:"{author}"'

    # Add source filter
    if source:
        query += f' source:"{source}"'

    return query

# Example: find papers on transfer learning for medical imaging
query = build_scholar_query(
    concepts=[
        ["transfer learning", "domain adaptation", "fine-tuning"],
        ["medical imaging", "radiology", "pathology images"],
        ["deep learning", "convolutional neural network"]
    ],
    exclude=["survey", "review"],
    title_only=False
)
print(query)
# Output: ("transfer learning" OR "domain adaptation" OR "fine-tuning")
#         ("medical imaging" OR "radiology" OR "pathology images")
#         ("deep learning" OR "convolutional neural network") -survey -review
```

## Citation Tracking Strategies

### Forward and Backward Citation Chaining

```
Seed Paper (a highly relevant paper you already know)
  |
  +--> "Cited by" link -> Forward citation tracking
  |    (who cited this paper? newer related work)
  |
  +--> Reference list -> Backward citation tracking
       (what did this paper cite? foundational work)

Repeat for each highly relevant paper found.
Stop when you reach saturation (no new relevant papers appearing).
```

### Identifying Key Papers

Use citation metrics strategically:

```python
def identify_key_papers(search_results: list[dict],
                         min_citations: int = 10) -> list[dict]:
    """
    Identify key papers from search results using citation analysis.

    Args:
        search_results: List of papers with 'title', 'year', 'citations'
        min_citations: Minimum citation threshold
    """
    import datetime
    current_year = datetime.datetime.now().year

    for paper in search_results:
        age = max(1, current_year - paper['year'])
        paper['citations_per_year'] = paper['citations'] / age

        # Classify influence
        if paper['citations_per_year'] > 50:
            paper['influence'] = 'landmark'
        elif paper['citations_per_year'] > 20:
            paper['influence'] = 'highly_influential'
        elif paper['citations_per_year'] > 5:
            paper['influence'] = 'influential'
        else:
            paper['influence'] = 'standard'

    # Filter and sort
    filtered = [p for p in search_results if p['citations'] >= min_citations]
    return sorted(filtered, key=lambda x: x['citations_per_year'], reverse=True)
```

## Google Scholar Alerts

Set up alerts to stay current:

1. Go to Google Scholar and run your search query
2. Click "Create alert" in the left sidebar
3. Configure email frequency (as-it-happens or weekly digest)
4. Use the same carefully constructed query from your search strategy

Best practices for alerts:
- Create separate alerts for each major concept group
- Use narrow, specific queries to reduce noise (10-20 results per alert is ideal)
- Review and refine alert queries quarterly

## Google Scholar Profiles

### Leveraging Author Profiles

- Follow prolific researchers in your field to get notifications of their new publications
- Use the "Related articles" feature on author profile pages
- Check co-author networks to discover related research groups
- The h-index and i10-index on profiles can help gauge researcher impact, but use with caution across different fields

## Limitations and Complementary Databases

Google Scholar has known limitations:
- No controlled vocabulary or MeSH terms (unlike PubMed)
- Cannot filter by study design or methodology
- Includes non-peer-reviewed sources (preprints, theses, slides)
- Citation counts may include self-citations and non-scholarly citations

For systematic reviews, always supplement Google Scholar with structured databases: PubMed/MEDLINE, Web of Science, Scopus, and domain-specific databases (e.g., IEEE Xplore, PsycINFO, EconLit). Document the number of results from each database for your PRISMA flow diagram.

版本历史

  1. v2026.07 GitHub ↗
    原版更新说明

    ## Highlights - **First tagged release.** Every gate is green: `make check` (validate + 183 unit tests + eval-harness + numeric benchmarks), validate-catalog, quality-evals, and OpenSSF Scorecard on `main`. - **Rigor double loop at 13 method families.** Each family closes taxonomy tag → eval scenario (does the agent avoid the method's known traps?) → deterministic numeric benchmark (does it recover the true effect?). New this cycle: heterogeneous treatment effects (CATE) and quantile treatment effects (QTE). - **Paper-WorkFlow flagship at 29/29 executable rigor gates**, now merged to its `main` with a drift-gated README badge — the credibility artifact is checked by CI, so it can never silently go stale ([RIGOR.md](https://github.com/brycewang-stanford/Paper-WorkFlow/blob/main/RIGOR.md)). - **1,150 vendored skills / 69 collections**, all license-audited, security-scanned, tracked in a machine-readable catalog with CI-enforced freshness, and importable as a single whole-repo router skill. - **Hardened weekly upstream syncs**: synced trees must pass the full gate before merge; this cycle both sync PRs were verified, patched (StatsPAI's SkillOpt execution-gate card restored), and merged. - **First-party plugin marketplace** (Python / R / Stata empirical-analysis plugins + guide) shipped in the previous cycle, now under a tagged version. ## Known Follow-Ups - Ecosystem benchmark comparison (AERS vs econometrics agents on the shared benchmark suite) — [PLAN-2026-07 week 3](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/main/docs/PLAN-2026-07.md). - Decomposition (Oaxaca–Blinder) and shift-share (Bartik) method families (weeks 3–4). - GitHub Pages catalog site, README demo screenshots, five-language README consistency script (week 4). ## Catalog - Top-level collections: **69** - `SKILL.md` files: **1150** - Cataloged agent tools: **335** ([`tools/CATALOG.md`](../tools/CATALOG.md)) ## Methodological rigor - Method families in the coverage map: **13** ([`RIGOR_COVERAGE.md`](RIGOR_COVERAGE.md)) - Eval scenarios: **26** (138 rubric items, 122 auto-checkable) ([`../eval-harness/`](../eval-harness/README.md)) - Benchmark tasks: **13** (70 gold checks, 58 required) ([`../benchmark/`](../benchmark/README.md)) ### Method families (skills tagged) - `iv`: 27 - `rdd`: 25 - `panel-fe`: 19 - `staggered-did`: 17 - `bayesian`: 13 - `did`: 10 - `event-study`: 10 - `matching`: 10 - `synthetic-control`: 10 - `cate`: 8 - `dml`: 8 - `survival`: 3 - `quantile`: 2 ### Eval scenarios by category - `causal-identification`: 14 - `citation-hygiene`: 1 - `reproducibility`: 2 - `research-integrity`: 1 - `runtime-safety`: 1 - `statistical-validity`: 2 - `writing-compliance`: 3 - `writing-style`: 2 ## License buckets - AGPL-3.0: 1 - Apache-2.0: 1 - CC-BY-NC-4.0 (non-commercial): 1 - CC-BY-SA-4.0: 1 - CC-BY-SA-4.0 (repository default): 4 - GPL-3.0: 1 - MIT: 35 - MIT Non-Commercial: 1 - Mixed (per-skill; see folder): 2 - UNKNOWN - check upstream: 22 ## Quality gates - `make check` — catalog/provenance/audit/eval freshness, repo hygiene, Paper-WorkFlow gates, stdlib unit tests, eval-harness lint + graded smoke, and the strict numeric benchmark (reference-gold drift fails the build). - External links and OpenSSF Scorecard run on their scheduled workflows.

当前收录版本

0.0.1

核对来源版本 ↗

质量评测

满分 100。前四项来自 DeepSkill 收录的质量报告。

场景价值85/100
评分依据

提供高级谷歌学术搜索技巧,涵盖布尔搜索、引用追踪、警报配置等,实用性强

触发精准95/100
评分依据

description 明确,keywords 覆盖核心概念,触发词精准完整

结构规范90/100
评分依据

结构清晰,分章节详细,含表格、代码示例、步骤说明

执行可靠90/100
评分依据

Python 函数逻辑完整,参数明确,示例可运行

证据可验 (前四项均值)90/100
计算方式

取前四项原始分值的算术平均,四舍五入取整。可通过收录报告核对各项评分与说明,运行记录需单独查证。

权限与使用前检查

根据当前主文档自动整理,命中内容可能是示例或防护说明;不是实际权限声明,也未覆盖附件、外部依赖或运行行为。

未从主文档识别到上述常见操作,不能据此判断无需权限或没有风险。

本站展示提示不会授予权限。涉及文件改动、密钥、外部发送或费用时,仍由你使用的工具按需确认。

安全评级与访问范围

risk · 静态证据核验,不代表运行安全保证。

使用前请由宿主核对并授权实际文件读写、外部服务和联网目的地;本站的核验不会授予任何运行权限。

来源与使用声明 SkillPi 的部分技能资料来自公开来源或创作者提交。第三方内容的权利归各自权利人所有。安装或运行前,请查看原站的许可、权限要求和使用风险。

来源与使用

请按详情页的作者、原始来源和许可证核对使用条件,运行前检查技能需要的权限。目录收录不等于已验证安装或安全性。